Abstract

A transmission hyperspectral microscopic imager (THMI) that utilizes machine learning algorithms for hyperspectral detection of microalgae is presented. The THMI system has excellent performance with spatial and spectral resolutions of 4 µm and 3 nm, respectively. We performed hyperspectral imaging (HSI) of three species of microalgae to verify their absorption characteristics. Transmission spectra were analyzed using principal component analysis (PCA) and peak ratio algorithms for dimensionality reduction and feature extraction, and a support vector machine (SVM) model was used for classification. The average accuracy, sensitivity and specificity to distinguish one species from the other two species were found to be 94.4%, 94.4% and 97.2%, respectively. A species identification experiment for a group of mixed microalgae in solution demonstrates the usability of the classification method. Using a random forest (RF) model, the growth stage in a phaeocystis growth cycle cultivated under laboratory conditions was predicted with an accuracy of 98.1%, indicating the feasibility to evaluate the growth state of microalgae through their transmission spectra. Experimental results show that the THMI system has the capability for classification, identification and growth stage estimation of microalgae, with strong potential for in-situ marine environmental monitoring and early warning detection applications.

© 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

1. Introduction

Microalgae are an indispensable part of marine ecosystems and play an important role for photosynthesis, energy conversion, and also for water quality evaluation. They are a rich source of food for plankton, and can also act as an indicator of eutrophication and water components, such as chlorophyll and carotenoid. On the other hand, outbreaks of harmful or toxic microalgae, such as red tides and algal blooms, are marine pollution issues that can cause severe economic harm to e.g. aquaculture industry. Therefore, methods for identifying and monitoring microalgae are of importance. Traditional methods for microalgae detection include remote sensing for the macro scale and optical microscopic observation for the micro scale. Remote sensing has been widely used for studying shallow marine and fresh water benthic environments [1] and aims at mapping the distribution of either a single benthic habitat, or several different benthic habitats, e.g. heterogeneous communities of seagrasses, coral reefs, and algae [24]. However, due to the limitations of spatial resolution and sensitivity, microalgae can only be observed when they are clustered or at high local concentrations. Inspection time delays limit the usability for early warning detection, which may prevent their use for effective mitigation of serious environmental damages. Optical microscopy methods for the detection of microalgae require skilled professionals trained to identify and classify various categories through morphological features, which is time consuming and very costly [5,6]. Even so, accuracy, sensitivity and specificity can be inadequate, especially for some microalgae that cannot readily be identified by morphological characteristics.

With the advantages of being non-invasive, having high efficiency and high throughput, hyperspectral imaging (HSI) technology can simultaneously obtain spatial and spectral information by generating a three-dimensional hyperspectral cube (x, y, λ) [7]. As obtained spectra can provide rich complex structural information that is related to the vibration behavior of molecular bonds or the absorption of a specific substance, HSI is used for a wide range of applications, such as on-site monitoring [810], food quality assessment [11,12] and biomedicine applications [13,14]. Higher spatial resolutions are required to image small objects, and thus, examples of combining HSI and optical microscopy, e.g. for pathological diagnosis [15,16], cancerous grades evaluation [17] and tumor classification [18], are being reported in the literature with increasing frequency. Several methods for HSI data acquisition, including spatial-scanning and spectral-scanning techniques, exist. Based on the principle of line-scanning, spatial-scanning collects hyperspectral information from a single narrow slit and reconstructs a spatial image through push-broom or whisk-broom scanning. Both push-broom and whisk-broom scanning require relative movement between camera and sample; push-broom implementations typically rely on the movement of a motorized stage to realize a wide scanning range [19], while whisk-broom utilizes the motion of a galvo-mirror, which has the advantages of high imaging speed and efficiency [20]. In contrast, spectral-scanning techniques aim to progressively collect all spatial information at different wavelengths; a single wavelength is captured each time, and the scan is performed by changing the central wavelength of the spectral channel to be imaged. Examples of spectral-scanning systems are filter wheels [21], liquid crystal tunable filters (LCTFs) [22], and acousto-optic tunable filters (AOTFs) [23].

Due to the high spectral resolution and broad spectral range, a captured hyperspectral cube typically covers hundreds of wavelength bands, with a spectral data set that is highly co-linear containing much redundant information. To provide reliable data input for classification and identification, it is convenient to make use of computational methods, e.g. machine learning algorithms, to investigate intrinsic relationships and extract difference information between large amounts of samples. Dimensionality reduction of superfluous data has proved effective to enhance classification accuracy and robustness of a model. A variety of feature reduction methods have been used to analyze spectral data, such as principal component analysis (PCA), local preserving projections (LPP), neighborhood preserving embedding (NPE), and linear discriminant analysis (LDA) [24]. Following feature retrieval, a supervised classifier, e.g. support vector machine (SVM), random forest (RF), neural network (NN) or multinomial logistic regression (MLR), is applied to make accurate classification and prediction [25]. Deep learning techniques have recently been utilized for automatic HSI feature extraction and classification [26]. Making use of both spectral and spatial properties of data for specific scenarios have also been reported [27].

To date, a few experimental studies on microalgae using HSI techniques that demonstrate great potential for environmental and ecological applications, have been reported. Wei and Bi et al. [28,29] developed a hyperspectral microscopic imaging system for species identification and survival competition analysis of microalgae, however the utilization of spectral-scanning method through LCTF was time consuming (∼3 min for a complete set of images, [28]), and the captured hyperspectral images’ field of view (FOV) were limited due to the lack of spatial-scanning capability. Through investigating visible/near infrared hyperspectral data, Shao et al. [30] showed that microalgae are a promising medium to identify varieties of pesticides and Pu et al. [24] demonstrated the potential of studying algae concentration levels to classify bodies of water. It is clear that there exist abundant further potential applications based on the combination of microalgae and HSI technologies, and thus it is worthwhile to aim to develop higher spatial and spectral resolutions, as well as more accurate models of classification, identification, estimation and prediction.

In this work, we develop a transmission hyperspectral microscopic imager (THMI) able to detect different species of microalgae. Trans-illumination patterns provide an excellent signal-to-noise ratio (SNR) for hyperspectral images, and calibration results show spatial and spectral resolutions of 4 µm and 3 nm, respectively. Based on the gray levels of the hyperspectral images, a region of interest (ROI) extraction algorithm was designed to identify spectra from microalgae at specific positions. Transmission spectra reflect the absorption characteristics of chlorophyll, carotenoid etc., and provide spectral differences for further classification data. The spectral data sets were processed by PCA and peak ratio algorithms for dimensional reduction and classified by a linear SVM classifier. The average accuracy, sensitivity and specificity to distinguish one species from other two species were found to be 94.4%, 94.4% and 97.2%, respectively. We also mixed two species of microalgae and could identify the separate species using these classification methods. Finally, simulation of a growth cycle of phaeocystis was done, and the corresponding growth stage was predicted using a hyperspectral data set and an RF model, with a 98.1% prediction accuracy.

The principal goal of this study is to demonstrate a set of feasible techniques and methods for classification and identification of microalgae species, which can also function as ecological environment early warning detection system for e.g. red tides and algae blooms.

2. Methods

2.1 System setup and calibration

The THMI system is mounted on a traditional microscope (RX50, SOPTOP, China) as shown in Fig. 1(a), and consists of an objective, an imaging lens, a slit, a collimator lens, a prism-grating-prism (PGP) structure, a tube lens and a CMOS (complementary metal oxide semiconductor) sensor arranged as depicted in Fig. 1(b). All of the optical components are Ø1” optics (with diameter 25.4 mm) and installed in a SM1 thread standard aluminum tube. A white LED lamp, with a spectral range covering all the visible bands, is used as the illuminator. The emitted light converges on the sample through a condenser, which maximizes the utilization of the light source and improves the imaging SNR. The transmission signal emitted from the focal plane is collected by a plane achromatic 40×/0.65 objective (RMS40X, Olympus, Japan), passes through the imaging lens (f = 50 mm, GCL-010652, DHC, China) and converges onto a 10 µm wide slit. After passing through the slit, the signal is collimated by a doublet lens (f = 50 mm, GCL-010652, DHC, China) and then dispersed by the PGP structure, which is used to deflect the 1st order diffraction pattern into the detection module. The PGP parameters are 300 grooves per millimeter with a 17.5-degree groove angle (GT25-03, Thorlabs Inc., USA), and the deflection angle of the prism is 10 degrees. The spread spectrum is finally focused onto the CMOS sensor (ASI74MM, ZWO, China) through a tube lens (f = 50 mm, GCL-010652, DHC, China). The short and long axes of the camera are set as the spatial and spectral axes, respectively. To maintain a high spatial resolution, the specimen holder is mounted on an XYZ three-axis motion stage (HDS-CBMS-XYZ-I-R, HEIDSTAR, China), which has a minimum movement step of 1 µm. Push-broom scanning, through which the hyperspectral cube can be obtained, is achieved by moving the specimen holder using the motion stage. The slit must be strictly perpendicular to the scanning direction and parallel to the spatial axis of CMOS sensor, otherwise the restored image will be distorted.

 figure: Fig. 1.

Fig. 1. (a) The full THMI system. (b) Schematic diagram of the transmission hyperspectral microscopic imager. 1: LED illuminator, 2: condenser, 3: sample and glass slide, 4: objective, 5: imaging lens, 6: slit, 7: doublet lens, 8: PGP (prism-grating-prism) structure, 9: tube lens, 10: CMOS camera. (c) Reconstructed spatial image of the resolution test target (1951 USAF-R1DS1P). Resolvable lines in element 1 of group 7 (∼3.9 µm) of the resolution test target are indicated. (d) Original spectral image of the calibration mercury lamp captured by the THMI. (e) Calibration result between the wavelength and pixel index. (f) Measured spectrum of the calibration mercury lamp. The spectral resolution is about 3 nm.

Download Full Size | PPT Slide | PDF

To characterize the performance of the THMI system, both spatial and spectral calibrations are required. Spatial calibration is done by performing a hyperspectral imaging experiment of a resolution test target (1951 USAF-R1DS1P, Thorlabs Inc., USA). A series of hyperspectral images are captured as the imager scans through the entire target plane, after which the images are stitched along the scanning direction. The restored spatial image is shown in Fig. 1(c). Due to some aberrations introduced by the diffraction module, the actual lateral spatial resolution of the imager is less than the theoretical calculated resolution of the microscope (0.61×λ/NA). The result shows that the THMI can distinguish the lines in element 1 of group 7 of the test target (indicated in Fig. 1(c)), for which the line width is 3.9 µm, indicating that our system has a spatial resolution of about 4 µm.

The spectral calibration enables the translation of pixel index to wavelength. A standard mercury lamp (HG-1, Ocean Optics Inc., USA) is used as the optical source [31]. The mixed light lines at different wavelengths from the optical source are diffracted by the PGP structure and captured by the CMOS sensor, shown in Fig. 1(d). The long axis represents the spectral axis since the spectrum expands along this axis, and the short axis represents the spatial axis. We select six vertical lines in the spectral image, representing the 435.833 nm, 546.074 nm, 578.013 nm, 750.387 nm, 763.511 nm and 772.376 nm light lines emitted from the mercury lamp source, whose corresponding pixel index values in the spectral axis are 1381, 1070, 979, 517, 483 and 459, respectively. We assume the wavelength of the imager to be a polynomial function of the pixel index of the spectral axis:

$$\lambda = {\alpha _0} + {a_1}x + {a_2}{x^2},$$
where λ is wavelength, x is pixel index, and α0, α1, α2 are calibration coefficients. Using a polynomial least squares fit method, the calibration coefficients α0, α1, α2 are found to be 952.9, -0.4022 and 2.017×10−5, respectively. The calibration result is shown in Fig. 1(e). After the wavelength calibration, each pixel index along the spectral axis corresponds to a specific wavelength. Figure 1(f) shows the spectrum of the calibration source obtained from the imager, and the full width at half maximum (FWHM) of the spectrum line of 546.074 nm is about 3 nm, indicating that the spectral resolution of our system is 3 nm.

2.2 Sample preparation

Three species of microalgae, phaeocystis, chlamydomonas and chaetoceros, supplied by South China Sea Fisheries Research Institute (CAFS), are used for classification experiments. The phaeocystis, chlamydomonas and chaetoceros are cultured in f/2, tap (tris-acetate-phosphate) and f/2+si medium, respectively. All of the samples are cultured in a light incubator (XY-QH-250CY, Xinyi Instrument Co., Ltd, China), at a temperature of 18 °C with an illumination of 2000 lux for 12 h per day. Table 1 summarizes the microalgae samples used in this study. To reduce the experimental error and ensure that the samples are a sufficiently representative set, 6×3 groups of specimens were prepared for detection and 60 hyperspectral images were captured for each species. A total of 180 (60×3) hyperspectral images were thus obtained for classification and further analysis.

Tables Icon

Table 1. 18 (6×3) groups of microalgae species.

For a phaeocystis growth cycle cultivated under laboratory conditions, a small number of microalgae species are sampled and cultured in f/2 medium with rich nutrient to promote the growth. The cultivation environment in light incubation is set at the temperature of 20 °C, with an illumination of 6000 lux for 12 h per day. Every three days, phaeocystis samples were taken and hyperspectral detection to monitor the growth process was performed. In order to avoid contamination, all cultivations were carried out in a sterile condition.

3. Results and discussion

In this section, we detail a range of microalgae detection experiments, which include hyperspectral imaging of the three species of microalgae; ROI and average transmission spectrum extraction; verification of absorption characteristics; classification of microalgae using PCA-SVM and peak ratio-SVM statistical analysis methods; species identification from a group of mixed microalgae solution; as well as phaeocystis growth stage estimation and validation. To avoid disturbance from the external or surrounding light, all experiments were performed in a dark room.

3.1 Hyperspectral imaging of three species of microalgae

To observe the morphological features of microalgae, a series of hyperspectral imaging detections were conducted. We pipetted the microalgae solution into a centrifuge tube and centrifuged at 4000 g for 2 min. Part of the supernatant was removed, and the remaining solution was shaken and dropped onto a glass slide for detection. The main purpose of the centrifugation procedure is to obtain high density microalgae samples, facilitating the morphology observation. The glass slide was placed on the motion stage and adjusted to the focal plane of the objective as the in-focus position has the sharpest spatial line in hyperspectral images. Push-broom scanning was subsequently performed by moving the glass slide in intervals of 1 µm using the motion stage. A total number of 400 hyperspectral images were obtained for the spatial image reconstruction. The total scanning time was 50 s, with the scanning speed mainly being limited by the efficiency of the CMOS sensor to transfer captured images to a computer hard disk. Using MATLAB software (The MathWorks Inc., USA), the captured images were stitched into a 3D hyperspectral cube along the scanning direction, in which the spatial image was acquired by summing the images over all wavelength bands [32]. The reconstructed spatial images of the microalgae are shown in Fig. 2, and their corresponding optical microscopic images are also shown as insets. The results show that the THMI system has excellent hyperspectral imaging capability. By replacing the objective with lower magnification one, the detection range and FOV can be enlarged to detect some clustered microalgae in real marine environment.

 figure: Fig. 2.

Fig. 2. Hyperspectral images of three species of microalgae. (a) phaeocystis, (b) chlammydomonas, (c) chaetoceros. Inserted (blue) images show their corresponding optical microscopic images. Scale bar: 50 µm.

Download Full Size | PPT Slide | PDF

3.2 Regions of interest (ROI) separation and average transmission spectrum extraction

Precise spectra of the tested microalgae can be automatically derived through ROI extraction of the spatial dimensions from the hyperspectral cube. In our work, the ROI is identified using segmentation with a simple threshold based on distinctive spectral differences between the samples and background. Using chlammydomonas as an example, the spatial hyperspectral image is transferred to a gray image, as shown in Fig. 3(a). It is obvious that the part with relatively low gray value is the microalgae, and the part with relatively high gray value represents the background. A mask is created by threshold segmentation to remove the background region. Based on the corresponding gray histogram of Fig. 3(a) shown in Fig. 3(b), we chose the position with an abrupt change of pixel number, whose gray value is 125, as the threshold. Additionally, we used an image filter to remove some noise. The resulting segmented binary image is shown in Fig. 3(c), which is the template for the image mask. After image masking, the ROI is successfully extracted and shown in Fig. 3(d). An average transmission spectrum of the ROI, defined as $\overline {T(\lambda )} $, can be calculated to be:

$$\overline {T(\lambda )} = \frac{1}{{Num}}\sum\limits_{x,y} {H(x,y,\lambda )} \textrm{, }(x,y) \in ROI$$
where the Num is the number of pixels in the ROI, and $H(x,y,\lambda )$ represents the hyperspectral cube. The average transmission spectrum of this chlammydomonas sample calculated by Eq. (2) is shown in Fig. 3(e).

 figure: Fig. 3.

Fig. 3. The process of ROI separation and average transmission spectrum extraction. (a) Gray spatial hyperspectral image of the chlammydomonas. (b) Corresponding gray histogram of (a). (c) Binary image of the sample, i.e. the image mask template. d) Purified hyperspectral image of the sample after masking. (e) The average transmission spectrum extracted from (d).

Download Full Size | PPT Slide | PDF

Using this process of ROI separation and average transmission spectrum extraction, an accurate spectrum of tested microalgae can be derived for further analysis.

3.3 Verification of absorption characteristics

For each microalgae species, the average transmission spectrum of specimens from 6 groups (a total number of 60 samples) is shown in Fig. 4(a). The spectrum of the LED light source is also shown in Fig. 4(a) for reference. To obviate the possible influence of solution concentration, each spectrum was normalized as

$${I_{norm}}(\lambda ) = \frac{{{I_{origin}}(\lambda ) - {I_{\min }}}}{{{I_{\max }} - {I_{\min }}}}$$
I in Eq. (3) is the transmission intensity. The normalized spectra are shown in Fig. 4(b). In addition, calculated microalgae transmittances relative to the LED light source shown in Fig. 4(c) suggest their corresponding absorption characteristics. From Figs. 4(a), 4(b) and 4(c), we find that all studied microalgae species have obvious absorption around the 440 nm band. Among them, chlamydomonas has the strongest absorption, followed by phaeocystis, with chaetoceros having the weakest absorption. In Fig. 4(c), we also find that chlamydomonas has a sharp absorption peak at about 680 nm.

 figure: Fig. 4.

Fig. 4. Verification of absorption characteristics of three microalgae. (a) Original transmission spectra of the LED light source and three microalgae. (b) Normalized spectra of (a) calculated by Eq. (2). (c) Transmittance of the microalgae relative to the LED light source. (d) Absorbance of the microalgae measured by a commercial spectrophotometer.

Download Full Size | PPT Slide | PDF

To verify the accuracy of the absorption characteristics, a commercial spectrophotometer (UV 2550, SHIMADZU, Japan) was used to measure the absorbance. The same amount and concentration of microalgae solutions as for the hyperspectral imaging were placed in cuvettes, which were subsequently placed in the spectrophotometer for measurements. Detection range was set to 380∼720 nm (i.e., the visible bands), and the measurement results are shown in Fig. 4(d). The absorbance confirms that chlamydomonas has the strongest absorption in the visible bands and has sharp peaks at the wavelengths of 440 nm and 680 nm. The absorbance of phaeocystis is also relatively higher than that of chaetoceros, especially around the wavelength of 440 nm. For chaetoceros we note that, when compared with the transmittance, the absorbance around the 440 nm band is missing some features. This is mainly due to differences in detection methods, which causes some measurement errors. The cuvettes, in which the solutions with the microalgae specimens were placed for detection by the commercial spectrophotometer, may cause some scattering that results in the loss of some features, while the ROI extraction of the microalgae transmittance spectra using our THMI system contains more precise features. However, there exists a clear trend consistency between the absorption characteristics in Figs. 4(c) and 4(d), that verifies the measurement accuracy of the hyperspectral detection of our THMI system.

3.4 Classification of microalgae by statistical analysis using the PCA-SVM method

In this section we discuss the use of a statistical approach to classify different species of microalgae. The transmission spectra of all samples listed in Table 1 are normalized and used as input for a multivariate statistical analysis. Principal component analysis (PCA) is an unsupervised method that is used to identify the combination of hyperspectral features that maximize the data variance for the purpose of decreasing dimensionality and computational burden [33,34]. These features are captured as a new set of variables, termed principal components (PCs), in a reduced dimension. The first few PCs will typically account for the majority of the data variance. However, as an unsupervised method, PCA has no prior knowledge of the groupings of the hyperspectral data, which means it is not suitable for the purposes of group separation. In contrast, support vector machine (SVM) is a supervised technique and is useful for discriminating between groups. We used a linear SVM algorithm [35] to classify the spectra for the three categories of samples, as shown in Fig. 5(a). The separation regions were calculated based on the first two principal components (PC1 and PC2).

 figure: Fig. 5.

Fig. 5. (a) Scatter plot of the scores of PC2 versus PC1 of three microalgae along with the linear SVM classifiers. The entire two-dimensional space is divided into three regions as labeled. (b) Confusion matrix of all transmission spectra for 180 samples (including 60 chaetoceros, 60 chlamydomonas and 60 phaeocystis). (c) The ROC curves corresponding to the SVM classifiers in (a).

Download Full Size | PPT Slide | PDF

Classification performance was evaluated using standard metrics, i.e. accuracy, sensitivity, and specificity, as well as a confusion matrix [36]. Predictive accuracy is the performance measure generally associated with machine learning algorithms. It is defined as the sum of true positives (TP) and true negatives (TN) divided by the sum of all examples, as expressed in Eq. (4), where FN and FP are the number of false negatives and false positives. Sensitivity is a measure of the proportion of positives correctly identified, as expressed in Eq. (5), and specificity is the equivalent measure of the proportion of negatives correctly identified, as expressed in Eq. (6). All the metrics were quantified in the confusion matrix shown in Fig. 5(b). The average accuracy, sensitivity and specificity to distinguish one species from other two species were calculated to be 94.4%, 94.4% and 97.2%, respectively.

$$Accuracy = \frac{{TP + TN}}{{TP + FP + FN + TN}},$$
$$Sensitivity = \frac{{TP}}{{TP + FN}},$$
$$Specificity = \frac{{TN}}{{TN + FP}}.$$

The receiver operating characteristic (ROC) curves were plotted as a true positive rate versus false positive rate (or 1 - specificity) in Fig. 5(c), and the area under curve (AUC) for each classification scenario were 0.965, 0.974 and 0.963, respectively.

3.5 Classification of microalgae using peak ratio and the SVM method

Since the PCA-SVM method shows an excellent classification performance based on PC1 and PC2 that carry the majority of spectral variance, we also consider absorption characteristics for classification. As discussed in Section 3.3, the main characteristics of the spectral absorptions appeared at the bands of 440 nm and 680 nm. Hence, a peak ratio method [37] to extract the differences at the absorption bands for classification can be used. A spectral band at 550 nm was selected as the baseline for comparison. The peak intensity ratios of I(680)/I(550) and I(440)/I(550) were calculated and scatter-plotted in Fig. 6(a), in which the separation regions derived from a linear SVM algorithm are also shown. The confusion matrix, shown in Fig. 6(b), shows the average accuracy, sensitivity and specificity to distinguish one species from other two species, which are 94.4%, 94.4% and 97.2%, respectively. The ROC curves, with 0.962, 1 and 0.976 of AUC, are plotted in Fig. 6(c).

 figure: Fig. 6.

Fig. 6. (a) Scatter plot of spectral peak intensity ratio I(680)/I(550) versus I(440)/I(550) for the three microalgae along with the linear SVM classifiers. The entire two-dimensional space is divided into three regions as labeled. (b) Confusion matrix of the transmission spectra for all 180 samples (60 chaetoceros, 60 chlamydomonas and 60 phaeocystis). (c) ROC curves corresponding to the SVM classifiers in (a).

Download Full Size | PPT Slide | PDF

The PCA-SVM and peak ratio-SVM methods show almost the same classification performance, which is mainly due to the fact that the absorption characteristics at the bands of 440 nm and 680 nm contribute to the majority of spectral variances, i.e. the first several principal components.

3.6 Species identification from a group of mixed microalgae solution

Section 3.5 demonstrates the feasibility for microalgae classification from spectral absorption characteristics. In this section, species identification of phaeocystis and chlamydomonas from a solution of a group of mixed microalgae using the above method is demonstrated. Equal amounts of phaeocystis and chlamydomonas in a solution were placed in a centrifuge tube, forming a group of mixed microalgae. Following centrifugation, part of the supernatant was removed, and remaining specimen was shaken and dropped onto a glass slide for detection. The sample is then scanned using the THMI at a movement interval of 1 µm, capturing a series of hyperspectral images for reconstruction. All captured images were stitched into a hyperspectral 3D cube, and the reconstructed spatial hyperspectral image is shown in Fig. 7(a), in which we can hardly distinguish the specific species. A spatial image considering the difference of the absorption characteristics between phaeocystis and chlamydomonas at the 680 nm band (details in Section 3.3) is shown in Fig. 7(b), in which the regions with relatively low gray values are chlamydomonas due to its stronger absorption, while the regions with relatively high gray values were phaeocystis. Threshold segmentation was applied to create a template image mask, as shown in Fig. 7(d). The species identification was then realized by adding template to the original hyperspectral image, as shown in Fig. 7(c).

 figure: Fig. 7.

Fig. 7. Demonstration for the species identification from a group of mixed microalgae. (a) Hyperspectral image of the mixed microalgae at the broad visible bands. (b) Hyperspectral image of the mixed microalgae at the single spectral band (680 nm). (c) The result of species identification on (a) after adding the image mask, the blue and red regions represent the chlamydomonas and phaeocystis, respectively. (d) The template image mask, generated by threshold segmentation on (b).

Download Full Size | PPT Slide | PDF

3.7 Estimation and validation of growth stage for phaeocystis

It is relatively easy for microalgae to gather and, as their numbers grow beyond a certain stage, for very rapid population growth to occur potentially resulting in severe ecological problems, such as a red tide. Real-time monitoring of microalgae growth stage is thus extremely desirable to enable early warning detection systems. We select phaeocystis for growth stage analysis as it is one of the main microalgae species causing red tide outbreaks [38,39]. We cultivated growth cycle of phaeocystis under laboratory conditions and established a corresponding statistical model to predict their growth stage based on a random forest (RF) algorithm. RF is an excellent regression algorithm that can effectively prevent overfitting while fully fitting the dataset.

Phaeocystis was cultured in an optimal growth environment and was sampled every three days for hyperspectral detection (details in Section 2.2). The growth stage was characterized by the density metric, i.e. the number of microalgae per unit volume. Before each test, we used a hemacytometer (Sigma-Aldrich, USA) to count the living microalgae extracted from the supernatant of the medium [40]. To avoid induced errors, the counting process was usually repeated five times from which the average was used. The growth curve for 25 days, during which the phaeocystis experienced a complete growth cycle, is plotted in Fig. 8(a). Generally, the growth cycle of microalgae consists of four phases: lag, exponential growth, stable and decline phase [41,42]. The growth of microalgae depends on the content of nutrients in the culture environment and with sufficient nutrients in the early stage, the growth will turn exponential, however with the gradual consumption of nutrients, the growth of microalgae eventually starts to decline.

 figure: Fig. 8.

Fig. 8. (a) Growth curve of phaeocystis over 25 days. 1: lag phase, 2: exponential growth phase, 3: stable phase, 4: decline phase. (b) Normalized transmission spectra of phaeocystis. (c) Predicted results of the growth stage by the training set. (d) Predicted results of the growth stage by the test set.

Download Full Size | PPT Slide | PDF

The average transmission spectrum for each detection was normalized using Eq. (3) and plotted in Fig. 8(b). The normalized intensity of the transmission spectrum is affected by the amount of pigment, such as chlorophyll, whose concentration is positively correlated with the density of living microalgae [4345]. It should be noted that the density of living microalgae may be equal in the exponential growth and decline phases, however, their spectra will still be slightly different due to the variations of nutrients and metabolites in the culture medium.

Through the whole detection sequence, a set of 60×9 transmission spectra were obtained, which were sorted randomly and divided into the training and test sets with a ratio of 7:3. I.e. 42×9 sample data were used to build the prediction model and 18×9 sample data were used to verify the reliability of the model. The predicted results of the training and test sets are shown in Figs. 8(c) and 8(d), respectively. Perfect agreement between the predicted and actual growth stages are shown as solid lines, and the region between the two dashed lines is the range of acceptable deviation. Considering the test interval of three days, the maximum acceptable deviation of the growth stage is set as 1.5 days. The proportion of the predicted data of the training and test sets in the allowable deviation range, i.e. the predicted accuracy, is 99.5% and 98.1%, respectively. The mean squared error (MSE) of training and test sets are 0.035 and 0.113, respectively and the mean absolute error (MAE) of the training and test sets are 0.039 and 0.085, respectively. The coefficient of determination (R-squared) of the training and tests set is up to 0.999 and 0.998, respectively, indicating a good linear relationship between the predicted and actual growth stages. As comparison, prediction performances by different supervised learning models are shown in the Table 2.

Tables Icon

Table 2. Prediction performances of five supervised learning models.

These results prove the viability of our THMI system for prediction of microalgae growth stage, making it suitable as an early warning detection system for in-situ environmental monitoring applications. For instance, the relationship between the transmission spectra and microalgae density or growth stage can be established, and a warning should be reported when the spectra signal correspond to the early exponential growth phase.

4. Summary and outlook

In this work, we have developed a transmission hyperspectral microscopic imager (THMI) for hyperspectral detection of microalgae. The THMI system shows excellent microscopy performance, with a spatial and spectral resolutions of 4 µm and 3 nm, respectively, which is suitable for most applications. A series of experiments have been conducted to verify the capacity of the THMI system: hyperspectral imaging of three species of microalgae; ROI and average transmission spectrum extraction; verification of absorption characteristics; classification of microalgae by statistical analysis using PCA-SVM and peak ratio-SVM methods; species identification from a group of mixed microalgae solution; as well as phaeocystis growth stage estimation and validation. Combined with machine learning algorithms, we find the average accuracy, sensitivity and specificity to distinguish one species from two other species reach 94.4%, 94.4% and 97.2%, respectively. In addition, the prediction accuracy of the phaeocystis growth stage was 98.1%, indicating the applicability of the prediction model. Experimental results show that the THMI system has the capability for classification, identification and growth stage estimation of microalgae, and have strong potential for applications of in-situ marine environmental monitoring and early warning detection. In contrast to other approaches, e.g. HSI equipment based on attaching a commercial HS camera to a conventional microscope, our THMI system provides a large degree of flexibility. E.g., the position of the illuminator can be adjusted to be directly on top of the samples to measure the reflection spectra, and objectives with different magnification can be used according to specific FOV and spatial resolution requirements.

In terms of future improvements, a wider wavelength detection range, specific identification in complex environments as well as multi-dimensional detection are feasible and to be considered. The THMI system can be expanded to cover a broad spectral range from ultraviolet (UV) to visible (VIS) to infra-red (IR), providing ample information such as fluorescence signal and Raman spectra with fingerprint characteristics [4648]. DNA probe technology can be combined with the THMI system, for identification of specific substances in a complex environment [49,50]. Furthermore, by combining the HSI technology with three-dimensional spatial imaging methods, the system could realize 4D (i.e., 1 spectral and 3 spatial dimensions) detection [51,52], for multi-dimensional inspection in biological and clinical applications.

Funding

Fundamental Research Funds for the Central Universities (Zhejiang University NGICS Platform); National Key Research and Development Program of China (2018YFC1407503); National Natural Science Foundation of China (61774131, 91833303).

Acknowledgments

We appreciate Dr. Qin Tan for valuable help.

Disclosures

The authors declare no conflicts of interest.

References

1. E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020). [CrossRef]  

2. J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011). [CrossRef]  

3. L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008). [CrossRef]  

4. E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006). [CrossRef]  

5. C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019). [CrossRef]  

6. A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

7. M. E. Pawlowski, J. G. Dwight, T.-U. Nguyen, and T. S. Tkaczyk, “High performance image mapping spectrometer (IMS) for snapshot hyperspectral imaging applications,” Opt. Express 27(2), 1597 (2019). [CrossRef]  

8. F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017). [CrossRef]  

9. Y. Wang, M. E. Pawlowski, S. Cheng, J. G. Dwight, R. I. Stoian, J. Lu, D. Alexander, and T. S. Tkaczyk, “Light-guide snapshot imaging spectrometer for remote sensing applications,” Opt. Express 27(11), 15701 (2019). [CrossRef]  

10. Ø Ødegård, A. A. Mogstad, G. Johnsen, A. J. Sørensen, and M. Ludvigsen, “Underwater hyperspectral imaging: a new tool for marine archaeology,” Appl. Opt. 57(12), 3214 (2018). [CrossRef]  

11. X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019). [CrossRef]  

12. L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015). [CrossRef]  

13. S. Pahlow, K. Weber, J. Popp, B. R. Wood, K. Kochan, A. Rüther, D. Perez-Guaita, P. Heraud, N. Stone, A. Dudgeon, B. Gardner, R. Reddy, D. Mayerich, and R. Bhargava, “Application of Vibrational Spectroscopy and Imaging to Point-of-Care Medicine: A Review,” Appl. Spectrosc. 72(S1), 52–84 (2018). [CrossRef]  

14. G. Lu and B. Fei, “Medical hyperspectral imaging: a review,” J. Biomed. Opt. 19(1), 010901 (2014). [CrossRef]  

15. M. Ishikawa, C. Okamoto, K. Shinoda, H. Komagata, C. Iwamoto, K. Ohuchida, M. Hashizume, A. Shimizu, and N. Kobayashi, “Detection of pancreatic tumor cell nuclei via a hyperspectral analysis of pathological slides based on stain spectra,” Biomed. Opt. Express 10(9), 4568 (2019). [CrossRef]  

16. S. Ortega, M. Halicek, H. Fabelo, G. M. Callico, and B. Fei, “Hyperspectral and multispectral imaging in digital and computational pathology: a systematic review [Invited],” Biomed. Opt. Express 11(6), 3195 (2020). [CrossRef]  

17. Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019). [CrossRef]  

18. B. Hu, J. Du, Z. Zhang, and Q. Wang, “Tumor tissue classification based on micro-hyperspectral technology and deep learning,” Biomed. Opt. Express 10(12), 6370 (2019). [CrossRef]  

19. Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020). [CrossRef]  

20. F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020). [CrossRef]  

21. Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020). [CrossRef]  

22. S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018). [CrossRef]  

23. U. Kürüm, P. R. Wiecha, R. French, and O. L. Muskens, “Deep learning enabled real time speckle recognition and hyperspectral imaging using a multimode fiber array,” Opt. Express 27(15), 20965 (2019). [CrossRef]  

24. H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016). [CrossRef]  

25. P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017). [CrossRef]  

26. S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019). [CrossRef]  

27. S. M. Borzov and O. I. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Optoelectron. Instrument. Proc. 54(6), 582–599 (2018). [CrossRef]  

28. L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017). [CrossRef]  

29. X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019). [CrossRef]  

30. Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016). [CrossRef]  

31. F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020). [CrossRef]  

32. F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018). [CrossRef]  

33. S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018). [CrossRef]  

34. Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, and M. Yao, “Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition,” Appl. Opt. 58(7), 1631 (2019). [CrossRef]  

35. C. C. Chang and C. J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011). [CrossRef]  

36. M. A. S. de Oliveira, M. Campbell, A. M. Afify, E. C. Huang, and J. W. Chan, “Hyperspectral Raman microscopy can accurately differentiate single cells of different human thyroid nodules,” Biomed. Opt. Express 10(9), 4411 (2019). [CrossRef]  

37. G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016). [CrossRef]  

38. Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018). [CrossRef]  

39. L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019). [CrossRef]  

40. M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015). [CrossRef]  

41. J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019). [CrossRef]  

42. D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998). [CrossRef]  

43. L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016). [CrossRef]  

44. J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015). [CrossRef]  

45. S. Bi, Y. Li, J. Xu, G. Liu, K. Song, M. Mu, H. Lyu, S. Miao, and J. Xu, “Optical classification of inland waters based on an improved Fuzzy C-Means method,” Opt. Express 27(24), 34838 (2019). [CrossRef]  

46. Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015). [CrossRef]  

47. G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019). [CrossRef]  

48. D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020). [CrossRef]  

49. C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005). [CrossRef]  

50. C. J. Kim and Y. Sako, “Molecular identification of toxic Alexandrium tamiyavanichii (Dinophyceae) using two DNA probes,” Harmful Algae 4(6), 984–991 (2005). [CrossRef]  

51. F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020). [CrossRef]  

52. Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020). [CrossRef]  

References

  • View by:
  • |
  • |
  • |

  1. E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020).
    [Crossref]
  2. J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011).
    [Crossref]
  3. L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
    [Crossref]
  4. E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
    [Crossref]
  5. C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
    [Crossref]
  6. A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).
  7. M. E. Pawlowski, J. G. Dwight, T.-U. Nguyen, and T. S. Tkaczyk, “High performance image mapping spectrometer (IMS) for snapshot hyperspectral imaging applications,” Opt. Express 27(2), 1597 (2019).
    [Crossref]
  8. F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
    [Crossref]
  9. Y. Wang, M. E. Pawlowski, S. Cheng, J. G. Dwight, R. I. Stoian, J. Lu, D. Alexander, and T. S. Tkaczyk, “Light-guide snapshot imaging spectrometer for remote sensing applications,” Opt. Express 27(11), 15701 (2019).
    [Crossref]
  10. Ø Ødegård, A. A. Mogstad, G. Johnsen, A. J. Sørensen, and M. Ludvigsen, “Underwater hyperspectral imaging: a new tool for marine archaeology,” Appl. Opt. 57(12), 3214 (2018).
    [Crossref]
  11. X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
    [Crossref]
  12. L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
    [Crossref]
  13. S. Pahlow, K. Weber, J. Popp, B. R. Wood, K. Kochan, A. Rüther, D. Perez-Guaita, P. Heraud, N. Stone, A. Dudgeon, B. Gardner, R. Reddy, D. Mayerich, and R. Bhargava, “Application of Vibrational Spectroscopy and Imaging to Point-of-Care Medicine: A Review,” Appl. Spectrosc. 72(S1), 52–84 (2018).
    [Crossref]
  14. G. Lu and B. Fei, “Medical hyperspectral imaging: a review,” J. Biomed. Opt. 19(1), 010901 (2014).
    [Crossref]
  15. M. Ishikawa, C. Okamoto, K. Shinoda, H. Komagata, C. Iwamoto, K. Ohuchida, M. Hashizume, A. Shimizu, and N. Kobayashi, “Detection of pancreatic tumor cell nuclei via a hyperspectral analysis of pathological slides based on stain spectra,” Biomed. Opt. Express 10(9), 4568 (2019).
    [Crossref]
  16. S. Ortega, M. Halicek, H. Fabelo, G. M. Callico, and B. Fei, “Hyperspectral and multispectral imaging in digital and computational pathology: a systematic review [Invited],” Biomed. Opt. Express 11(6), 3195 (2020).
    [Crossref]
  17. Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
    [Crossref]
  18. B. Hu, J. Du, Z. Zhang, and Q. Wang, “Tumor tissue classification based on micro-hyperspectral technology and deep learning,” Biomed. Opt. Express 10(12), 6370 (2019).
    [Crossref]
  19. Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020).
    [Crossref]
  20. F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
    [Crossref]
  21. Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
    [Crossref]
  22. S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
    [Crossref]
  23. U. Kürüm, P. R. Wiecha, R. French, and O. L. Muskens, “Deep learning enabled real time speckle recognition and hyperspectral imaging using a multimode fiber array,” Opt. Express 27(15), 20965 (2019).
    [Crossref]
  24. H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
    [Crossref]
  25. P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
    [Crossref]
  26. S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
    [Crossref]
  27. S. M. Borzov and O. I. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Optoelectron. Instrument. Proc. 54(6), 582–599 (2018).
    [Crossref]
  28. L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
    [Crossref]
  29. X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
    [Crossref]
  30. Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
    [Crossref]
  31. F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
    [Crossref]
  32. F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
    [Crossref]
  33. S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
    [Crossref]
  34. Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, and M. Yao, “Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition,” Appl. Opt. 58(7), 1631 (2019).
    [Crossref]
  35. C. C. Chang and C. J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011).
    [Crossref]
  36. M. A. S. de Oliveira, M. Campbell, A. M. Afify, E. C. Huang, and J. W. Chan, “Hyperspectral Raman microscopy can accurately differentiate single cells of different human thyroid nodules,” Biomed. Opt. Express 10(9), 4411 (2019).
    [Crossref]
  37. G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016).
    [Crossref]
  38. Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
    [Crossref]
  39. L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019).
    [Crossref]
  40. M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
    [Crossref]
  41. J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
    [Crossref]
  42. D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
    [Crossref]
  43. L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016).
    [Crossref]
  44. J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
    [Crossref]
  45. S. Bi, Y. Li, J. Xu, G. Liu, K. Song, M. Mu, H. Lyu, S. Miao, and J. Xu, “Optical classification of inland waters based on an improved Fuzzy C-Means method,” Opt. Express 27(24), 34838 (2019).
    [Crossref]
  46. Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
    [Crossref]
  47. G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
    [Crossref]
  48. D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
    [Crossref]
  49. C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005).
    [Crossref]
  50. C. J. Kim and Y. Sako, “Molecular identification of toxic Alexandrium tamiyavanichii (Dinophyceae) using two DNA probes,” Harmful Algae 4(6), 984–991 (2005).
    [Crossref]
  51. F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
    [Crossref]
  52. Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
    [Crossref]

2020 (9)

E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020).
[Crossref]

Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020).
[Crossref]

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
[Crossref]

S. Ortega, M. Halicek, H. Fabelo, G. M. Callico, and B. Fei, “Hyperspectral and multispectral imaging in digital and computational pathology: a systematic review [Invited],” Biomed. Opt. Express 11(6), 3195 (2020).
[Crossref]

F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
[Crossref]

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
[Crossref]

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

2019 (16)

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019).
[Crossref]

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

S. Bi, Y. Li, J. Xu, G. Liu, K. Song, M. Mu, H. Lyu, S. Miao, and J. Xu, “Optical classification of inland waters based on an improved Fuzzy C-Means method,” Opt. Express 27(24), 34838 (2019).
[Crossref]

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, and M. Yao, “Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition,” Appl. Opt. 58(7), 1631 (2019).
[Crossref]

M. A. S. de Oliveira, M. Campbell, A. M. Afify, E. C. Huang, and J. W. Chan, “Hyperspectral Raman microscopy can accurately differentiate single cells of different human thyroid nodules,” Biomed. Opt. Express 10(9), 4411 (2019).
[Crossref]

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

B. Hu, J. Du, Z. Zhang, and Q. Wang, “Tumor tissue classification based on micro-hyperspectral technology and deep learning,” Biomed. Opt. Express 10(12), 6370 (2019).
[Crossref]

U. Kürüm, P. R. Wiecha, R. French, and O. L. Muskens, “Deep learning enabled real time speckle recognition and hyperspectral imaging using a multimode fiber array,” Opt. Express 27(15), 20965 (2019).
[Crossref]

M. Ishikawa, C. Okamoto, K. Shinoda, H. Komagata, C. Iwamoto, K. Ohuchida, M. Hashizume, A. Shimizu, and N. Kobayashi, “Detection of pancreatic tumor cell nuclei via a hyperspectral analysis of pathological slides based on stain spectra,” Biomed. Opt. Express 10(9), 4568 (2019).
[Crossref]

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

M. E. Pawlowski, J. G. Dwight, T.-U. Nguyen, and T. S. Tkaczyk, “High performance image mapping spectrometer (IMS) for snapshot hyperspectral imaging applications,” Opt. Express 27(2), 1597 (2019).
[Crossref]

Y. Wang, M. E. Pawlowski, S. Cheng, J. G. Dwight, R. I. Stoian, J. Lu, D. Alexander, and T. S. Tkaczyk, “Light-guide snapshot imaging spectrometer for remote sensing applications,” Opt. Express 27(11), 15701 (2019).
[Crossref]

2018 (7)

Ø Ødegård, A. A. Mogstad, G. Johnsen, A. J. Sørensen, and M. Ludvigsen, “Underwater hyperspectral imaging: a new tool for marine archaeology,” Appl. Opt. 57(12), 3214 (2018).
[Crossref]

S. Pahlow, K. Weber, J. Popp, B. R. Wood, K. Kochan, A. Rüther, D. Perez-Guaita, P. Heraud, N. Stone, A. Dudgeon, B. Gardner, R. Reddy, D. Mayerich, and R. Bhargava, “Application of Vibrational Spectroscopy and Imaging to Point-of-Care Medicine: A Review,” Appl. Spectrosc. 72(S1), 52–84 (2018).
[Crossref]

S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
[Crossref]

S. M. Borzov and O. I. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Optoelectron. Instrument. Proc. 54(6), 582–599 (2018).
[Crossref]

F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
[Crossref]

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

2017 (3)

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
[Crossref]

2016 (4)

H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
[Crossref]

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016).
[Crossref]

L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016).
[Crossref]

2015 (4)

J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
[Crossref]

Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
[Crossref]

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

2014 (1)

G. Lu and B. Fei, “Medical hyperspectral imaging: a review,” J. Biomed. Opt. 19(1), 010901 (2014).
[Crossref]

2011 (2)

J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011).
[Crossref]

C. C. Chang and C. J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011).
[Crossref]

2008 (1)

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

2006 (1)

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

2005 (2)

C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005).
[Crossref]

C. J. Kim and Y. Sako, “Molecular identification of toxic Alexandrium tamiyavanichii (Dinophyceae) using two DNA probes,” Harmful Algae 4(6), 984–991 (2005).
[Crossref]

1998 (1)

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Afify, A. M.

Alexander, D.

Alfano, R. R.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Asgharnejad, H.

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

Badescu, V.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Banciu, A.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Belluco, E.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Benediktsson, J. A.

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

Bertels, L.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Bhargava, R.

Bi, S.

Bi, X.

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
[Crossref]

Borzov, S. M.

S. M. Borzov and O. I. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Optoelectron. Instrument. Proc. 54(6), 582–599 (2018).
[Crossref]

Bumbac, C.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Cai, F.

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
[Crossref]

F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
[Crossref]

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
[Crossref]

F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
[Crossref]

Callico, G. M.

Campbell, M.

Camuffo, M.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Cantin, L.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Cen, J.

L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019).
[Crossref]

Chan, J. W.

Chang, C. C.

C. C. Chang and C. J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011).
[Crossref]

Chen, C.

Chen, J.

F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
[Crossref]

Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, and M. Yao, “Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition,” Appl. Opt. 58(7), 1631 (2019).
[Crossref]

Chen, T.

Chen, W.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Chen, Y.

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

Chen, Z.

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Cheng, G.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Cheng, J. H.

H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
[Crossref]

Cheng, S.

Costa, M.

J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011).
[Crossref]

Côté, D. C.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Crumeyrolle, S.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

de Oliveira, M. A. S.

Deboudt, K.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Deguine, A.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

DePaoli, D.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Deronde, B.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Dong, Y.

Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
[Crossref]

Du, C.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Du, J.

B. Hu, J. Du, Z. Zhang, and Q. Wang, “Tumor tissue classification based on micro-hyperspectral technology and deep learning,” Biomed. Opt. Express 10(12), 6370 (2019).
[Crossref]

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Dubranna, J.

J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
[Crossref]

Dudgeon, A.

Dwight, J. G.

Ember, K.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Emmerich, J.

A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

Fabelo, H.

Fang, H.

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

Fang, L.

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

Fang, S.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Fei, B.

Ferrari, S.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Fertein, E.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Flament, P.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Forney, L. J.

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Forsberg, E.

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

French, R.

Gao, M.

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
[Crossref]

Gao, W.

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Gardner, B.

Ghamisi, P.

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

Gieskes, W. W. C.

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Goossens, R.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Gottschal, J. C.

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Govindwar, S.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Guo, G.

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Guo, J.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Guo, Y.

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

Halicek, M.

Hashizume, M.

He, S.

Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020).
[Crossref]

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
[Crossref]

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
[Crossref]

Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
[Crossref]

He, Y.

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

Heraud, P.

Hu, B.

Huang, E. C.

Hubert, P.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Ionescu, I.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Ishikawa, M.

Iwamoto, C.

Jeon, B. H.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Jiang, L.

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

Jiang, Y.

Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020).
[Crossref]

Johnsen, G.

Junne, S.

A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

Khan, M. A.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Kim, C. H.

C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005).
[Crossref]

Kim, C. J.

C. J. Kim and Y. Sako, “Molecular identification of toxic Alexandrium tamiyavanichii (Dinophyceae) using two DNA probes,” Harmful Algae 4(6), 984–991 (2005).
[Crossref]

C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005).
[Crossref]

Knaeps, E.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Kobayashi, N.

Kochan, K.

Komagata, H.

Kulinski, P.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Kurade, M. B.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Kürüm, U.

Kutser, T.

E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020).
[Crossref]

La, H. J.

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

Lazar, M. N.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Leblond, F.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Lemoine, É

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Li, J.

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

Li, L.

L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019).
[Crossref]

Li, M.

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Li, S.

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

Li, Y.

Li, Z.

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
[Crossref]

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Lin, C. J.

C. C. Chang and C. J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011).
[Crossref]

Lin, S.

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
[Crossref]

Liu, C.-H.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Liu, D.

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Liu, G.

Liu, M.

Lovo, S.

Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
[Crossref]

Lu, G.

G. Lu and B. Fei, “Medical hyperspectral imaging: a review,” J. Biomed. Opt. 19(1), 010901 (2014).
[Crossref]

Lu, J.

Lu, W.

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
[Crossref]

Lü, S.

L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019).
[Crossref]

Ludvigsen, M.

Luo, Z.

Lyu, H.

Manea, E.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Marani, A.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Marani, M.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Marbà-Ardébol, A. M.

A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

Mayerich, D.

Miao, S.

Modenese, L.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Mogstad, A. A.

Mu, M.

Muskens, O. L.

Muthig, M.

A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

Neubauer, P.

A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

Neukermans, G.

G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016).
[Crossref]

Nguyen, T.-U.

Noordkamp, D. J. B.

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

O’Neill, J. D.

J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011).
[Crossref]

Ødegård, Ø

Oh, H. M.

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

Ohuchida, K.

Okamoto, C.

Ortega, S.

Paavel, B.

E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020).
[Crossref]

Paeng, K. J.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Pahlow, S.

Pan, J.

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

Parent, M.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Pawlowski, M. E.

Pellegrinelli, A.

Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
[Crossref]

Perez-Guaita, D.

Petitprez, D.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Petrecca, K.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Plaza, A. J.

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

Plaza, J.

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

Popp, J.

Potaturkin, O. I.

S. M. Borzov and O. I. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Optoelectron. Instrument. Proc. 54(6), 582–599 (2018).
[Crossref]

Prud’homme, M.

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

Pu, H.

L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016).
[Crossref]

H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
[Crossref]

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Pu, Y.

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Reddy, R.

Reynolds, R. A.

G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016).
[Crossref]

J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
[Crossref]

Roh, H. S.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Russo, P.

Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
[Crossref]

Rüther, A.

Sako, Y.

C. J. Kim and Y. Sako, “Molecular identification of toxic Alexandrium tamiyavanichii (Dinophyceae) using two DNA probes,” Harmful Algae 4(6), 984–991 (2005).
[Crossref]

C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005).
[Crossref]

Sarrafzadeh, M. H.

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

Schotten, M.

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Seo, S. H.

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

Shao, Y.

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

Sharma, T.

J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011).
[Crossref]

Shi, L.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Shi, W.

F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
[Crossref]

Shimizu, A.

Shinoda, K.

Sigrist, M. W.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Silvestri, S.

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

Song, K.

Song, W.

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

Sørensen, A. J.

Sterckx, S.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Stoian, R. I.

Stoica, C.

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Stone, N.

Stramski, D.

G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016).
[Crossref]

J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
[Crossref]

Su, K.

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Su, Z.

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Sun, D. W.

H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
[Crossref]

L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016).
[Crossref]

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Sun, Y.

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Taddia, Y.

Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
[Crossref]

Tkaczyk, T. S.

Uitz, J.

J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
[Crossref]

Vahtmäe, E.

E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020).
[Crossref]

Van Coillie, S.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Van Rijssel, M.

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Vanderstraete, T.

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

Wang, D.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Wang, G.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Wang, H.

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Wang, K.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Wang, L.

H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
[Crossref]

L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016).
[Crossref]

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Wang, Q.

Wang, T.

F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
[Crossref]

Wang, Y.

Y. Wang, M. E. Pawlowski, S. Cheng, J. G. Dwight, R. I. Stoian, J. Lu, D. Alexander, and T. S. Tkaczyk, “Light-guide snapshot imaging spectrometer for remote sensing applications,” Opt. Express 27(11), 15701 (2019).
[Crossref]

F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
[Crossref]

Weber, K.

Wei, L.

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Wiecha, P. R.

Wood, B. R.

Wu, B.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Wu, C.

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

Wu, J.

F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
[Crossref]

Xie, J.

F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
[Crossref]

Xie, W.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Xie, X.

F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
[Crossref]

Xiong, J. Q.

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Xiong, Z.

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Xu, J.

Xu, Z.

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020).
[Crossref]

Yao, M.

Yao, X.

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

Yi, H.

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Yin, H.

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
[Crossref]

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Yong, Z.

Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
[Crossref]

Yu, X.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Zhang, C.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Zhang, L.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, and M. Yao, “Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition,” Appl. Opt. 58(7), 1631 (2019).
[Crossref]

Zhang, P.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Zhang, S.

Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
[Crossref]

Zhang, X.

F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
[Crossref]

Zhang, Z.

B. Hu, J. Du, Z. Zhang, and Q. Wang, “Tumor tissue classification based on micro-hyperspectral technology and deep learning,” Biomed. Opt. Express 10(12), 6370 (2019).
[Crossref]

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Zhao, M.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Zhou, D.

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Zhou, H.

Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, and M. Yao, “Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition,” Appl. Opt. 58(7), 1631 (2019).
[Crossref]

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

Zhou, W.

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Zhou, Y.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Zhu, K.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

Zhu, P.

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

Zhu, S.

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

S. Lin, X. Bi, S. Zhu, H. Yin, Z. Li, and C. Chen, “Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi,” Biomed. Opt. Express 9(9), 4496 (2018).
[Crossref]

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Zong, R.

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

ACM Trans. Intell. Syst. Technol. (1)

C. C. Chang and C. J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011).
[Crossref]

Appl. Geomatics (1)

Y. Taddia, P. Russo, S. Lovo, and A. Pellegrinelli, “Multispectral UAV monitoring of submerged seaweed in shallow water,” Appl. Geomatics 12(S1), 19–34 (2020).
[Crossref]

Appl. Opt. (2)

Appl. Sci. (1)

Z. Xu, Y. Jiang, and S. He, “Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples,” Appl. Sci. 10(14), 4876 (2020).
[Crossref]

Appl. Spectrosc. (1)

Aquat. Microb. Ecol. (1)

D. J. B. Noordkamp, M. Schotten, W. W. C. Gieskes, L. J. Forney, J. C. Gottschal, and M. Van Rijssel, “High acrylate concentrations in the mucus of Phaeocystis globosa colonies,” Aquat. Microb. Ecol. 16(1), 45–52 (1998).
[Crossref]

Biomed. Opt. Express (5)

Chemosphere (1)

J. Q. Xiong, S. Govindwar, M. B. Kurade, K. J. Paeng, H. S. Roh, M. A. Khan, and B. H. Jeon, “Toxicity of sulfamethazine and sulfamethoxazole and their removal by a green microalga, Scenedesmus obliquus,” Chemosphere 218, 551–558 (2019).
[Crossref]

Ecotoxicol. Environ. Saf. (1)

Y. Sun, W. Zhou, H. Wang, G. Guo, Z. Su, and Y. Pu, “Antialgal compounds with antialgal activity against the common red tide microalgae from a green algae Ulva pertusa,” Ecotoxicol. Environ. Saf. 157, 61–66 (2018).
[Crossref]

Food Anal. Methods (1)

L. Wang, D. Liu, H. Pu, D. W. Sun, W. Gao, and Z. Xiong, “Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice,” Food Anal. Methods 8(2), 515–523 (2015).
[Crossref]

Front. Phys. (1)

F. Cai, M. Gao, J. Li, W. Lu, and C. Wu, “Compact Dual-Channel (Hyperspectral and Video) Endoscopy,” Front. Phys. 8(110), 1–7 (2020).
[Crossref]

Harmful Algae (1)

C. J. Kim and Y. Sako, “Molecular identification of toxic Alexandrium tamiyavanichii (Dinophyceae) using two DNA probes,” Harmful Algae 4(6), 984–991 (2005).
[Crossref]

IEEE Geosci. Remote Sens. Mag. (1)

P. Ghamisi, J. Plaza, Y. Chen, J. Li, and A. J. Plaza, “Advanced Spectral Classifiers for Hyperspectral Images: A review,” IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017).
[Crossref]

IEEE Trans. Geosci. Remote Sens. (1)

S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, and J. A. Benediktsson, “Deep learning for hyperspectral image classification: An overview,” IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019).
[Crossref]

Int. J. Remote Sens. (1)

L. Bertels, T. Vanderstraete, S. Van Coillie, E. Knaeps, S. Sterckx, R. Goossens, and B. Deronde, “Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia,” Int. J. Remote Sens. 29(8), 2359–2391 (2008).
[Crossref]

J. Appl. Remote Sens. (1)

E. Vahtmäe, B. Paavel, and T. Kutser, “How much benthic information can be retrieved with hyperspectral sensor from the optically complex coastal waters?” J. Appl. Remote Sens. 14(01), 1 (2020).
[Crossref]

J. Biomed. Opt. (3)

Y. Zhou, C.-H. Liu, B. Wu, X. Yu, G. Cheng, K. Zhu, K. Wang, C. Zhang, M. Zhao, R. Zong, L. Zhang, L. Shi, and R. R. Alfano, “Optical biopsy identification and grading of gliomas using label-free visible resonance Raman spectroscopy,” J. Biomed. Opt. 24(09), 1 (2019).
[Crossref]

G. Lu and B. Fei, “Medical hyperspectral imaging: a review,” J. Biomed. Opt. 19(1), 010901 (2014).
[Crossref]

D. DePaoli, É Lemoine, K. Ember, M. Parent, M. Prud’homme, L. Cantin, K. Petrecca, F. Leblond, and D. C. Côté, “Rise of Raman spectroscopy in neurosurgery: a review,” J. Biomed. Opt. 25(05), 1 (2020).
[Crossref]

J. Biotechnol. (1)

M. H. Sarrafzadeh, H. J. La, S. H. Seo, H. Asgharnejad, and H. M. Oh, “Evaluation of various techniques for microalgal biomass quantification,” J. Biotechnol. 216, 90–97 (2015).
[Crossref]

J. Oceanol. Limnol. (1)

L. Li, S. Lü, and J. Cen, “Spatio-temporal variations of Harmful algal blooms along the coast of Guangdong, Southern China during 1980–2016,” J. Oceanol. Limnol. 37(2), 535–551 (2019).
[Crossref]

Limnol. Oceanogr. (1)

G. Neukermans, R. A. Reynolds, and D. Stramski, “Optical classification and characterization of marine particle assemblages within the western Arctic Ocean,” Limnol. Oceanogr. 61(4), 1472–1494 (2016).
[Crossref]

Mar. Biotechnol. (1)

C. J. Kim, C. H. Kim, and Y. Sako, “Development of molecular identification method for genus Alexandrium (Dinophyceae) using whole-cell FISH,” Mar. Biotechnol. 7(3), 215–222 (2005).
[Crossref]

Meat Sci. (1)

X. Yao, F. Cai, P. Zhu, H. Fang, J. Li, and S. He, “Non-invasive and rapid pH monitoring for meat quality assessment using a low-cost portable hyperspectral scanner,” Meat Sci. 152, 73–80 (2019).
[Crossref]

Opt. Commun. (2)

F. Cai, J. Chen, X. Xie, and J. Xie, “The design and implementation of portable rotational scanning imaging spectrometer,” Opt. Commun. 459, 125016 (2020).
[Crossref]

F. Cai, Y. Wang, M. Gao, and S. He, “The design and implementation of a low-cost multispectral endoscopy through galvo scanning of a fiber bundle,” Opt. Commun. 428, 1–6 (2018).
[Crossref]

Opt. Express (4)

Optik (2)

F. Cai, T. Wang, J. Wu, and X. Zhang, “Handheld four-dimensional optical sensor,” Optik 203, 164001 (2020).
[Crossref]

X. Bi, S. Lin, S. Zhu, H. Yin, Z. Li, and Z. Chen, “Species identification and survival competition analysis of microalgae via hyperspectral microscopic images,” Optik 176, 191–197 (2019).
[Crossref]

Optoelectron. Instrument. Proc. (1)

S. M. Borzov and O. I. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Optoelectron. Instrument. Proc. 54(6), 582–599 (2018).
[Crossref]

Prog. Electromagn. Res. (2)

Z. Yong, S. Zhang, Y. Dong, and S. He, “Broadband nanoantennas for plasmon enhanced fluorescence and Raman spectroscopies,” Prog. Electromagn. Res. 153, 123–131 (2015).
[Crossref]

G. Wang, P. Kulinski, P. Hubert, A. Deguine, D. Petitprez, S. Crumeyrolle, E. Fertein, K. Deboudt, P. Flament, M. W. Sigrist, H. Yi, and W. Chen, “Filter-free light absorption measurement of volcanic ashes and ambient particulate matter using multi-wavelength photoacoustic spectroscopy,” Prog. Electromagn. Res. 166, 59–74 (2019).
[Crossref]

Remote Sens. (1)

J. D. O’Neill, M. Costa, and T. Sharma, “Remote sensing of shallow coastal benthic substrates: In situ spectra and mapping of eelgrass (Zostera marina) in the Gulf Islands National Park Reserve of Canada,” Remote Sens. 3(5), 975–1005 (2011).
[Crossref]

Remote Sens. Environ. (2)

E. Belluco, M. Camuffo, S. Ferrari, L. Modenese, S. Silvestri, A. Marani, and M. Marani, “Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing,” Remote Sens. Environ. 105(1), 54–67 (2006).
[Crossref]

J. Uitz, D. Stramski, R. A. Reynolds, and J. Dubranna, “Assessing phytoplankton community composition from hyperspectral measurements of phytoplankton absorption coefficient and remote-sensing reflectance in open-ocean environments,” Remote Sens. Environ. 171, 58–74 (2015).
[Crossref]

Rev. Chim. (1)

C. Bumbac, E. Manea, A. Banciu, C. Stoica, I. Ionescu, V. Badescu, and M. N. Lazar, “Identification of physical, morphological and chemical particularities of mixed microalgae - Bacteria granules,” Rev. Chim. 70(1), 275–277 (2019).
[Crossref]

Sci. Rep. (2)

F. Cai, W. Lu, W. Shi, and S. He, “A mobile device-based imaging spectrometer for environmental monitoring by attaching a lightweight small module to a commercial digital camera,” Sci. Rep. 7(1), 15602 (2017).
[Crossref]

Y. Shao, L. Jiang, H. Zhou, J. Pan, and Y. He, “Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology,” Sci. Rep. 6(1), 24221 (2016).
[Crossref]

Sensors (1)

Z. Xu, E. Forsberg, Y. Guo, F. Cai, and S. He, “Light-sheet microscopy for surface topography measurements and quantitative analysis,” Sensors 20(10), C1 (2020).
[Crossref]

Spectrochim. Acta, Part A (1)

S. He, S. Fang, W. Xie, P. Zhang, Z. Li, D. Zhou, Z. Zhang, J. Guo, C. Du, J. Du, and D. Wang, “Assessment of physiological responses and growth phases of different microalgae under environmental changes by Raman spectroscopy with chemometrics,” Spectrochim. Acta, Part A 204, 287–294 (2018).
[Crossref]

Spectrosc. Lett. (1)

L. Wei, K. Su, S. Zhu, H. Yin, Z. Li, Z. Chen, and M. Li, “Identification of microalgae by hyperspectral microscopic imaging system,” Spectrosc. Lett. 50(1), 59–63 (2017).
[Crossref]

Talanta (1)

L. Wang, H. Pu, and D. W. Sun, “Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging,” Talanta 147, 422–429 (2016).
[Crossref]

Water, Air, Soil Pollut. (1)

H. Pu, L. Wang, D. W. Sun, and J. H. Cheng, “Comparing Four Dimension Reduction Algorithms to Classify Algae Concentration Levels in Water Samples Using Hyperspectral Imaging,” Water, Air, Soil Pollut. 227(9), 315 (2016).
[Crossref]

Other (1)

A. M. Marbà-Ardébol, J. Emmerich, M. Muthig, P. Neubauer, and S. Junne, “In situ microscopy for real-time determination of single-cell morphology in bioprocesses,” J. Vis. Exp. 2019(154), 1–9 (2019).

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (8)

Fig. 1.
Fig. 1. (a) The full THMI system. (b) Schematic diagram of the transmission hyperspectral microscopic imager. 1: LED illuminator, 2: condenser, 3: sample and glass slide, 4: objective, 5: imaging lens, 6: slit, 7: doublet lens, 8: PGP (prism-grating-prism) structure, 9: tube lens, 10: CMOS camera. (c) Reconstructed spatial image of the resolution test target (1951 USAF-R1DS1P). Resolvable lines in element 1 of group 7 (∼3.9 µm) of the resolution test target are indicated. (d) Original spectral image of the calibration mercury lamp captured by the THMI. (e) Calibration result between the wavelength and pixel index. (f) Measured spectrum of the calibration mercury lamp. The spectral resolution is about 3 nm.
Fig. 2.
Fig. 2. Hyperspectral images of three species of microalgae. (a) phaeocystis, (b) chlammydomonas, (c) chaetoceros. Inserted (blue) images show their corresponding optical microscopic images. Scale bar: 50 µm.
Fig. 3.
Fig. 3. The process of ROI separation and average transmission spectrum extraction. (a) Gray spatial hyperspectral image of the chlammydomonas. (b) Corresponding gray histogram of (a). (c) Binary image of the sample, i.e. the image mask template. d) Purified hyperspectral image of the sample after masking. (e) The average transmission spectrum extracted from (d).
Fig. 4.
Fig. 4. Verification of absorption characteristics of three microalgae. (a) Original transmission spectra of the LED light source and three microalgae. (b) Normalized spectra of (a) calculated by Eq. (2). (c) Transmittance of the microalgae relative to the LED light source. (d) Absorbance of the microalgae measured by a commercial spectrophotometer.
Fig. 5.
Fig. 5. (a) Scatter plot of the scores of PC2 versus PC1 of three microalgae along with the linear SVM classifiers. The entire two-dimensional space is divided into three regions as labeled. (b) Confusion matrix of all transmission spectra for 180 samples (including 60 chaetoceros, 60 chlamydomonas and 60 phaeocystis). (c) The ROC curves corresponding to the SVM classifiers in (a).
Fig. 6.
Fig. 6. (a) Scatter plot of spectral peak intensity ratio I(680)/I(550) versus I(440)/I(550) for the three microalgae along with the linear SVM classifiers. The entire two-dimensional space is divided into three regions as labeled. (b) Confusion matrix of the transmission spectra for all 180 samples (60 chaetoceros, 60 chlamydomonas and 60 phaeocystis). (c) ROC curves corresponding to the SVM classifiers in (a).
Fig. 7.
Fig. 7. Demonstration for the species identification from a group of mixed microalgae. (a) Hyperspectral image of the mixed microalgae at the broad visible bands. (b) Hyperspectral image of the mixed microalgae at the single spectral band (680 nm). (c) The result of species identification on (a) after adding the image mask, the blue and red regions represent the chlamydomonas and phaeocystis, respectively. (d) The template image mask, generated by threshold segmentation on (b).
Fig. 8.
Fig. 8. (a) Growth curve of phaeocystis over 25 days. 1: lag phase, 2: exponential growth phase, 3: stable phase, 4: decline phase. (b) Normalized transmission spectra of phaeocystis. (c) Predicted results of the growth stage by the training set. (d) Predicted results of the growth stage by the test set.

Tables (2)

Tables Icon

Table 1. 18 (6×3) groups of microalgae species.

Tables Icon

Table 2. Prediction performances of five supervised learning models.

Equations (6)

Equations on this page are rendered with MathJax. Learn more.

λ = α 0 + a 1 x + a 2 x 2 ,
T ( λ ) ¯ = 1 N u m x , y H ( x , y , λ ) ( x , y ) R O I
I n o r m ( λ ) = I o r i g i n ( λ ) I min I max I min
A c c u r a c y = T P + T N T P + F P + F N + T N ,
S e n s i t i v i t y = T P T P + F N ,
S p e c i f i c i t y = T N T N + F P .

Metrics