Open Access
Add to BibSonomy
Abstract
Lipid distribution in the liver provides crucial information for diagnosing the severity of fatty liver and fatty liver-associated liver cancer. Therefore, a noninvasive, label-free, and quantitative modality is eagerly anticipated. We report near-infrared hyperspectral imaging for the quantitative visualization of lipid content in mouse liver based on partial least square regression (PLSR) and support vector regression (SVR). Analysis results indicate that SVR with standard normal variate pretreatment outperforms PLSR by achieving better root mean square error (15.3 mg/g) and higher determination coefficient (0.97). The quantitative mapping of lipid content in the mouse liver is realized using SVR.
© 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
1. Introduction
Nonalcoholic fatty liver disease (NAFLD), including simple nonalcoholic fatty liver and nonalcoholic steatohepatitis (NASH), is one of the most common liver diseases worldwide, which can advance to liver cirrhosis and even hepatocellular carcinoma (HCC) [1–3]. The accumulation of excess lipids, such as triglycerides, in liver tissue is the distinctive feature of NAFLD [4,5]. Liver biopsy is the current reference standard for the definite diagnosis of NAFLD with a histology of intrahepatocellular fat accumulation [6]. The intrinsic limitations of biopsy, such as sampling error, difficulty in repeating, and invasiveness, necessitate the development of noninvasive and quantitative diagnosis. Ultrasonography and computed tomography can be used as noninvasive diagnostic tools for NAFLD; however, both lack the ability for the sensitive and fine detection of mild steatosis and slight changes in the fat content [7,8]. Magnetic resonance spectroscopy/imaging has been regarded as the most accurate quantitative method for measuring the fat content in the liver [9]. Although such diagnostic modalities have demonstrated in vivo feasibility for clinical use, a substantial need remains for the further development of noninvasive, quantitative, and rapid diagnostic modalities, with considerably higher spatial resolution, in particular, compared to magnetic resonance imaging (1–2 mm), computed tomography (0.5 mm) [10], and ultrasonography (∼0.5 mm) [11].
Spectroscopic and imaging techniques in the diffuse reflection mode provide a variety of clinically relevant information on the physiological composition, structure, and function of tissue [12], as well as sufficiently high spatial resolution down to the sub-micrometer level [13,14]. The visible and near-infrared region (VIS-NIR, approximately 400–1000 nm) is generally used to monitor the functional status of tissue by measuring the prominent absorption of oxygenated and deoxygenated hemoglobin [15–17]. For estimating the lipid concentration, the application of the shortwave infrared region (SWIR, 1000–2000 nm) is more advantageous than the VIS-NIR region. The SWIR region provides not only higher penetration depth but also beneficial information on the chemical composition due to the overtone and combination vibrational modes that induce 10–2 times weaker absorption compared to the midinfrared region. In addition, the absorption feature of lipids (1040, 1200, 1400, and 1700 nm) is more recognizable than in the VIS-NIR region [18]. An interesting attempt that takes advantage of the subtle lipid absorption in the SWIR region is photoacoustic imaging, which is a modality that combines optical excitation and ultrasound detection for in vivo vascular lipid detection using 1210-nm pulsed laser excitation [19]. Furthermore, some recent works demonstrated volumetric/contrast-enhanced lipid quantification based on bimodal photoacoustic tomography and ultrasound imaging [20] and photoacoustic imaging with the use of nanoprobes [21], both aiming for atherosclerosis. Such modalities are promising because they offer less-invasive optical contrast of tissue; however, very few studies on label-free quantitative investigation of lipids specifically for liver have been reported.
Hyperspectral imaging (HSI), first developed for the remote sensing of earth in the 1980s [22], integrates conventional spectroscopy and imaging in order to simultaneously obtain spatial (x, y) as well as spectral (λ) information. HSI has been intensively explored for the quality assessment of agricultural and pharmaceutical products [23,24], forensic sciences [25,26], and defense and security [27,28], among others. As an alternative to the existing diagnostics, medical HSI has been receiving increasing attention because it is a fully noninvasive, noncontact, nonionizing, and label-free technique [29–31]. Medical HSI applications that employ the NIR region (>700 nm) specifically for critical spectral information include the label-free detection of biomarkers [32–34], blood vessel visualization [35,36], cancer detection [37–40], and laparoscopic surgical guidance [41,42]. Many of the above-mentioned medical NIR-HSI applications have successfully used the emerging development of machine learning algorithms, and positive results for the detection of lipids have been realized. Chihara et al. [36] demonstrated the invasive and in situ detection of plaque in rabbit vessels through NIR-HSI at a spectral range of 1000–2350 nm. Their classification model based on the support vector machine (SVM), which has been extensively used due to its excellent multiparametric classification, achieved the delineation of atherosclerotic plaque containing cholesterol and fat as the major components. Ma et al. [43] recently reported the chemical mapping of monosaturated and polysaturated fatty acids in pork meats through reflectance NIR-HSI with the least squares SVM. However, limited progress has been made in the realization of quantitative lipid imaging for liver investigation, in particular, because of the excess data derived from the complicated correlation among neighboring bands in the SWIR absorption spectra. Therefore, it is essential to develop a label-free NIR-HSI system combined with a regression analytical model for lipid content estimation in the liver.
In this paper, we demonstrated the capability of using reflectance NIR-HSI with support vector regression (SVR) to perform ex vivo quantitative lipid visualization in mouse liver. The NIR-HSI system was based on a line-scanning system equipped with an NIR sensitive camera (spectral sensitivity: 900–1700 nm). The reflectance spectra were obtained at 1000–1600 nm through NIR-HSI. Liver samples were obtained from high-fat diet fed and normal-diet fed mice with various feeding durations and age. Two regression models, the partial least square regression (PLSR) and SVR, were evaluated using the coefficient of determination (R2) and root mean square error (RMSE).
2. Materials and methods
2.1 Sample preparation
All the animal experiments followed the protocols approved by the Animal Care and Use Committee of the Tokyo University of Science and Osaka City University. C57BL/6N mice and ICR mice were purchased from CLEA, Japan Inc. and Sankyo Labo Service, Japan, respectively. Male as well as female mice were used in this study. The C57BL/6NL and ICR mice were maintained under specific pathogen-free conditions on a 12-h light-dark cycle, and fed normal diet (ND) (CE-2, CLEA Japan Inc.) or high-fat diet (HFD) (D12492, D17011206, D17011207, Research Diets Inc.). The three HFDs (5.2 kcal/gm) provided comparable amounts of protein (20% energy), carbohydrate (20% energy), and total fat (60% energy). All these three HFDs contain the same 270gm% fat, but are composed of different types of oil. D12492 contains 245 gm of lard and 25 gm of Soybean oil. D17011206 contains 250.4 gm of Coconut oil and 19.6 gm of Safflower oil. D17011207 contains 151.6 gm Coconut oil and 118.4 gm of Safflower oil. Such a variety of diets feeding rendered mice harboring a wide range of lipid content in their livers. The livers isolated from the blood-removed mice were excised into approximately 3-mm-thick sections. These liver samples were first investigated using the NIR-HSI system. After image acquisition, the samples were processed to evaluate their lipid content.
2.2 Determination of the lipids extracted from mouse livers
The lipid content (LC; unit: mg/g) in mouse liver samples—the ratio of the extracted total lipid weight to the liver weight—is used for establishing the regression models. Folch extraction is a well-established protocol for isolating and purifying lipids in animal tissue [44]; this method was employed for extracting the total lipid content from each liver section, and the lipid content dissolved in organic solvent was measured. After acquiring the spectral images of the liver sample, the weight of the liver sample was measured using an electronic scale. The sample was then placed in a 15-mL falcon tube and a 2:1 (v/v) chloroform-methanol mixture was added to the tube. The lipids were collected by homogenizing the liver sample and transferring to the mixture. The lipid-containing mixture was then moved, through a filter paper, to another 15-mL falcon tube. After adding 2-mL of distilled water to the tube, ultracentrifugation was performed at 4000 rpm for 5 min. The organic fraction, which was thermodynamically separated from the tube, was then placed in a glass petri dish and heated on a hotplate to 90 °C, until the organic solvent completely evaporated. The weight of the lipids remaining in the dish was measured using an electronic scale. Because the liver weight varied among samples, the LC was calculated by dividing the lipid weight based on the liver weight for further analysis.
2.3 Near-infrared hyperspectral imaging system and data treatment
A line-scanning NIR-HSI system was used to obtain the hyperspectral images of the mouse liver samples, as schematically shown in Fig. 1. The system comprises an NIR reflectance imaging spectrometer (ImSpector N17E, SPECIM, Finland) coupled to an NIR sensitive camera (XEVA-1.7-320, Xenics, Belgium) and NIR objective lens (SWIR series 83–160, focal length 25 mm, Edmund Optics, USA), a rotation mirror for scanning the y-axis, light source, and personal computer hardware and software (JFE Techno-Research Corp., Tokyo, Japan). The NIR camera includes a two-dimensional indium gallium arsenide (InGaAs) sensor array (256 × 320 pixels corresponding to the wavelength and position, respectively), and can detect NIR light ranging from 900–1700 nm with a wavelength resolution of 2.2 nm. A halogen lamp (LA-150UE, Hayashi-Repic Inc, Tokyo, Japan) was employed as the light source and was attached to two flexible fiber light guides to irradiate the samples from both sides at 45°. Each liver sample was scanned using a 40 × 100-mm2 gold-coated mirror placed on a motorized rotation stage (SGSP-60YAW-OB, OptoSigma, Tokyo, Japan), while the camera acquired x-λ data. The frame rates ranged from 60–340 Hz, and the exposure time was fixed at 30 ms. To improve the signal-to-noise ratio, 16 scans were performed for each sample, and the averages of 16 full images for each wavelength were used for further analysis. The hyperspectral images were calibrated using white and dark reference images; a white reference plate was observed under the same condition, and the dark images were obtained by turning-off the illumination and covering the lens with a cap. Note that the power of the halogen lamp was controlled such that the sample temperature was stable. The NIR reflectance images were normalized to determine the relative reflectance R(λ) using the following equation:
Fig. 1. Schematic of the near-infrared hyperspectral imaging (NIR-HSI) system. The illumination path is shown in yellow, and the imaging path in black. An imaging spectrometer, equipped with an InGaAs CCD camera and a short-wave infrared (SWIR) lens, is placed in front of a gold-coated rotation mirror that enables a linearly scan of the sample- of-interest. The image acquisition and scanning mirror is controlled through an in-house data acquisition software. A slit installed in the imaging spectrometer selectively passes the light reflected at the central region of the rotation mirror.
2.4 Statistical modeling analysis
For quantitative regression modelling, PLSR and SVR developed using a kernel-based machine learning package Kernlab (version 2.5) with slight modification were used [45]. PLSR is an effective multiparametric linear statistical analysis as demonstrated in various biochemical modeling with HSI [43,46] and is suitable for handling a reflectance spectrum with several collinear variables [47]. This model is generally the first choice for building a predictive model; however, it may generate complicated results when the data are nonlinear regular. On the other hand, SVR is a nonparametric supervised machine learning algorithm, which is extended from the SVM [48]. The SVR model can transform a nonlinear regression problem into linear regression through the implementation of a kernel function [49]. This function can project the original feature space into higher dimensional space by finding a hyperplane that separates the largest section of datapoints with maximum margin among the classes. Among the various kernel functions such as the linear function, polynomial function, radial basis function (RBF), and sigmoid function, the RBF was used as the kernel because of its good performance and fewer input parameters (C, ɛ, and γ). γ, which defines the cost function, was first determined in order to minimize the variance of the Gram matrix of the training dataset. The two parameters, ɛ and C, representing the efficiency and cost of the kernel function, respectively, were determined through two-fold cross validation. NIR reflectance spectra are affected by scattering on the sample surface or the dark-current noise of the camera. Several combinations of preprocessing methods for the spectra, such as the standard normal variance (SNV) [50] and the first-order derivative, were evaluated. SNV was performed on the individual spectrum of each liver sample using the mean and standard deviation of the spectrum-of-interest. The modified spectrum is as follows:
3. Results and discussion
3.1 Analysis of the lipid content and NIR absorption spectra
The LCs in mouse liver samples (n = 75), defined as the ratio of the extracted lipid weight to the liver weight, were determined through the Folch extraction method. The LCs in the liver samples ranged from 32.6–296.8 mg/g with a mean value of 166.5 ± 15.5 mg/g (mean ± standard deviation). The 75 liver samples were categorized into five groups depending on their lipid content: group A- 32.6–67.6 mg/g; group B- 71.3–115.0 mg/g; group C- 139.6–207.4 mg/g; group D- 207.9–250.9 mg/g; group E- 251.0–296.8 mg/g. Table 1 lists the lipid content and weight of the liver samples for each group. Detailed information on all the liver samples is summarized in Table S1. The profiles of fatty acids in the HFD-fed mouse livers have been observed in previous studies: oleic acid (C18:1, 31%), palmitic acid (C16:0, 28%), linoleic acid (C18:2, 14%), and docosahexaenoic acid (C22:6, 8%) [51]. Given that the liver samples used follow the similar trend, the total LC differences among the group A–E can be related to the differences in C18:1 and C16:0. Figure 2(a) displays a representative hyperspectral montage of a mouse liver, composed of absorption images obtained from 1000–1600 nm in 50-nm steps. The visible and pseudocolored NIR images of the same liver sample are also shown in Fig. 2(b) for comparison. The mean NIR absorbance spectra of the liver samples, depicted in Fig. 2(c), exhibits remarkable changes in the NIR absorption peak due to the water bands at approximately 1450 nm, attributed to the first overtone of the O–H bond stretching [17]. Another distinctive increase in the peaks at 1160 and 1210 nm corresponds to the second overtone band of the -CH and -CH2 groups, respectively [52,53]. The lipid absorption peak at 1210 nm is in good agreement with the measurements performed by Nachabé [18]. This absorption band is particularly important for discriminating the degree of saturation of the fatty acids. Furthermore, slight changes at 1000–1050 nm and 1350–1390 nm were observed, attributed to the weak combination bands of the -CH2 group. The SNV-processed absorbance was significantly higher in group E than in group A at 1180–1220 nm and 1360–1420 nm (Fig. 2(d)). The downward shift in the absorption spectrum baseline in the 1300–1600 nm range indicates that the relative quantity of water at the sample surface decreases with the increase in lipid content, and that SNV preprocessing successfully removes such baseline drift due to the difference in light scattering at the sample surface.
Fig. 2. Near-infrared hyperspectral data: (a) Montage of a representative hyperspectral cube composed of 275 channels. A hotter color indicates higher absorption. (b) Visible (upper) and near-infrared (lower) images of a representative liver sample (scale bar: 5 mm). (c, d) Averaged absorption spectra with or without standard normal variate (SNV) scattering correction obtained from liver samples with different lipid content (LC). All the liver samples are classified based on their LC values: group A- 32.6–67.6 mg/g; group B- 71.3–115.0 mg/g; group C-, 139.6–207.4 mg/g; group D- 207.9–250.9 mg/g; group E- 251.0–296.8 mg/g. Arrows in the spectra indicate the peak at 1210 nm that is derived from lipid absorption.
Table 1. Lipid content (mg/g) in the mouse liver samples and their weight (g) with the mean, standard deviation (SD), minimum (Min), and maximum (Max). All the liver samples are classified into five groups based on their lipid content.
3.2 PLSR analysis
After extraction of the mean NIR spectra and the corresponding lipid content measured as reference data, PLSR models were established to study the relationship between the spectra and lipid content, and select appropriate image preprocessing methods. Leave-one-out cross-validation was used to evaluate the PLSR models. The performance of the PLSR models for the prediction of the lipid content of individual liver samples was determined using various spectral preprocessing methods, which affected the resultant estimation errors (Table 2). SNV preprocessing provided the best cross-validation performance with R2 = 0.953 and RMSE = 13.34 mg/g. Figure 3(a) shows the correlation between the lipid contents obtained using the PLSR model and the Folch extraction method. The model used was analyzed using the regression coefficient (RC) curve to select the optimum wavelengths with large absolute values of the peaks and troughs (Fig. 3(b)). A total of 27 optimal wavelengths were selected based on the optimal latent variables (LVs) of the model. Wavelengths with large absolute RC values included 1083, 1089, 1216, 1392, 1430, 1432, 1416, 1434, and 1533 nm, some of which corresponded to the overtone or combination vibrations mentioned above. For example, 1216, 1392, and 1416 nm are the characteristic wavelengths that appear in the absorption spectrum of a lipid [18]. The prediction errors need to be reduced further for quantification objectives; the relative standard errors in all the PLSR models were always greater than 11% and the prediction errors in the 150–250 mg/g range were nonnegligible. The number of LVs for the PLSR model with SNV was remarkably high, leading to overfitting of the model. The PLSR model optimized with the 10 LVs nominated by the RC curve, underperformed, compared to the PLSR model with full wavelengths (R2 = 0.832). Therefore, alternative models are needed to improve the prediction accuracy; nonlinear models would be suitable because certain absorptions in the NIR range originate from combinational vibration, which has a nonlinear dependence on the wavelength.
Fig. 3. (a) Results of the PLSR model developed for predicting the lipid content in liver samples. (b) Regression coefficient curve of the PLSR model. The red circles represent the wavelengths that are selected based on the optimized latent variables of the PLSR model. The numbers represent the wavelengths that appear in the absorption spectra of lipids [18].
Table 2. Performance of the PLSR and SVR models in lipid content regression. Note: PLSR- partial least squares regression; SVR- support vector regression; LV- latent variable; R2- Coefficient of determination in the cross-validation, RMSE- root mean squared error; ME- mean error; SE- standard error.
3.3 SVR-based predictive models
Similar to PLSR model development, four preprocessing methods were used to build the SVR models. As shown in Table 2, three SVR models exhibited better performances than those of the PLSR. The SVR model with SNV exhibited the best performance with R2 = 0.968 and RMSE = 15.28 mg/g, with a relative standard error as less as 8.5% (Fig. 4(a)). To investigate the effect of the calibration sample size, the absolute prediction errors between the measured and predicted values were evaluated through leave-out-k cross-validation. n images (n = 75 in this case) were divided into a subset of k images used for training, whereas the other n – k images were used as the validation set (k = 5, 10, 20, 30, 45, 60, and 74). The case of k = 74 indicates leave-one-out cross-validation. All the training sample combinations were validated. The absolute prediction error was calculated for each iteration, and the mean with the standard deviation was used for the result. Figure 4(b) displays the convergence of the absolute prediction error as a function of the calibration sample size (n). The dashed curve fitted using the least-squares method is proportional to n–1/2, where the relative prediction errors are assumed to obey a normal distribution, as displayed in Fig. S2. The absolute prediction error for the SVR decreased with the increase in the calibration sample size; however, the error obtained for k ≥ 30 was nearly constant. This is attributed to the fact that each hyperspectral image of the liver includes a significantly large number of spectra (>1000) with a wide variety of corresponding lipid content, and therefore, the number of liver samples used, n = 75, is sufficient to establish a reliable SVR model.
Fig. 4. (a) Results of the SVR model developed for predicting the lipid content in liver samples. (b) Dependence of the absolute prediction error on the sample size (n). The error bars correspond to the standard deviation among different combinations of the selected samples out of the total 75 liver samples. The dashed curve (absolute error ∼ n–1/2) is fitted using the least squares method.
3.4 Lipid visualization in mouse liver
We demonstrate the application of the SVR model for visualizing the distribution of the lipid content in mouse liver samples. Pixelwise estimation of the lipid content was performed using the SVR model with SNV pretreatment. Figure 5(a) shows the distribution map of the lipid content in 15 liver samples. Three characteristic samples were selected from each group listed in Table 1. As indicated by the scale bar in Fig. 5(a), the lipid content increases from blue to red; the numbers shown below each color-coded image correspond to the measured lipid content. Note that the white regions were excluded from the region-of-interest during SVR processing. For comparison, the conventional RGB images of the same samples acquired using a digital camera are shown in Fig. 5(b). In the RGB images, the color and shape of the samples can be easily discerned, but clues regarding the lipid content cannot be found, and the visible color does not directly relate to the lipid content or its existence. Contrarily, the quantity and distribution of lipids can be clearly recognized in the images obtained through SVR analysis, which show unequal distribution of the lipid content in the samples. Such visualization was realized using the unique characteristics of HSI for possessing the spectral as well as spatial information of the samples [36,43,54]. Interestingly, the edges of certain liver samples were enhanced with higher predicted lipid content, compared to the measured values, which may be due to the irregular shape of the surface. Visualization of the lipid content is the most crucial step in demonstrating the NIR-HSI results for evaluating the lipid content in a pixelwise manner. For lipid visualization, NIR-HSI is advantageous with respect to the spatial resolution, compared to existing diagnostic modalities such as the MRI, computed tomography, and ultrasonography. The prediction images generated by the SVR model have a spatial resolution of 0.25 mm, which is approximately half that of ultrasonography. As a label-free imaging for quantitatively observing lipids in livers, this method provides one of the finest spatial resolutions. In our setup, the spatial resolution can be further improved by replacing the SWIR lens with a lens having a shorter working distance, for example.
Fig. 5. Visualization of the lipid content in mouse liver: (a) Quantitative mapping of the lipid content in the liver samples. The numbers on the right indicate the scale of the lipid content in the corresponding colors, and the values below the images indicate the lipid content measured using the Folch extraction method. It is to be noted that the white regions were excluded from the region-of-interest upon SVR processing because of pixel saturation or artificial noise. (b) Visible images corresponding to the quantitative mapping shown in (a).
In future, studies should be performed to demonstrate the feasibility of the discriminative imaging of various fatty acids and microscopic analysis through reflectance NIR-HSI. The degree of lipid saturation is identifiable in the SWIR absorption spectrum by, for example, the change at 1140 nm due to the overtone vibration of carbon–carbon double bonds. A quantitative classification model can be established by preparing an appropriate set of absorption spectra for each fatty acid as the training dataset. For realizing this, more GC measurements will be required to quantify and identify the fatty acids contained in liver samples. Toward histopathological analysis, the approach described in this study can be applied for the label-free, microscopic histopathological investigation of lipids. Staining the lipids in tissue using lipophilic dyes such as Nile Red and Oil Red O is a standard protocol to provide contrast in histopathological slides, and the visible color is crucial. Animal models of liver diseases such as NASH and HCC are routinely evaluated by visualizing the tissue morphology with hematoxylin and eosin (H&E) or Masson's trichrome stains. The infiltration of lipids and lipid droplets are consequently delineated as white voids, where H&E stain the nuclei in blue, and the cytoplasm and extracellular matrix in different shades of pink, and Masson's trichrome stains the nuclei in black, collagen in blue, and the muscles, erythrocytes, and cytoplasm in red. Some studies have proposed digital staining of the histopathological images of the kidney [55] and lung [56], which is a machine vision approach to overlay artificial color contrast over unstained images; however, quantitative, label-free lipid visualization is yet to be realized. In principle, our NIR-HSI system can visualize the lipid distribution in histopathological slides without requiring physical staining. Acquiring the very weak NIR absorption derived from the lipids in slides will be the key to developing a better regression model.
4. Conclusions
A near-infrared hyperspectral imaging (NIR-HSI) system was demonstrated for the ex vivo quantitative visualization of the lipid concentration and distribution in mouse liver. Hyperspectral images in the spectral range of 1000–1600 nm were analyzed using both linear partial least square regression (PLSR) and nonlinear support vector regression (SVR) algorithms to predict the lipid content, whereas the actual lipid contents were measured through the Folch extraction method. Mice were fed with normal diets and high-fat diets in order to create variation in the lipid content. The changes in the lipid content caused distinctive changes in the NIR absorption spectra. SVR models with standard normal variate preprocessing outperformed the PLSR models, with R2 = 0.968 and a mean absolute error of 10.9 mg/g (8.5%). In addition, color mapping of the lipid content was realized using SVR analysis, which suggested uneven lipid distribution in each liver sample. Thus, NIR-HSI was proven to be a promising approach for the ex vivo detection of the lipid content in liver. This platform is expected to offer a new strategy for the noninvasive analysis of lipid localization in the liver, which can improve the diagnosis of nonalcoholic fatty liver diseases and contribute to the better understanding of the mechanism of the pathogenesis of steatosis.
Funding
Japan Society for the Promotion of Science (19H04002, 20K16121); Japan Agency for Medical Research and Development (JP20gm1010009h0003); Ministry of Education, Culture, Sports, Science and Technology (S1511012).
Acknowledgments
We would like to thank Editage (www.editage.com) for English language editing.
Disclosures
The authors declare no conflicts of interest.
See Supplement 1 for supporting content.
References
1. W. N. Hannah Jr and S. A. Harrison, “Noninvasive imaging methods to determine severity of nonalcoholic fatty liver disease and nonalcoholic steatohepatitis,” Hepatology 64(6), 2234–2243 (2016). [CrossRef]
2. G. A. Michelotti, M. V. Machado, and A. M. Diehl, “NAFLD, NASH and liver cancer,” Nat. Rev. Gastroenterol. Hepatol. 10(11), 656–665 (2013). [CrossRef]
3. P. Bannas, H. Kramer, D. Hernando, R. Agni, A. M. Cunningham, R. Mandal, U. Motosugi, S. D. Sharma, A. Munoz del Rio, L. Fernandez, and S. B. Reeder, “Quantitative magnetic resonance imaging of hepatic steatosis: Validation in ex vivo human livers,” Hepatology 62(5), 1444–1455 (2015). [CrossRef]
4. A. R. Araújo, N. Rosso, G. Bedogni, C. Tiribelli, and S. Bellentani, “Global epidemiology of non-alcoholic fatty liver disease/non-alcoholic steatohepatitis: What we need in the future,” Liver Int. 38, 47–51 (2018). [CrossRef]
5. M. E. Rinella, “Nonalcoholic fatty liver disease: A systematic review,” JAMA 313(22), 2263–2273 (2015). [CrossRef]
6. D. Joy, V. R. Thava, and B. B. Scott, “Diagnosis of fatty liver disease: Is biopsy necessary?” Eur. J. Gastroenterol. Hepatol. 15(5), 539–543 (2003). [CrossRef]
7. S. Lv, S. Jiang, S. Liu, Q. Dong, Y. Xin, and S. Xuan, “Noninvasive quantitative detection methods of liver fat content in nonalcoholic fatty liver disease,” J. Clin. Transl. Hepatol. 6(2), 217–221 (2018). [CrossRef]
8. G. Guaraldi, G. Besutti, C. Stentarelli, S. Zona, L. Nocetti, P. Loria, S. Ballestri, L. Losi, P. Torricelli, and G. Ligabue, “Magnetic resonance for quantitative assessment of liver steatosis: A new potential tool to monitor antiretroviral-drug-related toxicities,” Antiviral Ther. 17(6), 965–971 (2012). [CrossRef]
9. M. Thiele, V. Rausch, G. Fluhr, M. Kjærgaard, F. Piecha, J. Mueller, B. K. Straub, M. Lupșor-Platon, V. De-Ledinghen, H. K. Seitz, S. Detlefsen, B. Madsen, A. Krag, and S. Mueller, “Controlled attenuation parameter and alcoholic hepatic steatosis: Diagnostic accuracy and role of alcohol detoxification,” J. Hepatol. 68(5), 1025–1032 (2018). [CrossRef]
10. E. Lin and A. Alessio, “What are the basic concepts of temporal, contrast, and spatial resolution in cardiac CT?” J. Cardiovasc. Comput. Tomogr. 3(6), 403–408 (2009). [CrossRef]
11. H. Hasegawa, “Improvement of range spatial resolution of medical ultrasound imaging by element-domain signal processing,” Jpn. J. Appl. Phys. 56(7S1), 07JF02 (2017). [CrossRef]
12. T. D. O’Sullivan, A. E. Cerussi, B. J. Tromberg, and D. J. Cuccia, “Diffuse optical imaging using spatially and temporally modulated light,” J. Biomed. Opt. 17(7), 0713111 (2012). [CrossRef]
13. G. Hong, S. Diao, J. Chang, A. L. Antaris, C. Chen, B. Zhang, S. Zhao, D. N. Atochin, P. L. Huang, K. I. Andreasson, C. J. Kuo, and H. Dai, “Through-skull fluorescence imaging of the brain in a new near-infrared window,” Nat. Photonics 8(9), 723–730 (2014). [CrossRef]
14. K. Soga, M. Umezawa, and K. Okubo, eds., Transparency in Biology: Making the Invisible Visible (Springer Singapore, 2021), p. 263.
15. F. F. Jobsis, “Noninvasive, infrared monitoring of cerebral and myocardial oxygen sufficiency and circulatory parameters,” Science 198(4323), 1264–1267 (1977). [CrossRef]
16. M. Ferrari, I. Giannini, G. Sideri, and E. Zanette, “Continuous non invasive monitoring of human brain by near infrared spectroscopy,” in Oxygen Transport to Tissue VII, F. Kreuzer, S. M. Cain, Z. Turek, and T. K. Goldstick, eds. (Springer US, 1985), pp. 873–882.
17. R. H. Wilson, K. P. Nadeau, F. B. Jaworski, B. J. Tromberg, and A. J. Durkin, “Review of short-wave infrared spectroscopy and imaging methods for biological tissue characterization,” J. Biomed. Opt. 20(3), 030901 (2015). [CrossRef]
18. R. Nachábe, B. H. W. Hendriks, A. E. Desjardins, M. van der Voort, M. B. van der Mark, and H. J. C. M. Sterenborg, “Estimation of lipid and water concentrations in scattering media with diffuse optical spectroscopy from 900 to 1600 nm,” J. Biomed. Opt. 15(3), 037015 (2010). [CrossRef]
19. G. S. Sangha, E. H. Phillips, and C. J. Goergen, “In vivo photoacoustic lipid imaging in mice using the second near-infrared window,” Biomed. Opt. Express 8(2), 736–742 (2017). [CrossRef]
20. G. S. Sangha and C. J. Goergen, “Label-free photoacoustic and ultrasound imaging for murine atherosclerosis characterization,” APL Bioeng. 4(2), 026102 (2020). [CrossRef]
21. Z. Xie, Y. Yang, Y. He, C. Shu, D. Chen, J. Zhang, J. Chen, C. Liu, Z. Sheng, H. Liu, J. Liu, X. Gong, L. Song, and S. Dong, “In vivo assessment of inflammation in carotid atherosclerosis by noninvasive photoacoustic imaging,” Theranostics 10(10), 4694–4704 (2020). [CrossRef]
22. A. F. H. Goetz, G. Vane, J. E. Solomon, and B. N. Rock, “Imaging spectrometry for earth remote sensing,” Science 228(4704), 1147–1153 (1985). [CrossRef]
23. A. Gowen, C. Odonnell, P. Cullen, G. Downey, and J. Frias, “Hyperspectral imaging – an emerging process analytical tool for food quality and safety control,” Trends Food Sci. Technol. 18(12), 590–598 (2007). [CrossRef]
24. M. Manley, “Near-infrared spectroscopy and hyperspectral imaging: Non-destructive analysis of biological materials,” Chem. Soc. Rev. 43(24), 8200–8214 (2014). [CrossRef]
25. M. Á. Fernández de la Ossa, J. M. Amigo, and C. García-Ruiz, “Detection of residues from explosive manipulation by near infrared hyperspectral imaging: A promising forensic tool,” Forensic Sci. Int. 242, 228–235 (2014). [CrossRef]
26. G. J. Edelman, E. Gaston, T. G. van Leeuwen, P. J. Cullen, and M. C. G. Aalders, “Hyperspectral imaging for non-contact analysis of forensic traces,” Forensic Sci. Int. 223(1-3), 28–39 (2012). [CrossRef]
27. S. Michel, P. Gamet, and M. Lefevre-Fonollosa, “HYPXIM — a hyperspectral satellite defined for science, security and defence users,” in 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2011), 1–4.
28. V. C. Coffey, “Hyperspectral imaging for safety and security,” Opt. Photonics News 26(10), 26–33 (2015). [CrossRef]
29. Q. Li, X. He, Y. Wang, H. Liu, D. Xu, and F. Guo, “Review of spectral imaging technology in biomedical engineering: Achievements and challenges,” J. Biomed. Opt. 18(10), 100901 (2013). [CrossRef]
30. G. Lu and B. Fei, “Medical hyperspectral imaging: A review,” J. Biomed. Opt. 19(09), 1–24 (2014). [CrossRef]
31. M. J. Khan, H. S. Khan, A. Yousaf, K. Khurshid, and A. Abbas, “Modern trends in hyperspectral image analysis: A review,” IEEE Access 6, 14118–14129 (2018). [CrossRef]
32. T. Wang, Q. Li, X. Li, S. Zhao, Y. Lu, and G. Huang, “Use of hyperspectral imaging for label-free decoding and detection of biomarkers,” Opt. Lett. 38(9), 1524–1526 (2013). [CrossRef]
33. X. Hadoux, F. Hui, J. K. H. Lim, C. L. Masters, A. Pébay, S. Chevalier, J. Ha, S. Loi, C. J. Fowler, C. Rowe, V. L. Villemagne, E. N. Taylor, C. Fluke, J.-P. Soucy, F. Lesage, J.-P. Sylvestre, P. Rosa-Neto, S. Mathotaarachchi, S. Gauthier, Z. S. Nasreddine, J. D. Arbour, M.-A. Rhéaume, S. Beaulieu, M. Dirani, C. T. O. Nguyen, B. V. Bui, R. Williamson, J. G. Crowston, and P. van Wijngaarden, “Non-invasive in vivo hyperspectral imaging of the retina for potential biomarker use in Alzheimer’s disease,” Nat. Commun. 10(1), 4227 (2019). [CrossRef]
34. S. S. More and R. Vince, “Hyperspectral imaging signatures detect amyloidopathy in Alzheimer’s mouse retina well before onset of cognitive decline,” ACS Chem. Neurosci. 6(2), 306–315 (2015). [CrossRef]
35. J. A. Chin, E. C. Wang, and M. R. Kibbe, “Evaluation of hyperspectral technology for assessing the presence and severity of peripheral artery disease,” J. Vasc. Surg. 54(6), 1679–1688 (2011). [CrossRef]
36. H. Chihara, N. Oishi, A. Ishii, T. Munemitsu, D. Arai, H. Ikeda, and S. Miyamoto, “In vivo detection of atherosclerotic plaque using non-contact and label-free near-infrared hyperspectral imaging,” Atherosclerosis 250, 106–113 (2016). [CrossRef]
37. H. Akbari, K. Uto, Y. Kosugi, K. Kojima, and N. Tanaka, “Cancer detection using infrared hyperspectral imaging,” Cancer Sci. 102(4), 852–857 (2011). [CrossRef]
38. H. Akbari, L. V. Halig, D. M. Schuster, A. Osunkoya, V. Master, P. T. Nieh, G. Z. Chen, and B. Fei, “Hyperspectral imaging and quantitative analysis for prostate cancer detection,” J. Biomed. Opt. 17(7), 0760051 (2012). [CrossRef]
39. B. Regeling, W. Laffers, A. O. H. Gerstner, S. Westermann, N. A. Müller, K. Schmidt, J. Bendix, and B. Thies, “Development of an image pre-processor for operational hyperspectral laryngeal cancer detection,” J. Biophotonics 9(3), 235–245 (2016). [CrossRef]
40. M. Halicek, H. Fabelo, S. Ortega, G. M. Callico, and B. Fei, “In-vivo and ex-vivo tissue analysis through hyperspectral imaging techniques: Revealing the invisible features of cancer,” Cancers 11(6), 756 (2019). [CrossRef]
41. K. J. Zuzak, S. C. Naik, G. Alexandrakis, D. Hawkins, K. Behbehani, and E. Livingston, “Intraoperative bile duct visualization using near-infrared hyperspectral video imaging,” Am. J. Surg. 195(4), 491–497 (2008). [CrossRef]
42. K. J. Zuzak, S. C. Naik, G. Alexandrakis, D. Hawkins, K. Behbehani, and E. H. Livingston, “Characterization of a near-infrared laparoscopic hyperspectral imaging system for minimally invasive surgery,” Anal. Chem. 79(12), 4709–4715 (2007). [CrossRef]
43. J. Ma and D.-W. Sun, “Prediction of monounsaturated and polyunsaturated fatty acids of various processed pork meats using improved hyperspectral imaging technique,” Food Chem. 321, 126695 (2020). [CrossRef]
44. J. Folch, M. Lees, and G. H. S. Stanley, “A simple method for the isolation and purification of total lipides from animal tissues,” J. Biol. Chem. 226(1), 497–509 (1957). [CrossRef]
45. A. Karatzoglou, A. Smola, K. Hornik, and A. Zeileis, “Kernlab - an S4 package for kernel methods in R,” J. Stat. Soft. 11(9), 1–20 (2004). [CrossRef]
46. Y.-Z. Feng and D.-W. Sun, “Near-infrared hyperspectral imaging in tandem with partial least squares regression and genetic algorithm for non-destructive determination and visualization of pseudomonas loads in chicken fillets,” Talanta 109, 74–83 (2013). [CrossRef]
47. S. Wold, M. Sjöström, and L. Eriksson, “PLS-regression: A basic tool of chemometrics,” Chemom. Intell. Lab. Syst. 58(2), 109–130 (2001). [CrossRef]
48. M. Abbaszadeh, A. Hezarkhani, and S. Soltani-Mohammadi, “Proposing drilling locations based on the 3D modeling results of fluid inclusion data using the support vector regression method,” J. Geochem. Explor. 165, 23–34 (2016). [CrossRef]
49. Z. Pan, C. Glennie, C. Legleiter, and B. Overstreet, “Estimation of water depths and turbidity from hyperspectral imagery using support vector regression,” IEEE Geosci. Remote S. 12(10), 2165–2169 (2015). [CrossRef]
50. R. J. Barnes, M. S. Dhanoa, and S. J. Lister, “Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra,” Appl. Spectrosc. 43(5), 772–777 (1989). [CrossRef]
51. L. Liu, L. Na, Y. Niu, F. Guo, Y. Li, and C. Sun, “An ultrasonic assisted extraction procedure to free fatty acids from the liver samples of mice,” J. Chromatogr. Sci. 51(4), 376–382 (2013). [CrossRef]
52. P. Hourant, V. Baeten, M. T. Morales, M. Meurens, and R. Aparicio, “Oil and fat classification by selected bands of near-infrared spectroscopy,” Appl. Spectrosc. 54(8), 1168–1174 (2000). [CrossRef]
53. F. Westad, A. Schmidt, and M. Kermit, “Incorporating chemical band-assignment in near infrared spectroscopy regression models,” J. Near Infrared Spectrosc. 16(3), 265–273 (2008). [CrossRef]
54. F. Zhu, D. Zhang, Y. He, F. Liu, and D.-W. Sun, “Application of visible and near infrared hyperspectral imaging to differentiate between fresh and frozen–thawed fish fillets,” Food Bioproc. Tech. 6(10), 2931–2937 (2013). [CrossRef]
55. P. A. Bautista, T. Abe, M. Yamaguchi, Y. Yagi, and N. Ohyama, “Digital staining of unstained pathological tissue samples through spectral transmittance classification,” Opt. Rev. 12(1), 7–14 (2005). [CrossRef]
56. N. Bayramoglu, M. Kaakinen, L. Eklund, and J. Heikkilä, “Towards virtual H&E staining of hyperspectral lung histology images using conditional generative adversarial networks,” in 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) (2017), 64–71.
