Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Journal Home About Issues in Progress Current Issue All Issues Feature Issues

Multispectral digital microscopy for in vivo monitoring of oral neoplasia in the hamster cheek pouch model of carcinogenesis

Sun Young Park, Tom Collier, Jesse Aaron, Mia K. Markey, Rebecca Richards-Kortum, Konstantin Sokolov, Nick Mackinnon, Calum MacAulay, Lezlee Coghlan, Andrea Milbourne, and Michele Follen

Open Access Open Access

Abstract

In this study we use a multi-spectral digital microscope (MDM) to measure multi-spectral auto-fluorescence and reflectance images of the hamster cheek pouch model of DMBA (dimethylbenz[α]anthracene)-induced oral carcinogenesis. The multi-spectral images are analyzed both in the RGB (red, green, blue) color space as well as in the YCbCr (luminance, chromatic minus blue, chromatic minus red) color space. Mean image intensity, standard deviation, skewness, and kurtosis are selected as features to design a classification algorithm to discriminate normal mucosa from neoplastic tissue. The best diagnostic performance is achieved using features extracted from the YCbCr space, indicating the importance of chromatic information for classification. A sensitivity of 96% and a specificity of 84% were achieved in separating normal from abnormal cheek pouch lesions. The results of this study suggest that a simple and inexpensive MDM has the potential to provide a cost-effective and accurate alternative to standard white light endoscopy.

©2005 Optical Society of America

Full Article  |  PDF Article
More Like This
Optimal fluorescence excitation wavelengths for detection of squamous intra-epithelial neoplasia: results from an animal model

Lezlee Coghlan, Urs Utzinger, Rebekah Drezek, Douglas Heintzelman, Andres Zuluaga, Carrie Brookner, Rebecca Richards-Kortum, Irma Gimenez-Conti, and Michele Follen
Opt. Express 7(12) 436-446 (2000)

Dark field optical imaging reveals vascular changes in an inducible hamster cheek pouch model during carcinogenesis

Fangyao Hu, Robert Morhard, Helen A. Murphy, Caigang Zhu, and Nimmi Ramanujam
Biomed. Opt. Express 7(9) 3247-3261 (2016)

Comparison of a physical model and principal component analysis for the diagnosis of epithelial neoplasias in vivo using diffuse reflectance spectroscopy

Melissa C. Skala, Gregory M. Palmer, Kristin M. Vrotsos, Annette Gendron-Fitzpatrick, and Nirmala Ramanujam
Opt. Express 15(12) 7863-7875 (2007)

View More...

Cited By

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

Alert me when this article is cited.


Figures (8)
Fig. 1.
Fig. 1. (a) System diagram and (b) a photograph of the MDM system

Download Full Size | PDF

Table 1.
Table 1. Overview of the study design. DMBA weekly treatment frequency is indicated by the number in ach cell; cells without a number indicate no DMBA treatment. Cells are color coded to indicate image acquisition and tissue classification. Different colors represent different tissue classifications: cyan for normal, green for intermediate, and red for neoplastic.

Download Full Size | PDF

Fig. 2.
Fig. 2. Time course of RGB images for a representative DMBA treated hamster : 1st week, b) 5th week, c) 7th week d) 11th week, and e) 13th week (left: white light reflectance images, middle: 345 nm excited fluorescence images and right: 440 nm excited autofluorescence images).

Download Full Size | PDF

Fig. 3.
Fig. 3. Relative frequency histograms of the mean intensity of pixels randomly chosen from fluorescence images at (a) 345 nm and (b) 440 nm excitation in the normal and neoplastic groups. The left column shows data from the red channel, the middle column from the green channel and the right column from the blue channel.

Download Full Size | PDF

Fig. 4.
Fig. 4. Two dimensional scatter plots of the statistical parameters from pixels randomly chosen from fluorescence images at 345 nm excitation vs the same parameters at 440 nm excitation, including (a) mean intensity, (b) standard deviation, (c) skewness and (d) kurtosis. The left column shows data from the red channel, the middle column from the green channel and the right column from the blue channel. A data point is shown for each hamster at each time point in the normal, intermediate and neoplastic groups.

Download Full Size | PDF

Fig. 5.
Fig. 5. Relative frequency histograms of the mean intensity of pixels randomly chosen from fluorescence images at (a) 345 nm and (b) 440 nm excitation in the normal and neoplastic groups. The left column shows data from the Y channel, the middle column from the Cb channel and the right column from the Cr channel.

Download Full Size | PDF

Fig. 6.
Fig. 6. Two dimensional scatter plots of the statistical parameters from pixels randomly chosen from fluorescence images at 345 nm excitation vs the same parameters at 440 nm excitation, including (a) mean intensity, (b) standard deviation, (c) skewness and (d) kurtosis. The left column shows data from the Y channel, the middle column from the Cb channel and the right column from the Cr channel. A data point is shown for each hamster at each time point in the normal, intermediate and neoplastic groups.

Download Full Size | PDF

Table 2.
Table 2. Classification results using the input data from images in the YCbCr color space for each hamster at each time point. Colored cells indicate time points at which images were acquired. The cells are color-coded to indicate which group the images were assigned to as in Table 1. The results of the classification algorithm are represented by the letter in the cell, where N indicates the measurement was classified as normal and A indicates the measurement was classified as neoplastic. Circled letters indicate misclassifications for hamsters in the normal and neoplastic groups.

Download Full Size | PDF

Equations (3)

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

Y = c 1 R + c 2 G + c 3 B ,
C b = B − Y 2 − 2 c 3 ,
C r = R − Y 2 − 2 c 1 ,
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use