Automated identification of basal cell carcinoma by polarization-sensitive optical coherence tomography

Abstract

We report an automated classifier to detect the presence of basal cell carcinoma in images of mouse skin tissue samples acquired by polarization-sensitive optical coherence tomography (PS-OCT). The sensitivity and specificity of the classifier based on combined information of the scattering intensity and birefringence properties of the samples are significantly higher than when intensity or birefringence information are used alone. The combined information offers a sensitivity of 94.4% and specificity of 92.5%, compared to 78.2% and 82.2% for intensity-only information and 85.5% and 87.9% for birefringence-only information. These results demonstrate that analysis of the combination of complementary optical information obtained by PS-OCT has great potential for accurate skin cancer diagnosis.

Keywords: (100.2960) Image analysis; (110.5405) Polarimetric imaging; (170.1870) Dermatology; (170.3880) Medical and biological imaging; (170.4500) Optical coherence tomography.

Fig. 1

Representative histological (left column), intensity (middle column), and phase retardation (right column) images obtained from the same or similar locations in healthy (top row), endogenous BCC (top row), and allograft BCC (bottom row) mouse skin tissue. White arrows indicate location of tumors. The scale bars are applicable to all images.

Fig. 2

Surface segmentation and ROI selection for intensity images. The red and green curves represent the first and second (true) skin surface segmentations, respectively.

Fig. 3

Description of global intensity parameters. (a) An intensity image of mouse skin. (b) Averaged intensity A-line versus depth and visual guides to calculate parameters of interest. The black curve is averaged intensity A-line. The leftmost black, vertical dashed line indicates the starting position of the linear regression (red, dashed line), while the green line connects the starting point of the linear regression to the point 65 pixels below it and is used to calculate the thickness of the dermis layer.

Fig. 4

Description of global retardation parameters. (a) Phase retardation image of a mouse skin sample. (b) The red and yellow regions are the two sub-ROIs comprising the first and second 50 pixels below the surface. (c) The red and yellow curves show the mean retardation in each lateral line in the red and yellow areas, respectively. (d) The black curve is the difference between the red and yellow curves in (c), and the blue line is the binary signal created based on the threshold indicated by the black dashed line.

Fig. 5

Description of local retardation parameters. (a) The red box identifies a representative moving window in a retardation image. (b) A linear regression for the retardation curve was fit over the 30-pixel range having the lowest residual in a linear fit.

Fig. 6

ROCs of different classifiers based on using intensity-only, birefringence-only or intensity and birefringence parameters.

Fig. 7

Example PS-OCT images of a misclassified “normal sample.” The red arrow denotes a location showing BCC-like features.

Fig. 8

Performance changes in accuracy, sensitivity, and specificity of classifiers excluding a given proposed parameter. The excluded parameter ID corresponds to numbers shown in the third column of Tab. 1.