Automated segmentation algorithm for detection of changes in vaginal epithelial morphology using optical coherence tomography

Abstract

We have explored the use of optical coherence tomography (OCT) as a noninvasive tool for assessing the toxicity of topical microbicides, products used to prevent HIV, by monitoring the integrity of the vaginal epithelium. A novel feature-based segmentation algorithm using a nearest-neighbor classifier was developed to monitor changes in the morphology of vaginal epithelium. The two-step automated algorithm yielded OCT images with a clearly defined epithelial layer, enabling differentiation of normal and damaged tissue. The algorithm was robust in that it was able to discriminate the epithelial layer from underlying stroma as well as residual microbicide product on the surface. This segmentation technique for OCT images has the potential to be readily adaptable to the clinical setting for noninvasively defining the boundaries of the epithelium, enabling quantifiable assessment of microbicide-induced damage in vaginal tissue.

Fig. 1

System block diagram. (a) Segmentation system. (b) Postprocessing module.

Fig. 2

Feature images. (a), Gabor filter. (b), Eight-tap Daubechies wavelet filter. (c), Laws filter followed by standard deviation.

Fig. 3

Representative OCT images of the sheep vagina. (a), (d), (g), Original. (b), (e), (h), Segmented. (c), (f), (i), Output images.

Fig. 4

Representative OCT images of the sheep vagina after treatment with 2% N9. (a), (d), (g), Original. (b), (e), (h), Segmented. (c), (f), (i), Output images.

Fig. 5

Representative histologic and OCT images of the sheep cervicovaginal epithelium after treatment with placebo (a) (b) or 2% N9 (c) (d).