Encoder-Weighted W-Net for Unsupervised Segmentation of Cervix Region in Colposcopy Images

SIMPLE SUMMARY: The cervix region segmentation significantly affects the accuracy of diagnosis when analyzing colposcopy. Detecting the cervix region requires manual, intensive, and time-consuming labor from a trained gynecologist. In this paper, we propose a deep learning-based automatic cervix region segmentation method that enables the extraction of the region of interest from colposcopy images in an unsupervised manner. The segmentation performance with a Dice coefficient improved from 0.612 to 0.710 by applying the proposed loss function and encoder-weighted learning scheme and showed the best performance among all the compared methods. The automatically detected cervix region can improve the performance of image-based interpretation and diagnosis by suggesting where the clinicians should focus during colposcopy analysis. ABSTRACT: Cervical cancer can be prevented and treated better if it is diagnosed early. Colposcopy, a way of clinically looking at the cervix region, is an efficient method for cervical cancer screening and its early detection. The cervix region segmentation significantly affects the performance of computer-aided diagnostics using a colposcopy, particularly cervical intraepithelial neoplasia (CIN) classification. However, there are few studies of cervix segmentation in colposcopy, and no studies of fully unsupervised cervix region detection without image pre- and post-processing. In this study, we propose a deep learning-based unsupervised method to identify cervix regions without pre- and post-processing. A new loss function and a novel scheduling scheme for the baseline W-Net are proposed for fully unsupervised cervix region segmentation in colposcopy. The experimental results showed that the proposed method achieved the best performance in the cervix segmentation with a Dice coefficient of 0.71 with less computational cost. The proposed method produced cervix segmentation masks with more reduction in outliers and can be applied before CIN detection or other diagnoses to improve diagnostic performance. Our results demonstrate that the proposed method not only assists medical specialists in diagnosis in practical situations but also shows the potential of an unsupervised segmentation approach in colposcopy.