Cervical optical coherence tomography image classification based on contrastive self-supervised texture learning

Cervical cancer (CC) seriously affects the health of the female reproductive system. Optical coherence tomography (OCT) emerged as a noninvasive, high-resolution imaging technology for cervical disease detection. However, OCT image annotation is knowledge-intensive and time-consuming, which impedes the training process of deep-learning-based classification models.

This study aims to develop a computer-aided diagnosis (CADx) approach to classifying in-vivo cervical OCT images based on self-supervised learning.

In addition to high-level semantic features extracted by a convolutional neural network (CNN), the proposed CADx approach designs a contrastive texture learning strategy to leverage unlabeled cervical OCT images' texture features. We conducted 10-fold cross-validation on the OCT image dataset from a multicenter clinical study on 733 patients from China.

In a binary classification task for detecting high-risk diseases, including high-grade squamous intraepithelial lesion and CC, our method achieved an area-under-the-curve value of 0.9798 ± 0.0157 with a sensitivity of 91.17% ± 4.99% and a specificity of 93.96% ± 4.72% for OCT image patches; also, it outperformed two out of four medical experts on the test set. Furthermore, our method achieved 91.53% sensitivity and 97.37% specificity on an external validation dataset containing 287 three-dimensional OCT volumes from 118 Chinese patients in a new hospital using a cross-shaped threshold voting strategy.

The proposed contrastive-learning-based CADx method outperformed the end-to-end CNN models and provided better interpretability based on texture features, which holds great potential to be used in the clinical protocol of "see-and-treat."