Computer-Aided Diagnosis of Label-Free 3-D Optical Coherence Microscopy Images of Human Cervical Tissue

Ultrahigh-resolution optical coherence microscopy (OCM) has recently demonstrated its potential for accurate diagnosis of human cervical diseases. One major challenge for clinical adoption, however, is the steep learning curve clinicians need to overcome to interpret OCM images. Developing an intelligent technique for computer-aided diagnosis (CADx) to accurately interpret OCM images will facilitate clinical adoption of the technology and improve patient care.

497 high-resolution three-dimensional (3-D) OCM volumes (600 cross-sectional images each) were collected from 159 ex vivo specimens of 92 female patients. OCM image features were extracted using a convolutional neural network (CNN) model, concatenated with patient information [e.g., age and human papillomavirus (HPV) results], and classified using a support vector machine classifier. Ten-fold cross-validations were utilized to test the performance of the CADx method in a five-class classification task and a binary classification task.

An 88.3 ± 4.9% classification accuracy was achieved for five fine-grained classes of cervical tissue, namely normal, ectropion, low-grade and high-grade squamous intraepithelial lesions (LSIL and HSIL), and cancer. In the binary classification task [low-risk (normal, ectropion, and LSIL) versus high-risk (HSIL and cancer)], the CADx method achieved an area-under-the-curve value of 0.959 with an 86.7 ± 11.4% sensitivity and 93.5 ± 3.8% specificity.

The proposed deep-learning-based CADx method outperformed four human experts. It was also able to identify morphological characteristics in OCM images that were consistent with histopathological interpretations.

Label-free OCM imaging, combined with deep-learning-based CADx methods, holds a great promise to be used in clinical settings for the effective screening and diagnosis of cervical diseases.