2019/07/24 by Yuan Xue, Qianying Zhou, Xue, Yuan +13 · 1 citation
Computer Science · Engineering · Medicine · #AI in cancer detection #Artificial intelligence #Centroid #Cervical Cancer and HPV Research #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #FOS: Electrical engineering #Feature vector #Generative Adversarial Networks and Image Synthesis #Grading (engineering) #Histopathology #Image and Video Processing (eess.IV) #Medicine #Pathology #Pattern recognition (psychology) #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1907.10655
MICCAI 2019
arxiv created 2019/07/24 · openalex publication_date 2019/07/24 · arxiv updated 2019/07/26 · openalex created_date 2019/07/30 · openalex updated_date 2026/08/06
Cervical intraepithelial neoplasia (CIN) grade of histopathology images is a crucial indicator in cervical biopsy results. Accurate CIN grading of epithelium regions helps pathologists with precancerous lesion diagnosis and treatment planning. Although an automated CIN grading system has been desired, supervised training of such a system would require a large amount of expert annotations, which are expensive and time-consuming to collect. In this paper, we investigate the CIN grade classification problem on segmented epithelium patches. We propose to use conditional Generative Adversarial Networks (cGANs) to expand the limited training dataset, by synthesizing realistic cervical histopathology images. While the synthetic images are visually appealing, they are not guaranteed to contain meaningful features for data augmentation. To tackle this issue, we propose a synthetic-image filtering mechanism based on the divergence in feature space between generated images and class centroids in order to control the feature quality of selected synthetic images for data augmentation. Our models are evaluated on a cervical histopathology image dataset with a limited number of patch-level CIN grade annotations. Extensive experimental results show a significant improvement of classification accuracy from 66.3% to 71.7% using the same ResNet18 baseline classifier after leveraging our cGAN generated images with feature-based filtering, which demonstrates the effectiveness of our models.