Application of semi-supervised learning models in the Los Angeles grading of reflux esophagitis(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2025年第9期
- Page:
- 1236-1244
- Research Field:
- 医学人工智能
- Publishing date:
Info
- Title:
- Application of semi-supervised learning models in the Los Angeles grading of reflux esophagitis
- Author(s):
- ZHAO Hang1; 2; XU Xiaodan2; ZHU Jinzhou1
- 1. Department of Gastroenterology, the First Affiliated Hospital of Soochow University, Suzhou 215506, China 2. Department of Gastroenterology, Changshu Affiliated Hospital of Soochow University, Suzhou 215005, China
- Keywords:
- Keywords: reflux esophagitis self-supervised learning simple framework for contrastive learning of visual representation computer-aided diagnosis deep learning Grad-CAM
- PACS:
- R318；R571
- DOI:
- DOI:10.3969/j.issn.1005-202X.2025.09.016
- Abstract:
- Abstract: Objective To construct a classification model for the Los Angeles grading of endoscopic reflux esophagitis based on the SimCLR algorithms semi-supervised learning framework. Methods The designed learning framework was pre-trained on a large unlabeled dataset through self-supervised learning, and further finely tuned on a small labeled dataset according to the Los Angeles grading criteria. The performance test on the model was conducted on an independent dataset, and the proposed model was compared with the models of supervised learning algorithms and endoscopists in terms of accuracy, Matthews correlation coefficient, and Cohens kappa value. Finally, Grad-CAM and t-SNE were used for the visualization of the models interpretation. Results The SimCLR model with ResNet as the backbone network showed superior performance in accuracy (0.840), Matthews correlation coefficient (0.800), and Cohens kappa value (0.960) than the traditional supervised learning model with ResNet as the backbone (0.680, 0.601, and 0.870) as well as junior endoscopists (0.770, 0.713, and 0.940), but there was still a slight gap compared with senior endoscopists (0.850, 0.813, and 0.960). In addition, the results of t-SNE showed that self-supervised learning in SimCLR was more effective in clustering multi-dimensional samples than traditional supervised transfer learning. Conclusion Compared with traditional supervised learning methods, semi-supervised learning demonstrates outstanding performance even with only a small number of labeled endoscopic images.
Last Update: 2025-09-30