{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/semi-supervised-deep-learning-for-abnormality","title":"Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images","arxiv_id":"1812.07832","date":"2018-12-19","proceeding":null,"authors":["Bruno Lecouat","Ken Chang","Chuan-Sheng Foo","Balagopal Unnikrishnan","James M. Brown","Houssam Zenati","Andrew Beers","Vijay Chandrasekhar","Jayashree Kalpathy-Cramer","Pavitra Krishnaswamy"],"abstract":"Supervised deep learning algorithms have enabled significant performance\ngains in medical image classification tasks. But these methods rely on large\nlabeled datasets that require resource-intensive expert annotation.\nSemi-supervised generative adversarial network (GAN) approaches offer a means\nto learn from limited labeled data alongside larger unlabeled datasets, but\nhave not been applied to discern fine-scale, sparse or localized features that\ndefine medical abnormalities. To overcome these limitations, we propose a\npatch-based semi-supervised learning approach and evaluate performance on\nclassification of diabetic retinopathy from funduscopic images. Our\nsemi-supervised approach achieves high AUC with just 10-20 labeled training\nimages, and outperforms the supervised baselines by upto 15% when less than 30%\nof the training dataset is labeled. Further, our method implicitly enables\ninterpretation of the SSL predictions. As this approach enables good accuracy,\nresolution and interpretability with lower annotation burden, it sets the\npathway for scalable applications of deep learning in clinical imaging.","url_abs":"http://arxiv.org/abs/1812.07832v1","url_pdf":"http://arxiv.org/pdf/1812.07832v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"semi-supervised-deep-learning-for-abnormality","repo_url":"https://github.com/theidentity/Improved-GAN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"medical-image-classification","task_name":"Medical Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.07832","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}