{"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/attention-based-glaucoma-detection-a-large","title":"Attention Based Glaucoma Detection: A Large-scale Database and CNN Model","arxiv_id":"1903.10831","date":"2019-03-26","proceeding":"CVPR 2019 6","authors":["Liu Li","Mai Xu","Xiaofei Wang","Lai Jiang","Hanruo Liu"],"abstract":"Recently, the attention mechanism has been successfully applied in\nconvolutional neural networks (CNNs), significantly boosting the performance of\nmany computer vision tasks. Unfortunately, few medical image recognition\napproaches incorporate the attention mechanism in the CNNs. In particular,\nthere exists high redundancy in fundus images for glaucoma detection, such that\nthe attention mechanism has potential in improving the performance of CNN-based\nglaucoma detection. This paper proposes an attention-based CNN for glaucoma\ndetection (AG-CNN). Specifically, we first establish a large-scale attention\nbased glaucoma (LAG) database, which includes 5,824 fundus images labeled with\neither positive glaucoma (2,392) or negative glaucoma (3,432). The attention\nmaps of the ophthalmologists are also collected in LAG database through a\nsimulated eye-tracking experiment. Then, a new structure of AG-CNN is designed,\nincluding an attention prediction subnet, a pathological area localization\nsubnet and a glaucoma classification subnet. Different from other\nattention-based CNN methods, the features are also visualized as the localized\npathological area, which can advance the performance of glaucoma detection.\nFinally, the experiment results show that the proposed AG-CNN approach\nsignificantly advances state-of-the-art glaucoma detection.","url_abs":"http://arxiv.org/abs/1903.10831v3","url_pdf":"http://arxiv.org/pdf/1903.10831v3.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":"attention-based-glaucoma-detection-a-large","repo_url":"https://github.com/smilell/AG-CNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"lag","name":"LAG","full_name":"Large-scale Attention based Glaucoma"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.10831","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}