{"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/deep-multi-instance-networks-with-sparse-1","title":"Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification","arxiv_id":"1705.08550","date":"2017-05-23","proceeding":null,"authors":["Wentao Zhu","Qi Lou","Yeeleng Scott Vang","Xiaohui Xie"],"abstract":"Mammogram classification is directly related to computer-aided diagnosis of\nbreast cancer. Traditional methods rely on regions of interest (ROIs) which\nrequire great efforts to annotate. Inspired by the success of using deep\nconvolutional features for natural image analysis and multi-instance learning\n(MIL) for labeling a set of instances/patches, we propose end-to-end trained\ndeep multi-instance networks for mass classification based on whole mammogram\nwithout the aforementioned ROIs. We explore three different schemes to\nconstruct deep multi-instance networks for whole mammogram classification.\nExperimental results on the INbreast dataset demonstrate the robustness of\nproposed networks compared to previous work using segmentation and detection\nannotations.","url_abs":"http://arxiv.org/abs/1705.08550v1","url_pdf":"http://arxiv.org/pdf/1705.08550v1.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":"deep-multi-instance-networks-with-sparse-1","repo_url":"https://github.com/wentaozhu/deep-mil-for-whole-mammogram-classification","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"suspicous-birads-45-no-suspicous-birads-123","task_name":"Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification"},{"task_slug":"whole-mammogram-classification","task_name":"Whole Mammogram Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/suspicous-birads-45-no-suspicous-birads-123","task":"Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification","dataset":"InBreast","model":"AlexNet+Sparse MIL INbr. Auto.","rank_in_archive_order":9,"of":16,"metrics":{"AUC":"0.89"},"uses_additional_data":false},{"leaderboard":"/sota/suspicous-birads-45-no-suspicous-birads-123","task":"Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification","dataset":"InBreast","model":"AlexNet+Label Assign. MIL INbr. Auto.","rank_in_archive_order":12,"of":16,"metrics":{"AUC":"0.84"},"uses_additional_data":false},{"leaderboard":"/sota/suspicous-birads-45-no-suspicous-birads-123","task":"Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification","dataset":"InBreast","model":"AlexNet+Max Pooling MIL","rank_in_archive_order":14,"of":16,"metrics":{"AUC":"0.83"},"uses_additional_data":false},{"leaderboard":"/sota/suspicous-birads-45-no-suspicous-birads-123","task":"Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification","dataset":"InBreast","model":"AlexNet","rank_in_archive_order":15,"of":16,"metrics":{"AUC":"0.79"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}