{"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/end-to-end-training-for-whole-image-breast","title":"End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design","arxiv_id":"1711.05775","date":"2017-11-15","proceeding":null,"authors":["Li Shen"],"abstract":"We develop an end-to-end training algorithm for whole-image breast cancer\ndiagnosis based on mammograms. It requires lesion annotations only at the first\nstage of training. After that, a whole image classifier can be trained using\nonly image level labels. This greatly reduced the reliance on lesion\nannotations. Our approach is implemented using an all convolutional design that\nis simple yet provides superior performance in comparison with the previous\nmethods. On DDSM, our best single-model achieves a per-image AUC score of 0.88\nand three-model averaging increases the score to 0.91. On INbreast, our best\nsingle-model achieves a per-image AUC score of 0.96. Using DDSM as benchmark,\nour models compare favorably with the current state-of-the-art. We also\ndemonstrate that a whole image model trained on DDSM can be easily transferred\nto INbreast without using its lesion annotations and using only a small amount\nof training data. Code availability: https://github.com/lishen/end2end-all-conv","url_abs":"http://arxiv.org/abs/1711.05775v1","url_pdf":"http://arxiv.org/pdf/1711.05775v1.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":"end-to-end-training-for-whole-image-breast","repo_url":"https://github.com/lishen/end2end-all-conv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"end-to-end-training-for-whole-image-breast","repo_url":"https://github.com/aralab-unr/ga-mammograms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"end-to-end-training-for-whole-image-breast","repo_url":"https://github.com/gkaposto/end2end_lishen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"end-to-end-training-for-whole-image-breast","repo_url":"https://github.com/yuyuyu123456/CBIS-DDSM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.05775","atlas_url":"https://app.syntology.ai/?focus=1711.05775","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}