{"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/intraoperative-margin-assessment-of-human","title":"Intraoperative margin assessment of human breast tissue in optical coherence tomography images using deep neural networks","arxiv_id":"1703.10827","date":"2017-03-31","proceeding":null,"authors":["Amal Rannen Triki","Matthew B. Blaschko","Yoon Mo Jung","Seungri Song","Hyun Ju Han","Seung Il Kim","Chulmin Joo"],"abstract":"Objective: In this work, we perform margin assessment of human breast tissue\nfrom optical coherence tomography (OCT) images using deep neural networks\n(DNNs). This work simulates an intraoperative setting for breast cancer\nlumpectomy. Methods: To train the DNNs, we use both the state-of-the-art\nmethods (Weight Decay and DropOut) and a newly introduced regularization method\nbased on function norms. Commonly used methods can fail when only a small\ndatabase is available. The use of a function norm introduces a direct control\nover the complexity of the function with the aim of diminishing the risk of\noverfitting. Results: As neither the code nor the data of previous results are\npublicly available, the obtained results are compared with reported results in\nthe literature for a conservative comparison. Moreover, our method is applied\nto locally collected data on several data configurations. The reported results\nare the average over the different trials. Conclusion: The experimental results\nshow that the use of DNNs yields significantly better results than other\ntechniques when evaluated in terms of sensitivity, specificity, F1 score,\nG-mean and Matthews correlation coefficient. Function norm regularization\nyielded higher and more robust results than competing methods. Significance: We\nhave demonstrated a system that shows high promise for (partially) automated\nmargin assessment of human breast tissue, Equal error rate (EER) is reduced\nfrom approximately 12\\% (the lowest reported in the literature) to 5\\%\\,--\\,a\n58\\% reduction. The method is computationally feasible for intraoperative\napplication (less than 2 seconds per image).","url_abs":"http://arxiv.org/abs/1703.10827v1","url_pdf":"http://arxiv.org/pdf/1703.10827v1.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":"intraoperative-margin-assessment-of-human","repo_url":"https://github.com/AmalRT/DNN_Reg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}