{"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/knowledge-transfer-for-melanoma-screening","title":"Knowledge Transfer for Melanoma Screening with Deep Learning","arxiv_id":"1703.07479","date":"2017-03-22","proceeding":null,"authors":["Afonso Menegola","Michel Fornaciali","Ramon Pires","Flávia Vasques Bittencourt","Sandra Avila","Eduardo Valle"],"abstract":"Knowledge transfer impacts the performance of deep learning -- the state of\nthe art for image classification tasks, including automated melanoma screening.\nDeep learning's greed for large amounts of training data poses a challenge for\nmedical tasks, which we can alleviate by recycling knowledge from models\ntrained on different tasks, in a scheme called transfer learning. Although much\nof the best art on automated melanoma screening employs some form of transfer\nlearning, a systematic evaluation was missing. Here we investigate the presence\nof transfer, from which task the transfer is sourced, and the application of\nfine tuning (i.e., retraining of the deep learning model after transfer). We\nalso test the impact of picking deeper (and more expensive) models. Our results\nfavor deeper models, pre-trained over ImageNet, with fine-tuning, reaching an\nAUC of 80.7% and 84.5% for the two skin-lesion datasets evaluated.","url_abs":"http://arxiv.org/abs/1703.07479v1","url_pdf":"http://arxiv.org/pdf/1703.07479v1.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":"knowledge-transfer-for-melanoma-screening","repo_url":"https://github.com/learningtitans/data-depth-design","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"knowledge-transfer-for-melanoma-screening","repo_url":"https://github.com/learningtitans/isbi2017-part3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"skin-cancer-classification","task_name":"Skin Cancer Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.07479","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}