{"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/3d-context-enhanced-region-based","title":"3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection","arxiv_id":"1806.09648","date":"2018-06-25","proceeding":null,"authors":["Ke Yan","Mohammadhadi Bagheri","Ronald M. Summers"],"abstract":"Detecting lesions from computed tomography (CT) scans is an important but\ndifficult problem because non-lesions and true lesions can appear similar. 3D\ncontext is known to be helpful in this differentiation task. However, existing\nend-to-end detection frameworks of convolutional neural networks (CNNs) are\nmostly designed for 2D images. In this paper, we propose 3D context enhanced\nregion-based CNN (3DCE) to incorporate 3D context information efficiently by\naggregating feature maps of 2D images. 3DCE is easy to train and end-to-end in\ntraining and inference. A universal lesion detector is developed to detect all\nkinds of lesions in one algorithm using the DeepLesion dataset. Experimental\nresults on this challenging task prove the effectiveness of 3DCE. We have\nreleased the code of 3DCE in\nhttps://github.com/rsummers11/CADLab/tree/master/lesion_detector_3DCE.","url_abs":"http://arxiv.org/abs/1806.09648v2","url_pdf":"http://arxiv.org/pdf/1806.09648v2.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":"3d-context-enhanced-region-based","repo_url":"https://github.com/rsummers11/CADLab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"3d-context-enhanced-region-based","repo_url":"https://github.com/fsafe/Capstone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"3d-context-enhanced-region-based","repo_url":"https://github.com/truetqy/lesion_det_dual_att","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":null},{"paper_slug":"3d-context-enhanced-region-based","repo_url":"https://github.com/urmagicsmine/MVP-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"lesion-detection","task_name":"Lesion Detection"},{"task_slug":"medical-object-detection","task_name":"Medical Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-object-detection-on-deeplesion","task":"Medical Object Detection","dataset":"DeepLesion","model":"3DCE","rank_in_archive_order":10,"of":10,"metrics":{"Sensitivity":"75.55"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.09648","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}