{"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/deeplesion-automated-deep-mining","title":"DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations","arxiv_id":"1710.01766","date":"2017-10-04","proceeding":null,"authors":["Ke Yan","Xiaosong Wang","Le Lu","Ronald M. Summers"],"abstract":"Extracting, harvesting and building large-scale annotated radiological image\ndatasets is a greatly important yet challenging problem. It is also the\nbottleneck to designing more effective data-hungry computing paradigms (e.g.,\ndeep learning) for medical image analysis. Yet, vast amounts of clinical\nannotations (usually associated with disease image findings and marked using\narrows, lines, lesion diameters, segmentation, etc.) have been collected over\nseveral decades and stored in hospitals' Picture Archiving and Communication\nSystems. In this paper, we mine and harvest one major type of clinical\nannotation data - lesion diameters annotated on bookmarked images - to learn an\neffective multi-class lesion detector via unsupervised and supervised deep\nConvolutional Neural Networks (CNN). Our dataset is composed of 33,688\nbookmarked radiology images from 10,825 studies of 4,477 unique patients. For\nevery bookmarked image, a bounding box is created to cover the target lesion\nbased on its measured diameters. We categorize the collection of lesions using\nan unsupervised deep mining scheme to generate clustered pseudo lesion labels.\nNext, we adopt a regional-CNN method to detect lesions of multiple categories,\nregardless of missing annotations (normally only one lesion is annotated,\ndespite the presence of multiple co-existing findings). Our integrated mining,\ncategorization and detection framework is validated with promising empirical\nresults, as a scalable, universal or multi-purpose CAD paradigm built upon\nabundant retrospective medical data. Furthermore, we demonstrate that detection\naccuracy can be significantly improved by incorporating pseudo lesion labels\n(e.g., Liver lesion/tumor, Lung nodule/tumor, Abdomen lesions, Chest lymph node\nand others). This dataset will be made publicly available (under the open\nscience initiative).","url_abs":"http://arxiv.org/abs/1710.01766v2","url_pdf":"http://arxiv.org/pdf/1710.01766v2.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":"deeplesion-automated-deep-mining","repo_url":"https://github.com/Masaaki-75/proct","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deeplesion-automated-deep-mining","repo_url":"https://github.com/mtcazzolato/featset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"}],"methods":[],"datasets_introduced":[{"slug":"deeplesion","name":"DeepLesion","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.01766","atlas_url":"https://app.syntology.ai/?focus=1710.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.01766"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Masaaki-75/proct","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mtcazzolato/featset","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":1,"unverified":10},"by_repo_kind":{"listed":{"samples":11,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0d209028c2dee969","entry":"gaussian","repo":"Masaaki-75/proct","repo_kind":"listed","path":"utilities/rec_loss.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/utilities/rec_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d209028c2dee969"}},{"code_sha256_prefix":"bb04d14701260c0f","entry":"build_sincos2d_pos_embed","repo":"Masaaki-75/proct","repo_kind":"listed","path":"modules/rope.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/modules/rope.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb04d14701260c0f"}},{"code_sha256_prefix":"0e211f4654d783be","entry":"forward_channel_last","repo":"Masaaki-75/proct","repo_kind":"listed","path":"modules/basic_layers.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/modules/basic_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e211f4654d783be"}},{"code_sha256_prefix":"799fe50f1f9e224c","entry":"forward_channel_second","repo":"Masaaki-75/proct","repo_kind":"listed","path":"modules/basic_layers.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/modules/basic_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"799fe50f1f9e224c"}},{"code_sha256_prefix":"968a74d4e1310a55","entry":"freq_bands","repo":"Masaaki-75/proct","repo_kind":"listed","path":"modules/rope.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/modules/rope.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"968a74d4e1310a55"}},{"code_sha256_prefix":"c6e8792591fbec4c","entry":"get_conv_block","repo":"Masaaki-75/proct","repo_kind":"listed","path":"modules/basic_layers.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/modules/basic_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6e8792591fbec4c"}},{"code_sha256_prefix":"8bf3319a7b1db318","entry":"get_metrics","repo":"Masaaki-75/proct","repo_kind":"listed","path":"utilities/rec_loss.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/utilities/rec_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bf3319a7b1db318"}},{"code_sha256_prefix":"363dfe1b7fa7f2ba","entry":"get_mse","repo":"Masaaki-75/proct","repo_kind":"listed","path":"utilities/rec_loss.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/utilities/rec_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"363dfe1b7fa7f2ba"}},{"code_sha256_prefix":"025f4d123711b4e5","entry":"pixel_freq_bands","repo":"Masaaki-75/proct","repo_kind":"listed","path":"modules/rope.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/modules/rope.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"025f4d123711b4e5"}},{"code_sha256_prefix":"6de2f712f7f3e0a1","entry":"poly_lr","repo":"Masaaki-75/proct","repo_kind":"listed","path":"trainers/basic_trainer.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/trainers/basic_trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6de2f712f7f3e0a1"}},{"code_sha256_prefix":"413b87f93f023198","entry":"vmap","repo":"Masaaki-75/proct","repo_kind":"listed","path":"sources/proct.py","file_url":"https://github.com/Masaaki-75/proct/blob/HEAD/sources/proct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"413b87f93f023198"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}