{"url":"/sota/medical-object-detection-on-deeplesion","task":{"name":"Medical Object Detection","url":"/task/medical-object-detection","note":null},"dataset":{"name":"DeepLesion","url":"/dataset/deeplesion"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Medical object detection is the task of identifying medical-based objects within an image.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector](https://github.com/L0SG/grouped-ssd-pytorch) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Sensitivity"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Sensitivity":null}},"counts":{"rows":10,"rows_with_code":6,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"P3D","metrics":{"Sensitivity":"88.55"},"uses_additional_data":false,"paper_date":"2022-01-05","paper":"/paper/advancing-3d-medical-image-analysis-with","paper_url":"https://arxiv.org/abs/2201.01426v1","paper_title":"Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training","code":"https://github.com/urmagicsmine/cspr","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DKMA-ULD","metrics":{"Sensitivity":"87.16"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/dkma-uld-domain-knowledge-augmented-multi-1","paper_url":"https://arxiv.org/abs/2203.06886v1","paper_title":"DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"AlignShift","metrics":{"Sensitivity":"86.83"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/conditional-training-with-bounding-map-for","paper_url":"https://arxiv.org/abs/2103.12277v1","paper_title":"Conditional Training with Bounding Map for Universal Lesion Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"MP3D","metrics":{"Sensitivity":"86.74"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/revisiting-3d-context-modeling-with","paper_url":"https://arxiv.org/abs/2012.08770v1","paper_title":"Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices","code":"https://github.com/urmagicsmine/MP3D","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"MELD","metrics":{"Sensitivity":"86.6"},"uses_additional_data":true,"paper_date":"2020-05-28","paper":"/paper/universal-lesion-detection-by-learning-from","paper_url":"https://arxiv.org/abs/2005.13753v1","paper_title":"Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"FCOS","metrics":{"Sensitivity":"86.05"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/an-efficient-anchor-free-universal-lesion","paper_url":"https://arxiv.org/abs/2203.16074v1","paper_title":"An Efficient Anchor-free Universal Lesion Detection in CT-scans","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"MULAN","metrics":{"Sensitivity":"85.22"},"uses_additional_data":false,"paper_date":"2019-08-12","paper":"/paper/mulan-multitask-universal-lesion-analysis","paper_url":"https://arxiv.org/abs/1908.04373v1","paper_title":"MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation","code":"https://github.com/rsummers11/CADLab","n_code_links":15,"syntology":null},{"rank_in_archive_order":8,"model":"MVP Net","metrics":{"Sensitivity":"83.64"},"uses_additional_data":false,"paper_date":"2019-09-10","paper":"/paper/mvp-net-multi-view-fpn-with-position-aware","paper_url":"https://arxiv.org/abs/1909.04247v3","paper_title":"MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection","code":"https://github.com/urmagicsmine/MVP-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Improved RetinaNet","metrics":{"Sensitivity":"82.36"},"uses_additional_data":false,"paper_date":"2019-06-05","paper":"/paper/improving-retinanet-for-ct-lesion-detection","paper_url":"https://arxiv.org/abs/1906.02283v1","paper_title":"Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels","code":"https://github.com/fizyr/keras-retinanet","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":6,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"3DCE","metrics":{"Sensitivity":"75.55"},"uses_additional_data":false,"paper_date":"2018-06-25","paper":"/paper/3d-context-enhanced-region-based","paper_url":"http://arxiv.org/abs/1806.09648v2","paper_title":"3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection","code":"https://github.com/rsummers11/CADLab","n_code_links":4,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":6,"n_samples":13,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":6,"n_samples":13,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}