{"url":"/dataset/deeplesion","name":"DeepLesion","full_name":null,"description_markdown":"The National Institutes of Health’s Clinical Center has made a large-scale dataset of CT images publicly available to help the scientific community improve detection accuracy of lesions. While most publicly available medical image datasets have less than a thousand lesions, this dataset, named DeepLesion, has over 32,000 annotated lesions (220GB) identified on CT images.\r\nDeepLesion, a dataset with 32,735 lesions in 32,120 CT slices from 10,594 studies of 4,427 unique patients. There are a variety of lesion types in this dataset, such as lung nodules, liver tumors, enlarged lymph nodes, and so on. It has the potential to be used in various medical image applications","description_withheld":null,"homepage":"https://nihcc.app.box.com/v/DeepLesion","introduced_date":"2017-10-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/deeplesion-automated-deep-mining","title":"DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations","first_author":"Ke Yan","url":null},"license":null,"modalities":[{"name":"Biomedical","url":"/datasets/modality/biomedical"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Medical Object Detection","url":"/task/medical-object-detection","datasets_with_task":"/datasets/task/medical-object-detection"}],"languages":[],"variants":["DeepLesion"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/medical-object-detection-on-deeplesion","task":"Medical Object Detection","dataset_variant":"DeepLesion","rows":10,"metrics":["Sensitivity"],"first_row_in_archive_order":{"model":"P3D","paper":"/paper/advancing-3d-medical-image-analysis-with","metrics":{"Sensitivity":"88.55"},"code_links":[{"title":"urmagicsmine/cspr","url":"https://github.com/urmagicsmine/cspr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/an-efficient-anchor-free-universal-lesion","title":"An Efficient Anchor-free Universal Lesion Detection in CT-scans","date":"2022-03-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dkma-uld-domain-knowledge-augmented-multi-1","title":"DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection","date":"2022-03-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/advancing-3d-medical-image-analysis-with","title":"Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training","date":"2022-01-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/conditional-training-with-bounding-map-for","title":"Conditional Training with Bounding Map for Universal Lesion Detection","date":"2021-03-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/revisiting-3d-context-modeling-with","title":"Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices","date":"2020-12-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/universal-lesion-detection-by-learning-from","title":"Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets","date":"2020-05-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mvp-net-multi-view-fpn-with-position-aware","title":"MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection","date":"2019-09-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mulan-multitask-universal-lesion-analysis","title":"MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation","date":"2019-08-12","rows_on_this_dataset":1,"code_links":15,"syntology":null},{"paper":"/paper/improving-retinanet-for-ct-lesion-detection","title":"Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels","date":"2019-06-05","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":0,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/3d-context-enhanced-region-based","title":"3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection","date":"2018-06-25","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":13,"samples_ran":0,"samples_unverified":13,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}