{"url":"/task/lesion-segmentation","name":"Lesion Segmentation","slug":"lesion-segmentation","description_markdown":"Lesion segmentation is the task of segmenting out lesions from other objects in medical based images.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [D-UNet](https://arxiv.org/pdf/1908.05104v1.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":640,"papers_with_code":269,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/lesion-segmentation-on","slug":"lesion-segmentation-on","dataset":null,"dataset_url":null,"rows_in_archive":17,"metrics":["Dice"],"first_row_in_archive_order":{"model":"STPNet","paper_title":"STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation","paper_url":"/paper/stpnet-scale-aware-text-prompt-network-for","paper_date":"2025-04-02","arxiv_id":"2504.01561","code_links":[{"title":"huanglizi/stpnet","url":"https://github.com/huanglizi/stpnet"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-isic-2018","slug":"lesion-segmentation-on-isic-2018","dataset":"ISIC 2018","dataset_url":null,"rows_in_archive":17,"metrics":["mean Dice","F1-Score","Mean IoU"],"first_row_in_archive_order":{"model":"Polar Res-U-Net++","paper_title":"Training on Polar Image Transformations Improves Biomedical Image Segmentation","paper_url":"/paper/training-on-polar-image-transformations","paper_date":"2021-09-29","arxiv_id":null,"code_links":[{"title":"marinbenc/medical-polar-training","url":"https://github.com/marinbenc/medical-polar-training"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-anatomical-tracings-of-1","slug":"lesion-segmentation-on-anatomical-tracings-of-1","dataset":"Anatomical Tracings of Lesions After Stroke (ATLAS)","dataset_url":null,"rows_in_archive":5,"metrics":["Dice","Precision","IoU","Recall"],"first_row_in_archive_order":{"model":"D-UNet","paper_title":"D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation","paper_url":"/paper/d-unet-a-dimension-fusion-u-shape-network-for","paper_date":"2019-08-14","arxiv_id":"1908.05104","code_links":[{"title":"SZUHvern/D-UNet","url":"https://github.com/SZUHvern/D-UNet"},{"title":"SWKoreaBME/D-Unet_PyTorch","url":"https://github.com/SWKoreaBME/D-Unet_PyTorch"},{"title":"nellish123/contrib","url":"https://github.com/nellish123/contrib"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-university-of-waterloo","slug":"lesion-segmentation-on-university-of-waterloo","dataset":"University of Waterloo skin cancer database","dataset_url":"/dataset/university-of-waterloo-skin-cancer-database","rows_in_archive":5,"metrics":["Dice score"],"first_row_in_archive_order":{"model":"DTP-Net","paper_title":"DTP-Net: A convolutional neural network model to predict threshold for localizing the lesions on dermatological macro-images","paper_url":"/paper/dtp-net-a-convolutional-neural-network-model","paper_date":"2022-07-12","arxiv_id":null,"code_links":[{"title":"VipinBioLab/DTP-Net","url":"https://github.com/VipinBioLab/DTP-Net"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-anatomical-tracings-of","slug":"lesion-segmentation-on-anatomical-tracings-of","dataset":"Anatomical Tracings of Lesions After Stroke (ATLAS)","dataset_url":null,"rows_in_archive":4,"metrics":["IoU","Precision","Recall","Dice"],"first_row_in_archive_order":{"model":"MGA-Net","paper_title":"Mutual gain adaptive network for segmenting brain stroke lesions","paper_url":"/paper/mutual-gain-adaptive-network-for-segmenting","paper_date":"2022-08-27","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-bus-2017-dataset-b","slug":"lesion-segmentation-on-bus-2017-dataset-b","dataset":"BUS 2017 Dataset B","dataset_url":null,"rows_in_archive":4,"metrics":["Dice Score"],"first_row_in_archive_order":{"model":"Attn U-Net + Multi-Input + FTL","paper_title":"A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation","paper_url":"/paper/a-novel-focal-tversky-loss-function-with","paper_date":"2018-10-18","arxiv_id":"1810.07842","code_links":[{"title":"nabsabraham/focal-tversky-unet","url":"https://github.com/nabsabraham/focal-tversky-unet"},{"title":"Jo-dsa/SemanticSeg","url":"https://github.com/Jo-dsa/SemanticSeg"},{"title":"SahinTiryaki/Brain-tumor-segmentation-Vgg19UNet","url":"https://github.com/SahinTiryaki/Brain-tumor-segmentation-Vgg19UNet"},{"title":"EvgenyDyshlyuk/Oil_Seep_Detection","url":"https://github.com/EvgenyDyshlyuk/Oil_Seep_Detection"},{"title":"woans0104/sk_project","url":"https://github.com/woans0104/sk_project"},{"title":"woans0104/project_review","url":"https://github.com/woans0104/project_review"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-ph2","slug":"lesion-segmentation-on-ph2","dataset":"PH2","dataset_url":"/dataset/ph2","rows_in_archive":3,"metrics":["Dice Score"],"first_row_in_archive_order":{"model":"IARS SegNet","paper_title":"IARS SegNet: Interpretable Attention Residual Skip connection SegNet for melanoma segmentation","paper_url":"/paper/iars-segnet-interpretable-attention-residual","paper_date":"2023-10-31","arxiv_id":"2310.20292","code_links":[],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-ham10000","slug":"lesion-segmentation-on-ham10000","dataset":"HAM10000","dataset_url":"/dataset/ham10000-1","rows_in_archive":1,"metrics":["Dice Score"],"first_row_in_archive_order":{"model":"DermoSegDiff-B","paper_title":"DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation","paper_url":"/paper/dermosegdiff-a-boundary-aware-segmentation","paper_date":"2023-08-05","arxiv_id":"2308.02959","code_links":[{"title":"mindflow-institue/dermosegdiff","url":"https://github.com/mindflow-institue/dermosegdiff"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-isic-2017","slug":"lesion-segmentation-on-isic-2017","dataset":"ISIC 2017","dataset_url":null,"rows_in_archive":1,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"Automatic skin lesion segmentation with fully convolutional-deconvolutional networks","paper_title":"Automatic skin lesion segmentation with fully convolutional-deconvolutional networks","paper_url":"/paper/automatic-skin-lesion-segmentation-with-fully","paper_date":"2017-03-15","arxiv_id":"1703.05165","code_links":[{"title":"manideep2510/melanoma_segmentation","url":"https://github.com/manideep2510/melanoma_segmentation"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-isic-2018-task-1","slug":"lesion-segmentation-on-isic-2018-task-1","dataset":"ISIC 2018 Task 1","dataset_url":"/dataset/isic-2018-task-1","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DCSAU-Net","paper_title":"DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation","paper_url":"/paper/dcsau-net-a-deeper-and-more-compact-split","paper_date":"2022-02-02","arxiv_id":"2202.00972","code_links":[{"title":"xq141839/DCSAU-Net","url":"https://github.com/xq141839/DCSAU-Net"}],"syntology":null}},{"leaderboard":"/sota/lesion-segmentation-on-isles-2015","slug":"lesion-segmentation-on-isles-2015","dataset":"ISLES-2015","dataset_url":null,"rows_in_archive":1,"metrics":["Dice Score"],"first_row_in_archive_order":{"model":"3D CNN + CRF","paper_title":"Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation","paper_url":"/paper/efficient-multi-scale-3d-cnn-with-fully","paper_date":"2016-03-18","arxiv_id":"1603.05959","code_links":[{"title":"Kamnitsask/deepmedic","url":"https://github.com/Kamnitsask/deepmedic"},{"title":"etjoa003/medical_imaging","url":"https://github.com/etjoa003/medical_imaging"}],"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/ham10000-1","name":"HAM10000","full_name":"HAM10000","num_papers_in_archive":209},{"url":"/dataset/isic2016-task-1","name":"ISIC2016","full_name":"Lesion Segmentation","num_papers_in_archive":50},{"url":"/dataset/isic-2018-task-1","name":"ISIC 2018 Task 1","full_name":"ISIC 2018 Task 1","num_papers_in_archive":27},{"url":"/dataset/hecktor","name":"HECKTOR","full_name":"","num_papers_in_archive":26},{"url":"/dataset/digestpath","name":"DigestPath","full_name":"","num_papers_in_archive":23},{"url":"/dataset/fgadr","name":"FGADR","full_name":"","num_papers_in_archive":20},{"url":"/dataset/coir","name":"CoIR","full_name":"Code Information Retrieval Benchmark","num_papers_in_archive":18},{"url":"/dataset/isic-2017-task-1","name":"ISIC 2017 Task 1","full_name":"ISIC 2017 Task 1","num_papers_in_archive":15},{"url":"/dataset/isic-2018-task-3","name":"ISIC 2018 Task 3","full_name":"ISIC 2018 Task 3","num_papers_in_archive":11},{"url":"/dataset/sd-198","name":"SD-198","full_name":"","num_papers_in_archive":11},{"url":"/dataset/ph2","name":"PH2","full_name":"","num_papers_in_archive":10},{"url":"/dataset/retinal-lesions","name":"Retinal-Lesions","full_name":"","num_papers_in_archive":8},{"url":"/dataset/university-of-waterloo-skin-cancer-database","name":"University of Waterloo skin cancer database","full_name":"","num_papers_in_archive":8},{"url":"/dataset/isic-2018-task-2","name":"ISIC 2018 Task 2","full_name":"ISIC 2018 Task 2","num_papers_in_archive":6},{"url":"/dataset/isic-2017-task-3","name":"ISIC 2017 Task 3","full_name":"ISIC 2017 Task 3","num_papers_in_archive":5},{"url":"/dataset/autopet","name":"AutoPET","full_name":"","num_papers_in_archive":4},{"url":"/dataset/isic-2017-task-2","name":"ISIC 2017 Task 2","full_name":"ISIC 2017 Task 2","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/medical-image-segmentation","name":"Medical Image Segmentation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":269,"tagged_in_all":640,"items":[{"url":"/paper/u-net-convolutional-networks-for-biomedical","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","date":"2015-05-18","arxiv_id":"1505.04597","repositories_listed":487,"syntology":{"n":757,"n_ran":510,"n_unverified":247,"n_pointer_only":426}},{"url":"/paper/encoder-decoder-with-atrous-separable","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","date":"2018-02-07","arxiv_id":"1802.02611","repositories_listed":78,"syntology":{"n":72,"n_ran":43,"n_unverified":29,"n_pointer_only":40}},{"url":"/paper/segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","arxiv_id":"1511.00561","repositories_listed":74,"syntology":{"n":44,"n_ran":9,"n_unverified":35,"n_pointer_only":10}},{"url":"/paper/pyramid-scene-parsing-network","title":"Pyramid Scene Parsing Network","date":"2016-12-04","arxiv_id":"1612.01105","repositories_listed":67,"syntology":{"n":29,"n_ran":7,"n_unverified":22,"n_pointer_only":5}},{"url":"/paper/skin-lesion-analysis-toward-melanoma-1","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","date":"2019-02-09","arxiv_id":"1902.03368","repositories_listed":18,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/road-extraction-by-deep-residual-u-net","title":"Road Extraction by Deep Residual U-Net","date":"2017-11-29","arxiv_id":"1711.10684","repositories_listed":13,"syntology":null},{"url":"/paper/recurrent-residual-convolutional-neural","title":"Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation","date":"2018-02-20","arxiv_id":"1802.06955","repositories_listed":12,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/skin-lesion-analysis-toward-melanoma","title":"Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)","date":"2017-10-13","arxiv_id":"1710.05006","repositories_listed":12,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/a-novel-focal-tversky-loss-function-with","title":"A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation","date":"2018-10-18","arxiv_id":"1810.07842","repositories_listed":6,"syntology":null},{"url":"/paper/boundary-loss-for-highly-unbalanced","title":"Boundary loss for highly unbalanced segmentation","date":"2018-12-17","arxiv_id":"1812.07032","repositories_listed":5,"syntology":{"n":26,"n_ran":2,"n_unverified":24,"n_pointer_only":0}},{"url":"/paper/u-net-v2-rethinking-the-skip-connections-of-u","title":"U-Net v2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation","date":"2023-11-29","arxiv_id":"2311.17791","repositories_listed":4,"syntology":null},{"url":"/paper/matthews-correlation-coefficient-loss-for","title":"Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation","date":"2020-10-26","arxiv_id":"2010.13454","repositories_listed":4,"syntology":null},{"url":"/paper/doubleu-net-a-deep-convolutional-neural","title":"DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation","date":"2020-06-08","arxiv_id":"2006.04868","repositories_listed":4,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/bi-directional-convlstm-u-net-with-densley","title":"Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions","date":"2019-08-31","arxiv_id":"1909.00166","repositories_listed":4,"syntology":null},{"url":"/paper/recod-titans-at-isic-challenge-2017","title":"RECOD Titans at ISIC Challenge 2017","date":"2017-03-14","arxiv_id":"1703.04819","repositories_listed":4,"syntology":null},{"url":"/paper/automatic-liver-and-tumor-segmentation-of-ct","title":"Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks","date":"2017-02-20","arxiv_id":"1702.05970","repositories_listed":4,"syntology":null},{"url":"/paper/otre-where-optimal-transport-guided-unpaired","title":"OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing","date":"2023-02-06","arxiv_id":"2302.03003","repositories_listed":3,"syntology":null},{"url":"/paper/diffusion-models-for-implicit-image","title":"Diffusion Models for Implicit Image Segmentation Ensembles","date":"2021-12-06","arxiv_id":"2112.03145","repositories_listed":3,"syntology":{"n":19,"n_ran":13,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/ca-net-comprehensive-attention-convolutional","title":"CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation","date":"2020-09-22","arxiv_id":"2009.10549","repositories_listed":3,"syntology":null},{"url":"/paper/comparative-study-of-deep-learning-methods","title":"Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients","date":"2020-07-29","arxiv_id":"2007.15546","repositories_listed":3,"syntology":null},{"url":"/paper/d-unet-a-dimension-fusion-u-shape-network-for","title":"D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation","date":"2019-08-14","arxiv_id":"1908.05104","repositories_listed":3,"syntology":null},{"url":"/paper/one-shot-domain-adaptation-in-multiple","title":"One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks","date":"2018-05-31","arxiv_id":"1805.12415","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-liver-and-lesion-segmentation-in-ct","title":"Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields","date":"2016-10-07","arxiv_id":"1610.02177","repositories_listed":3,"syntology":null},{"url":"/paper/longitudinal-segmentation-of-ms-lesions-via","title":"Longitudinal Segmentation of MS Lesions via Temporal Difference Weighting","date":"2024-09-20","arxiv_id":"2409.13416","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/autopet-challenge-iii-testing-the-robustness","title":"AutoPET Challenge III: Testing the Robustness of Generalized Dice Focal Loss trained 3D Residual UNet for FDG and PSMA Lesion Segmentation from Whole-Body PET/CT Images","date":"2024-09-16","arxiv_id":"2409.10151","repositories_listed":2,"syntology":null},{"url":"/paper/synthetic-data-for-robust-stroke-segmentation","title":"Synthetic Data for Robust Stroke Segmentation","date":"2024-04-02","arxiv_id":"2404.01946","repositories_listed":2,"syntology":null},{"url":"/paper/a-robust-ensemble-algorithm-for-ischemic","title":"A Robust Ensemble Algorithm for Ischemic Stroke Lesion Segmentation: Generalizability and Clinical Utility Beyond the ISLES Challenge","date":"2024-03-28","arxiv_id":"2403.19425","repositories_listed":2,"syntology":null},{"url":"/paper/structural-based-uncertainty-in-deep-learning","title":"Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation","date":"2023-11-15","arxiv_id":"2311.08931","repositories_listed":2,"syntology":null},{"url":"/paper/unlocking-fine-grained-details-with-wavelet","title":"Unlocking Fine-Grained Details with Wavelet-based High-Frequency Enhancement in Transformers","date":"2023-08-25","arxiv_id":"2308.13442","repositories_listed":2,"syntology":null},{"url":"/paper/mdvit-multi-domain-vision-transformer-for","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","date":"2023-07-05","arxiv_id":"2307.02100","repositories_listed":2,"syntology":null}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}