{"url":"/sota/medical-image-segmentation-on-etis","task":{"name":"Medical Image Segmentation","url":"/task/medical-image-segmentation","note":null},"dataset":{"name":"ETIS-LARIBPOLYPDB","url":null},"category":"Computer Vision","categories":["Computer Vision","Medical"],"category_note":null,"description":"**Medical Image Segmentation** is a computer vision task that involves dividing an medical image into multiple segments, where each segment represents a different object or structure of interest in the image. The goal of medical image segmentation is to provide a precise and accurate representation of the objects of interest within the image, typically for the purpose of diagnosis, treatment planning, and quantitative analysis.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [IVD-Net](https://github.com/josedolz/IVD-Net) )</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":["mean Dice","Average MAE","S-Measure","max E-Measure","mIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mean Dice":"higher","Average MAE":"lower","S-Measure":null,"max E-Measure":null,"mIoU":null}},"counts":{"rows":25,"rows_with_code":22,"rows_with_paper_page":25,"rows_dated":25,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RAPUNet","metrics":{"mIoU":"0.9179","mean Dice":"0.9572"},"uses_additional_data":false,"paper_date":"2024-09-16","paper":"/paper/metaformer-and-cnn-hybrid-model-for-polyp","paper_url":"https://ieeexplore.ieee.org/document/10681057","paper_title":"MetaFormer and CNN Hybrid Model for Polyp Image Segmentation","code":"https://github.com/hyunnamlee/RAPUNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SegMed","metrics":{"mIoU":"0.879","mean Dice":"0.936"},"uses_additional_data":false,"paper_date":"2025-01-31","paper":"/paper/from-semantic-segmentation-of-natural-images","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-80507-3_12","paper_title":"From Semantic Segmentation of Natural Images to Medical Image Segmentation Using ViT-Based Architectures","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"DUCK-Net","metrics":{"mIoU":"0.8788","mean Dice":"0.9354"},"uses_additional_data":false,"paper_date":"2023-11-03","paper":"/paper/using-duck-net-for-polyp-image-segmentation-1","paper_url":"https://arxiv.org/abs/2311.02239v1","paper_title":"Using DUCK-Net for Polyp Image Segmentation","code":"https://github.com/RazvanDu/DUCK-Net","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"EMCAD","metrics":{"mean Dice":"0.9229"},"uses_additional_data":false,"paper_date":"2024-05-11","paper":"/paper/emcad-efficient-multi-scale-convolutional","paper_url":"https://arxiv.org/abs/2405.06880v1","paper_title":"EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation","code":"https://github.com/sldgroup/emcad","n_code_links":1,"syntology":{"n_ran":20,"n_unverified":3,"n_samples":23,"n_pointer_only_licence":23}},{"rank_in_archive_order":5,"model":"ProMISe","metrics":{"mIoU":"0.750","mean Dice":"0.840"},"uses_additional_data":false,"paper_date":"2024-03-07","paper":"/paper/promise-promptable-medical-image-segmentation","paper_url":"https://arxiv.org/abs/2403.04164v3","paper_title":"ProMISe: Promptable Medical Image Segmentation using SAM","code":"https://github.com/xinkunwang111/promise","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"RSAFormer","metrics":{"mean Dice":"0.835"},"uses_additional_data":false,"paper_date":"2024-04-01","paper":"/paper/rsaformer-a-method-of-polyp-segmentation-with","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0010482524003524#preview-section-abstract","paper_title":"RSAFormer: A method of polyp segmentation with region self-attention transformer","code":"https://github.com/JunZengz/RSAFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"ESFPNet-L","metrics":{"mIoU":"0.748","mean Dice":"0.823"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/esfpnet-efficient-deep-learning-architecture","paper_url":"https://arxiv.org/abs/2207.07759v3","paper_title":"ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic video","code":"https://github.com/dumyCq/CFPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"DuAT","metrics":{"Average MAE":"0.013","mIoU":"0.746","mean Dice":"0.822"},"uses_additional_data":false,"paper_date":"2022-12-21","paper":"/paper/duat-dual-aggregation-transformer-network-for","paper_url":"https://arxiv.org/abs/2212.11677v1","paper_title":"DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation","code":"https://github.com/Barrett-python/DuAT","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"PVT-CASCADE","metrics":{"mIoU":"0.7258","mean Dice":"0.8007"},"uses_additional_data":false,"paper_date":"2023-01-03","paper":"/paper/medical-image-segmentation-via-cascaded","paper_url":"https://openaccess.thecvf.com/content/WACV2023/html/Rahman_Medical_Image_Segmentation_via_Cascaded_Attention_Decoding_WACV_2023_paper.html","paper_title":"Medical Image Segmentation via Cascaded Attention Decoding","code":"https://github.com/SLDGroup/CASCADE","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SSFormer-L","metrics":{"mIoU":"0.720","mean Dice":"0.796"},"uses_additional_data":false,"paper_date":"2022-03-07","paper":"/paper/stepwise-feature-fusion-local-guides-global","paper_url":"https://arxiv.org/abs/2203.03635v3","paper_title":"Stepwise Feature Fusion: Local Guides Global","code":"https://github.com/Qiming-Huang/ssformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"MEGANet(ResNet-34)","metrics":{"mIoU":"0.709","mean Dice":"0.789"},"uses_additional_data":false,"paper_date":"2023-09-06","paper":"/paper/meganet-multi-scale-edge-guided-attention","paper_url":"https://arxiv.org/abs/2309.03329v3","paper_title":"MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation","code":"https://github.com/uark-aicv/meganet","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"Meta-Polyp","metrics":{"mIoU":"0.704","mean Dice":"0.78"},"uses_additional_data":false,"paper_date":"2023-05-13","paper":"/paper/meta-polyp-a-baseline-for-efficient-polyp","paper_url":"https://arxiv.org/abs/2305.07848v3","paper_title":"Meta-Polyp: a baseline for efficient Polyp segmentation","code":"https://github.com/huyquoctrinh/metapolyp-cbms2023","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"UACANet-L","metrics":{"Average MAE":"0.012","S-Measure":"0.859","mIoU":"0.689","max E-Measure":"0.905","mean Dice":"0.766"},"uses_additional_data":false,"paper_date":"2021-07-06","paper":"/paper/uacanet-uncertainty-augmented-context","paper_url":"https://arxiv.org/abs/2107.02368v3","paper_title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","code":"https://github.com/plemeri/UACANet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"SAM-EG","metrics":{"mIoU":"0.681","mean Dice":"0.757"},"uses_additional_data":false,"paper_date":"2024-06-21","paper":"/paper/sam-eg-segment-anything-model-with-egde","paper_url":"https://arxiv.org/abs/2406.14819v1","paper_title":"SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"CaraNet","metrics":{"Average MAE":"0.017","S-Measure":"0.868","mIoU":"0.672","max E-Measure":"0.894","mean Dice":"0.747"},"uses_additional_data":false,"paper_date":"2021-08-16","paper":"/paper/caranet-context-axial-reverse-attention","paper_url":"https://arxiv.org/abs/2108.07368v3","paper_title":"CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects","code":"https://github.com/AngeLouCN/CaraNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"MEGANet(Res2Net-50)","metrics":{"mIoU":"0.665","mean Dice":"0.739"},"uses_additional_data":false,"paper_date":"2023-09-06","paper":"/paper/meganet-multi-scale-edge-guided-attention","paper_url":"https://arxiv.org/abs/2309.03329v3","paper_title":"MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation","code":"https://github.com/uark-aicv/meganet","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"TransFuse-L","metrics":{"mIoU":"0.661","mean Dice":"0.737"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/transfuse-fusing-transformers-and-cnns-for","paper_url":"https://arxiv.org/abs/2102.08005v2","paper_title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","code":"https://github.com/Rayicer/TransFuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"TransFuse-S","metrics":{"mIoU":"0.659","mean Dice":"0.733"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/transfuse-fusing-transformers-and-cnns-for","paper_url":"https://arxiv.org/abs/2102.08005v2","paper_title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","code":"https://github.com/Rayicer/TransFuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"HarDNet-DFUS","metrics":{"mean Dice":"0.730"},"uses_additional_data":false,"paper_date":"2022-09-15","paper":"/paper/hardnet-dfus-an-enhanced-harmonically","paper_url":"https://arxiv.org/abs/2209.07313v1","paper_title":"HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image Segmentation and Colonoscopy Polyp Segmentation","code":"https://github.com/yuwenlo/hardnet-dfus","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"COMMA (Res2Net-50)","metrics":{"Average MAE":"0.015","S-Measure":"0.844","mIoU":"0.648","max E-Measure":"0.887","mean Dice":"0.711"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/comma-propagating-complementary-multi-level","paper_url":"https://www.mdpi.com/2076-3417/12/4/2114","paper_title":"COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"UACANet-S","metrics":{"Average MAE":"0.023","S-Measure":"0.815","mIoU":"0.615","max E-Measure":"0.851","mean Dice":"0.694"},"uses_additional_data":false,"paper_date":"2021-07-06","paper":"/paper/uacanet-uncertainty-augmented-context","paper_url":"https://arxiv.org/abs/2107.02368v3","paper_title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","code":"https://github.com/plemeri/UACANet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"HarDNet-MSEG","metrics":{"mIoU":"0.613","mean Dice":"0.677"},"uses_additional_data":false,"paper_date":"2021-01-18","paper":"/paper/hardnet-mseg-a-simple-encoder-decoder-polyp","paper_url":"https://arxiv.org/abs/2101.07172v2","paper_title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","code":"https://github.com/james128333/HarDNet-MSEG","n_code_links":4,"syntology":null},{"rank_in_archive_order":23,"model":"ResUNet++","metrics":{"mIoU":"0.7534","mean Dice":"0.6364"},"uses_additional_data":false,"paper_date":"2019-11-16","paper":"/paper/resunet-an-advanced-architecture-for-medical","paper_url":"https://arxiv.org/abs/1911.07067v1","paper_title":"ResUNet++: An Advanced Architecture for Medical Image Segmentation","code":"https://github.com/rishikksh20/ResUnet","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":24,"model":"PraNet","metrics":{"Average MAE":"0.031","S-Measure":"0.794","mIoU":"0.5670","max E-Measure":"0.841","mean Dice":"0.6280"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/pranet-parallel-reverse-attention-network-for","paper_url":"https://arxiv.org/abs/2006.11392v4","paper_title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation","code":"https://github.com/DengPingFan/PraNet","n_code_links":4,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"ResUNet++ + TTA","metrics":{"mIoU":"0.7458","mean Dice":"0.6136"},"uses_additional_data":false,"paper_date":"2021-07-26","paper":"/paper/a-comprehensive-study-on-colorectal-polyp","paper_url":"https://arxiv.org/abs/2107.12435v1","paper_title":"A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation","code":"https://github.com/DebeshJha/ResUNet-with-CRF-and-TTA","n_code_links":1,"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":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":31,"n_unverified":9,"n_samples":40,"n_pointer_only_licence":27,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":32,"n_unverified":12,"n_samples":44,"n_pointer_only_licence":27,"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"}}}