Browse State-of-the-Art › Medical Image Segmentation

Medical Image Segmentation

1,080 papers with code · 50 benchmarks · 52 datasets archive 2025-07-28

Computer VisionMedical

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.

( Image credit: IVD-Net )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

50 leaderboard tables shown for this task, 50 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 50 until expanded.

Syntology 14 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Kvasir-SEG (5 judged, 0 placed), CVC-ClinicDB (3 judged, 0 placed), CVC-ColonDB (4 judged, 0 placed), ETIS-LARIBPOLYPDB (2 judged, 0 placed), GlaS (2 judged, 0 placed), DRIVE (3 judged, 0 placed), ISIC 2018 (1 judged, 0 placed), ISIC2018 (2 judged, 0 placed), Kvasir-Instrument (1 judged, 0 placed), MosMedData (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Kvasir-SEG (58 rows) DUCK-Net Using DUCK-Net for Polyp Image Segmentation code — Compare
CVC-ClinicDB (48 rows) DUCK-Net Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation code — Compare
CVC-ColonDB (25 rows) RAPUNet MetaFormer and CNN Hybrid Model for Polyp Image Segmentation code — Compare
ETIS-LARIBPOLYPDB (25 rows) RAPUNet MetaFormer and CNN Hybrid Model for Polyp Image Segmentation code — Compare
Synapse multi-organ CT (23 rows) Interactive AI-SAM gt box AI-SAM: Automatic and Interactive Segment Anything Model code — Compare
Automatic Cardiac Diagnosis Challenge (ACDC) (20 rows) FCT Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation code — Compare
MoNuSeg (15 rows) Stardist Cell Detection with Star-convex Polygons code Syntology official (archive's flag): 1 ran · 17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 16 unverified Compare
2018 Data Science Bowl (10 rows) ReN-UNet Rethinking the Nested U-Net Approach: Enhancing Biomarker... code — Compare
GlaS (10 rows) Hi-gMISnet Hi-gMISnet: generalized medical image segmentation using DWT based... code — Compare
BKAI-IGH NeoPolyp-Small (9 rows) RaBiT RaBiT: An Efficient Transformer using Bidirectional Feature... code — Compare
MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge (8 rows) MERIT Multi-scale Hierarchical Vision Transformer with Cascaded... code — Compare
ACDC (6 rows) FCT The Fully Convolutional Transformer for Medical Image Segmentation code — Compare
CVC-VideoClinicDB (5 rows) ResUNet++ + TTA A Comprehensive Study on Colorectal Polyp Segmentation with... code — Compare
DRIVE (5 rows) MERIT-GCASCADE G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified Compare
ISIC 2018 (5 rows) ProMISe ProMISe: Promptable Medical Image Segmentation using SAM code — Compare
Medical Segmentation Decathlon (5 rows) Swin UNETR Self-Supervised Pre-Training of Swin Transformers for 3D Medical... code — Compare
ROBUST-MIS (4 rows) ColonsegNet Exploring Deep Learning Methods for Real-Time Surgical Instrument... — — Compare
Brain US (3 rows) MedT Medical Transformer: Gated Axial-Attention for Medical Image Segmentation code — Compare
CHASE_DB1 (3 rows) MERIT-GCASCADE G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified Compare
EM (3 rows) EMCAD EMCAD: Efficient Multi-scale Convolutional Attention Decoding for... code Syntology official (archive's flag): 20 ran · 20 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified Compare
ISBI 2012 EM Segmentation (3 rows) DC-UNet DC-UNet: Rethinking the U-Net Architecture with Dual Channel... code Syntology official (archive's flag): 2 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
ISIC2018 (3 rows) MobileUNETR MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer... code — Compare
Kvasir-Instrument (3 rows) efficientnetb1 Transfer Learning in Polyp and Endoscopic Tool Segmentation from... code — Compare
RITE (3 rows) KiU-Net KiU-Net: Overcomplete Convolutional Architectures for Biomedical... code — Compare
Endotect Polyp Segmentation Challenge Dataset (2 rows) DDANet DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation code — Compare
ISIC 2018 (2 rows) EMCAD EMCAD: Efficient Multi-scale Convolutional Attention Decoding for... code Syntology official (archive's flag): 20 ran · 20 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified Compare
KvasirCapsule-SEG (2 rows) NanoNet NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy... code — Compare
LiTS2017 (2 rows) UNet 3+ UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation code Syntology official (archive's flag): 1 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified Compare
Medico automatic polyp segmentation challenge (dataset) (2 rows) NanoNet-A NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy... code — Compare
2015 MICCAI Polyp Detection (1 row) DoubleUNet DoubleU-Net: A Deep Convolutional Neural Network for Medical Image... code Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
AMOS (1 row) MedNeXt-L (5x5x5) MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
ASU-Mayo Clinic dataset (1 row) ResUNet++ ResUNet++: An Advanced Architecture for Medical Image Segmentation code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
Autoimmune Dataset (1 row) Unet with APP A Data-Efficient Deep Learning Framework for Segmentation and... code — Compare
Autooral dataset (1 row) HF-UNet A high-order focus interaction model and oral ulcer dataset for... code — Compare
Cell (1 row) UNet++ UNet++: Redesigning Skip Connections to Exploit Multiscale... code Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified Compare
CHAOS MRI Dataset (1 row) MS-Dual-Guided Multi-scale self-guided attention for medical image segmentation code — Compare
Electron Microscopy Dataset (1 row) ReN-UNet Rethinking the Nested U-Net Approach: Enhancing Biomarker... code — Compare
ENSeg (1 row) YOLOv8-m + SAM-b ENSeg: A Novel Dataset and Method for the Segmentation of Enteric... code — Compare
Extended Task10_Colon Medical Decathlon (1 row) nnUNet Expanding the Medical Decathlon dataset: segmentation of colon and... code — Compare
HSVM (1 row) MS-Dual-Guided Multi-scale self-guided attention for medical image segmentation code — Compare
Hyper-Kvasir Dataset (1 row) efficientnetb1 Transfer Learning in Polyp and Endoscopic Tool Segmentation from... code — Compare
iSEG 2017 Challenge (1 row) HyperDenseNet HyperDense-Net: A hyper-densely connected CNN for multi-modal... code Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
MICCAI 2015 Head and Neck Challenge (1 row) AnatomyNet AnatomyNet: Deep Learning for Fast and Fully Automated... code — Compare
MoNuSAC (1 row) MaxViT-UNet MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation code — Compare
MoNuSeg 2018 (1 row) MaxViT-UNet MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation code — Compare
MosMedData (1 row) C2FVL Coarse-to-Fine Covid-19 Segmentation via Vision-Language Alignment code — Compare
PROMISE12 (1 row) Hi-gMISnet Hi-gMISnet: generalized medical image segmentation using DWT based... code — Compare
SegPC-2021 (1 row) DCSAU-Net DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for... code — Compare
Synapse (1 row) nnFormer nnFormer: Interleaved Transformer for Volumetric Segmentation code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
TNBC (1 row) ReN-UNet Rethinking the Nested U-Net Approach: Enhancing Biomarker... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

52 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 52 until expanded.

Subtasks archive 2025-07-28

31 subtasks in the archive's task tree. 30 shown of 31 until expanded.

Papers archive 2025-07-28

archive papers tagged: 2,089 · with a code link: 1,080 · where Syntology ran a sample: 190 (161 with a run with no instrument failure, 29 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (190 of 2,089 tagged: 161 with a run with no instrument failure, 29 where every run was a failure of Syntology's instrument)

Page 1 of 21: papers 1 to 100 of 2,089, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 44 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections