Codesota · Medical · Medical Image Segmentation · ACDCTasks/Medical/Medical Image Segmentation
Medical Image Segmentation · benchmark dataset · 2017 · EN

Automated Cardiac Diagnosis Challenge.

150 cardiac MRI cases segmenting right ventricle, myocardium, and left ventricle. MICCAI 2017 challenge.

Paper ↗Download datasetSubmit a result ↵
§ 01 · Leaderboard

Best published scores.

6 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
mean-dsc · higher is better
mean-dsc· primary
6 rows
#ModelOrgSubmittedPaper / codemean-dsc
01MedNeXt-LOSSGerman Cancer Research Center (DKFZ)Mar 2023MedNeXt: Transformer-driven Scaling of ConvNets for Medi… · code92.65
02nnU-Net v2OSSGerman Cancer Research Center (DKFZ)Mar 2023MedNeXt: Transformer-driven Scaling of ConvNets for Medi… · code91.61
03LightM-UNetOSSLiao et al.Mar 2024LightM-UNet: Mamba Assists in Lightweight UNet for Medic… · code90.49
04U-Mamba (Bot)OSSWang et al. (University of Toronto)Jan 2024U-Mamba: Enhancing Long-range Dependency for Biomedical … · code90.32
05nnFormerOSSZhou et al.Sep 2021nnFormer: Interleaved Transformer for Volumetric Segment… · code90.22
06TransUNetOSSChen et al. (JHU)Feb 2021TransUNet: Transformers Make Strong Encoders for Medical… · code89.07
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

3 steps
of state of the art.

Each row below marks a model that broke the previous record on mean-dsc. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · mean-dsc
  1. Feb 8, 2021TransUNetChen et al. (JHU)89.07
  2. Sep 7, 2021nnFormerZhou et al.90.22
  3. Mar 17, 2023MedNeXt-LGerman Cancer Research Center (DKFZ)92.65
Fig 3 · SOTA-setting models only. 3 entries span Feb 2021 → Mar 2023.
§ 04 · Literature

5 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies