# Cardiac Segmentation on M&Ms

Source: [Cardiac Segmentation on M&Ms](<https://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:40:23.227Z

Evaluation of cardiac segmentation models on the M&Ms dataset, reporting Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), Jaccard Index (JAC), Average Symmetric Surface Distance (ASSD), and Min-max Score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Cardiac Segmentation |
| Dataset (including any stated split) | M&Ms |
| Metric | DSC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [DSC](<https://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms.md?metric=DSC>): Higher is better; unit: PERCENT.

- [HD](<https://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms.md?metric=HD>): Lower is better; unit: OTHER.

- [JAC](<https://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms.md?metric=JAC>): Higher is better; unit: PERCENT.

- [ASSD](<https://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms.md?metric=ASSD>): Lower is better; unit: OTHER.

- [Min-max Score](<https://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms.md?metric=Min-max%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | DSC | Result date | Report paper |
| --- | --- | --- | --- |
| P1 | 88.13 | Not recorded | 68fa6a7b1e209131cea287df |
| P2 | 87.5 | Not recorded | 68fa6a7b1e209131cea287df |
| LSCL-TTA | 87.1 | Not recorded | 68fa6a7b1e209131cea287df |
| P3 | 87.05 | Not recorded | 68fa6a7b1e209131cea287df |

### P1

DSC: 88.13. Result ID: 698e3a5bffc3901de09bd3d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea287df.md>)

Recorded evaluation configuration: {"Training time":"60 h","Inference time":"≈ 1s","GPU Device":"Titan XP"}. This record does not assert independent reproduction.

### P2

DSC: 87.5. Result ID: 698e3a5bffc3901de09bd3d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea287df.md>)

Recorded evaluation configuration: {"Training time":"48 h","Inference time":"4.8 s","GPU Device":"Tesla V100"}. This record does not assert independent reproduction.

### LSCL-TTA

DSC: 87.1. Result ID: 698e3a5bffc3901de09bd3d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea287df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea287df.md>)

Recorded evaluation configuration: {"Training time":"5 h","Inference time":"0.2 s","GPU Device":"GTX 1080 Ti","Test-time Augmentation (TTA)":"true"}. This record does not assert independent reproduction.

### P3

DSC: 87.05. Result ID: 698e3a5bffc3901de09bd3d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea287df.md>)

Recorded evaluation configuration: {"Training time":"4-5 days","Inference time":"N/A","GPU Device":"TITAN V100"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.