# Multi-class Semantic Segmentation on ACDC (Dice and IoU per Class)

Source: [Multi-class Semantic Segmentation on ACDC (Dice and IoU per Class)](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class>)

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

Data updated: 2026-06-05T09:32:31.865Z

Evaluation of Multi-class Semantic Segmentation performance on the ACDC dataset, reporting detailed Dice and IoU scores for RV, Myo, and LV structures, alongside mean metrics.

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 | Multi-class Semantic Segmentation |
| Dataset (including any stated split) | ACDC |
| Metric | Dice RV |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Dice RV](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Dice%20RV>): Higher is better; unit: PERCENT.

- [Dice Myo](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Dice%20Myo>): Higher is better; unit: PERCENT.

- [Dice LV](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Dice%20LV>): Higher is better; unit: PERCENT.

- [Mean Dice](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Mean%20Dice>): Higher is better; unit: PERCENT.

- [IoU RV](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=IoU%20RV>): Higher is better; unit: PERCENT.

- [IoU Myo](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=IoU%20Myo>): Higher is better; unit: PERCENT.

- [IoU LV](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=IoU%20LV>): Higher is better; unit: PERCENT.

- [Mean IoU](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Mean%20IoU>): Higher is better; unit: PERCENT.

- [Mean Sensitivity](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Mean%20Sensitivity>): Higher is better; unit: PERCENT.

- [Mean Precision](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Mean%20Precision>): Higher is better; unit: PERCENT.

- [Mean MCC](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Mean%20MCC>): Higher is better; unit: PERCENT.

- [Dice FG](<https://www.sota2.com/research/sota/multi-class-semantic-segmentation-on-acdc-dice-and-iou-per-class.md?metric=Dice%20FG>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Dice RV | Result date | Report paper |
| --- | --- | --- | --- |
| U-Net Transformer | 91.23 | Not recorded | 6a22587b86173ad9c1468a3a |
| MS-DKC-UTrans-ABR | 90.86 | Not recorded | 6a22587b86173ad9c1468a3a |
| U-Net | 90.72 | Not recorded | 6a22587b86173ad9c1468a3a |
| DKC-HDNeXt-Lite | 85.12 | Not recorded | 6a22587b86173ad9c1468a3a |
| Shallow U-Net | 77.66 | Not recorded | 6a22587b86173ad9c1468a3a |

### U-Net Transformer

Dice RV: 91.23. Result ID: 6a2297adfbc373592c2110f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

Recorded evaluation configuration: {"Protocol":"NoAug/NoVal"}. This record does not assert independent reproduction.

### MS-DKC-UTrans-ABR

Dice RV: 90.86. Result ID: 6a2297adfbc373592c2110f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

Recorded evaluation configuration: {"Protocol":"NoAug/NoVal"}. This record does not assert independent reproduction.

### U-Net

Dice RV: 90.72. Result ID: 6a2297adfbc373592c2110f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61e11e209131ce9f653d.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net>)

Recorded evaluation configuration: {"Protocol":"NoAug/NoVal"}. This record does not assert independent reproduction.

### DKC-HDNeXt-Lite

Dice RV: 85.12. Result ID: 6a2297adfbc373592c2110f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

Recorded evaluation configuration: {"Protocol":"NoAug/NoVal"}. This record does not assert independent reproduction.

### Shallow U-Net

Dice RV: 77.66. Result ID: 6a2297adfbc373592c2110f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

Recorded evaluation configuration: {"Protocol":"NoAug/NoVal"}. This record does not assert independent reproduction.

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