# Tumor Segmentation on In-house Colon Tumor Data

Source: [Tumor Segmentation on In-house Colon Tumor Data](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data>)

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

Data updated: 2026-02-26T05:40:31.367Z

Evaluation of tumor segmentation performance on the proprietary In-house Colon Tumor dataset, reporting Dice Similarity Coefficients (DSC) for individual tumor classes (T1-T4) and average metrics including HD95.

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 | Tumor Segmentation |
| Dataset (including any stated split) | In-house Colon Tumor Data |
| Metric | DSC (T1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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 (T1)](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data.md?metric=DSC%20(T1)>): Higher is better; unit: PERCENT.

- [DSC (T2)](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data.md?metric=DSC%20(T2)>): Higher is better; unit: PERCENT.

- [DSC (T3)](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data.md?metric=DSC%20(T3)>): Higher is better; unit: PERCENT.

- [DSC (T4)](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data.md?metric=DSC%20(T4)>): Higher is better; unit: PERCENT.

- [Avg DSC](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data.md?metric=Avg%20DSC>): Higher is better; unit: PERCENT.

- [HD95 (Avg)](<https://www.sota2.com/research/sota/tumor-segmentation-on-in-house-colon-tumor-data.md?metric=HD95%20(Avg)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | DSC (T1) | Result date | Report paper |
| --- | --- | --- | --- |
| SegVol | 36.93 | Not recorded | 68fa757b1e209131cea68405 |
| SAM-Med3D | 34.28 | Not recorded | 68fa757b1e209131cea68405 |
| CAT | 30.62 | Not recorded | 68fa757b1e209131cea68405 |
| ZePT | 23.87 | Not recorded | 68fa757b1e209131cea68405 |
| Swin UNETR | 21.4 | Not recorded | 68fa757b1e209131cea68405 |
| nnUNet | 19.51 | Not recorded | 68fa757b1e209131cea68405 |
| Universal | 7.11 | Not recorded | 68fa757b1e209131cea68405 |

### SegVol

DSC (T1): 36.93. Result ID: 6993b6c73a6c31484918053f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76f01e209131cea701c0.md>)

[Implementation](<https://github.com/BAAI-DCAI/SegVol>)

Recorded evaluation configuration: {"weights":"Official pre-trained weights"}. This record does not assert independent reproduction.

### SAM-Med3D

DSC (T1): 34.28. Result ID: 6993b6c73a6c31484918053e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c81e209131cea63c72.md>)

Recorded evaluation configuration: {"weights":"Official pre-trained weights"}. This record does not assert independent reproduction.

### CAT

DSC (T1): 30.62. Result ID: 6993b6c73a6c314849180542.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ZePT

DSC (T1): 23.87. Result ID: 6993b6c73a6c314849180541.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729f1e209131cea579a7.md>)

Recorded evaluation configuration: {"training\_mode":"Implemented from official code and trained on same dataset"}. This record does not assert independent reproduction.

### Swin UNETR

DSC (T1): 21.4. Result ID: 6993b6c73a6c31484918053d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea3234f.md>)

[Implementation](<https://monai.io/research/swin-unetr>)

Recorded evaluation configuration: {"training\_mode":"Implemented from official code and trained on same dataset"}. This record does not assert independent reproduction.

### nnUNet

DSC (T1): 19.51. Result ID: 6993b6c73a6c31484918053c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

Recorded evaluation configuration: {"training\_mode":"Implemented from official code and trained on same dataset"}. This record does not assert independent reproduction.

### Universal

DSC (T1): 7.11. Result ID: 6993b6c73a6c314849180540.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757b1e209131cea68405.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73e31e209131cea5eb0d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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