# Brain Tumor Segmentation on Multi-modal brain tumor segmentation dataset (test)

Source: [Brain Tumor Segmentation on Multi-modal brain tumor segmentation dataset (test)](<https://www.sota2.com/research/sota/brain-tumor-segmentation-on-multi-modal-brain-tumor-segmentation-dataset-test>)

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

Data updated: 2026-02-26T05:48:30.275Z

Evaluation of model efficiency for Brain Tumor Segmentation on the test split of the Multi-modal brain tumor segmentation dataset, focusing on parameter count, inference speed, and memory footprint.

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 | Brain Tumor Segmentation |
| Dataset (including any stated split) | Multi-modal brain tumor segmentation dataset (test) |
| Metric | Latency (s) |
| Unit | TIME |
| Direction | Lower 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

- [Latency (s)](<https://www.sota2.com/research/sota/brain-tumor-segmentation-on-multi-modal-brain-tumor-segmentation-dataset-test.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

- [Params (M)](<https://www.sota2.com/research/sota/brain-tumor-segmentation-on-multi-modal-brain-tumor-segmentation-dataset-test.md?metric=Params%20(M)>): Lower is better; unit: SIZE.

- [Memory Footprint (GB)](<https://www.sota2.com/research/sota/brain-tumor-segmentation-on-multi-modal-brain-tumor-segmentation-dataset-test.md?metric=Memory%20Footprint%20(GB)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Latency (s) | Result date | Report paper |
| --- | --- | --- | --- |
| V-Net-DS | 0.33 | Not recorded | 68fa70ca1e209131cea4d1e0 |
| UTNet | 0.41 | Not recorded | 68fa70ca1e209131cea4d1e0 |
| HartleyMHA | 0.57 | Not recorded | 68fa70ca1e209131cea4d1e0 |
| FNO | 0.61 | Not recorded | 68fa70ca1e209131cea4d1e0 |
| HNOSeg | 0.71 | Not recorded | 68fa70ca1e209131cea4d1e0 |

### V-Net-DS

Latency (s): 0.33. Result ID: 6991588a3a6c314849077cb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64db1e209131cea06c52.md>)

Recorded evaluation configuration: {"Batch size":1,"Input resolution":"240x240x155"}. This record does not assert independent reproduction.

### UTNet

Latency (s): 0.41. Result ID: 6991588a3a6c314849077cb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ad71e209131cea2ab44.md>)

Recorded evaluation configuration: {"Batch size":1,"Input resolution":"240x240x155"}. This record does not assert independent reproduction.

### HartleyMHA

Latency (s): 0.57. Result ID: 6991588a3a6c314849077cb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Implementation](<https://github.com/IBM/multimodal-3d-image-segmentation>)

Recorded evaluation configuration: {"Batch size":1,"Input resolution":"240x240x155"}. This record does not assert independent reproduction.

### FNO

Latency (s): 0.61. Result ID: 6991588a3a6c314849077cb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa581d1e209131ce9ab45d.md>)

Recorded evaluation configuration: {"Batch size":1,"Input resolution":"240x240x155"}. This record does not assert independent reproduction.

### HNOSeg

Latency (s): 0.71. Result ID: 6991588a3a6c314849077cb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ca1e209131cea4d1e0.md>)

[Implementation](<https://github.com/IBM/multimodal-3d-image-segmentation>)

Recorded evaluation configuration: {"Batch size":1,"Input resolution":"240x240x155"}. This record does not assert independent reproduction.

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