# Organ Segmentation on MICCAI head and neck challenge 2015 (test)

Source: [Organ Segmentation on MICCAI head and neck challenge 2015 (test)](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test>)

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

Data updated: 2026-02-26T05:39:07.676Z

Evaluation of organ segmentation performance on the test split of the MICCAI Head and Neck Challenge 2015, reporting Dice Similarity Coefficients (DSC) for specific anatomical structures like the Brain Stem, Optic Nerves, and Parotid glands.

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 | Organ Segmentation |
| Dataset (including any stated split) | MICCAI head and neck challenge 2015 (test) |
| Metric | Chiasm DSC |
| 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

- [Chiasm DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Chiasm%20DSC>): Higher is better; unit: PERCENT.

- [Brain Stem DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Brain%20Stem%20DSC>): Higher is better; unit: PERCENT.

- [Mandible DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Mandible%20DSC>): Higher is better; unit: PERCENT.

- [Optic Nerve Left DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Optic%20Nerve%20Left%20DSC>): Higher is better; unit: PERCENT.

- [Optic Nerve Right DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Optic%20Nerve%20Right%20DSC>): Higher is better; unit: PERCENT.

- [Parotid Left DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Parotid%20Left%20DSC>): Higher is better; unit: PERCENT.

- [Parotid Right DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Parotid%20Right%20DSC>): Higher is better; unit: PERCENT.

- [Submandibular Left DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Submandibular%20Left%20DSC>): Higher is better; unit: PERCENT.

- [Submandibular Right DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Submandibular%20Right%20DSC>): Higher is better; unit: PERCENT.

- [Average DSC](<https://www.sota2.com/research/sota/organ-segmentation-on-miccai-head-and-neck-challenge-2015-test.md?metric=Average%20DSC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Chiasm DSC | Result date | Report paper |
| --- | --- | --- | --- |
| Ren et al. | 58 | Not recorded | 68fa65711e209131cea0a72e |
| MICCAI 2015 | 55 | Not recorded | 68fa65711e209131cea0a72e |
| AnatomyNet | 53.22 | Not recorded | 68fa65711e209131cea0a72e |
| Fritscher et al. | 49 | Not recorded | 68fa65711e209131cea0a72e |

### Ren et al.

Chiasm DSC: 58. Result ID: 698cae008b517eb4331c01d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65711e209131cea0a72e.md>)

Recorded evaluation configuration: {"Model Type":"Interleaved ConvNets","Prediction Scope":"Small region of interest (ROI)"}. This record does not assert independent reproduction.

### MICCAI 2015

Chiasm DSC: 55. Result ID: 698cae008b517eb4331c01d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65711e209131cea0a72e.md>)

Recorded evaluation configuration: {"Description":"Best result for each anatomy from the MICCAI 2015 challenge"}. This record does not assert independent reproduction.

### AnatomyNet

Chiasm DSC: 53.22. Result ID: 698cae008b517eb4331c01d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65711e209131cea0a72e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65711e209131cea0a72e.md>)

[Implementation](<https://www.sota2.com/xhx@ics.uci.edu>)

Recorded evaluation configuration: {"Architecture":"3D U-Net variant","Prediction Scope":"Whole-volume slices"}. This record does not assert independent reproduction.

### Fritscher et al.

Chiasm DSC: 49. Result ID: 698cae008b517eb4331c01d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65711e209131cea0a72e.md>)

Recorded evaluation configuration: {"Model Type":"Atlas based ConvNets"}. This record does not assert independent reproduction.

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