Cracking the PUMA Challenge in 24 Hours with CellViT++ and nnU-Net
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917958612156416 |
|---|---|
| author | Shahamiri, Negar Rempe, Moritz Heine, Lukas Kleesiek, Jens Hörst, Fabian |
| author_facet | Shahamiri, Negar Rempe, Moritz Heine, Lukas Kleesiek, Jens Hörst, Fabian |
| contents | Automatic tissue segmentation and nuclei detection is an important task in pathology, aiding in biomarker extraction and discovery. The panoptic segmentation of nuclei and tissue in advanced melanoma (PUMA) challenge aims to improve tissue segmentation and nuclei detection in melanoma histopathology. Unlike many challenge submissions focusing on extensive model tuning, our approach emphasizes delivering a deployable solution within a 24-hour development timeframe, using out-of-the-box frameworks. The pipeline combines two models, namely CellViT++ for nuclei detection and nnU-Net for tissue segmentation. Our results demonstrate a significant improvement in tissue segmentation, achieving a Dice score of 0.750, surpassing the baseline score of 0.629. For nuclei detection, we obtained results comparable to the baseline in both challenge tracks. The code is publicly available at https://github.com/TIO-IKIM/PUMA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12269 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cracking the PUMA Challenge in 24 Hours with CellViT++ and nnU-Net Shahamiri, Negar Rempe, Moritz Heine, Lukas Kleesiek, Jens Hörst, Fabian Computer Vision and Pattern Recognition Automatic tissue segmentation and nuclei detection is an important task in pathology, aiding in biomarker extraction and discovery. The panoptic segmentation of nuclei and tissue in advanced melanoma (PUMA) challenge aims to improve tissue segmentation and nuclei detection in melanoma histopathology. Unlike many challenge submissions focusing on extensive model tuning, our approach emphasizes delivering a deployable solution within a 24-hour development timeframe, using out-of-the-box frameworks. The pipeline combines two models, namely CellViT++ for nuclei detection and nnU-Net for tissue segmentation. Our results demonstrate a significant improvement in tissue segmentation, achieving a Dice score of 0.750, surpassing the baseline score of 0.629. For nuclei detection, we obtained results comparable to the baseline in both challenge tracks. The code is publicly available at https://github.com/TIO-IKIM/PUMA. |
| title | Cracking the PUMA Challenge in 24 Hours with CellViT++ and nnU-Net |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12269 |