Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg
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_ | 1866912340681687040 |
|---|---|
| author | Zou, Jingchen Li, Jianqiang Jimenez, Gabriel Zhao, Qing Racoceanu, Daniel Cosarinsky, Matias Ferrante, Enzo Fu, Guanghui |
| author_facet | Zou, Jingchen Li, Jianqiang Jimenez, Gabriel Zhao, Qing Racoceanu, Daniel Cosarinsky, Matias Ferrante, Enzo Fu, Guanghui |
| contents | The performance of medical image segmentation models is usually evaluated using metrics like the Dice score and Hausdorff distance, which compare predicted masks to ground truth annotations. However, when applying the model to unseen data, such as in clinical settings, it is often impractical to annotate all the data, making the model's performance uncertain. To address this challenge, we propose the Segmentation Performance Evaluator (SPE), a framework for estimating segmentation models' performance on unlabeled data. This framework is adaptable to various evaluation metrics and model architectures. Experiments on six publicly available datasets across six evaluation metrics including pixel-based metrics such as Dice score and distance-based metrics like HD95, demonstrated the versatility and effectiveness of our approach, achieving a high correlation (0.956$\pm$0.046) and low MAE (0.025$\pm$0.019) compare with real Dice score on the independent test set. These results highlight its ability to reliably estimate model performance without requiring annotations. The SPE framework integrates seamlessly into any model training process without adding training overhead, enabling performance estimation and facilitating the real-world application of medical image segmentation algorithms. The source code is publicly available |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15667 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg Zou, Jingchen Li, Jianqiang Jimenez, Gabriel Zhao, Qing Racoceanu, Daniel Cosarinsky, Matias Ferrante, Enzo Fu, Guanghui Image and Video Processing Computer Vision and Pattern Recognition The performance of medical image segmentation models is usually evaluated using metrics like the Dice score and Hausdorff distance, which compare predicted masks to ground truth annotations. However, when applying the model to unseen data, such as in clinical settings, it is often impractical to annotate all the data, making the model's performance uncertain. To address this challenge, we propose the Segmentation Performance Evaluator (SPE), a framework for estimating segmentation models' performance on unlabeled data. This framework is adaptable to various evaluation metrics and model architectures. Experiments on six publicly available datasets across six evaluation metrics including pixel-based metrics such as Dice score and distance-based metrics like HD95, demonstrated the versatility and effectiveness of our approach, achieving a high correlation (0.956$\pm$0.046) and low MAE (0.025$\pm$0.019) compare with real Dice score on the independent test set. These results highlight its ability to reliably estimate model performance without requiring annotations. The SPE framework integrates seamlessly into any model training process without adding training overhead, enabling performance estimation and facilitating the real-world application of medical image segmentation algorithms. The source code is publicly available |
| title | Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15667 |