A methodology for clinically driven interactive segmentation evaluation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914086947651584 |
|---|---|
| author | Esmaeili, Parhom Fernandez, Virginia Borges, Pedro Gibson, Eli Ourselin, Sebastien Cardoso, M. Jorge |
| author_facet | Esmaeili, Parhom Fernandez, Virginia Borges, Pedro Gibson, Eli Ourselin, Sebastien Cardoso, M. Jorge |
| contents | Interactive segmentation is a promising strategy for building robust, generalisable algorithms for volumetric medical image segmentation. However, inconsistent and clinically unrealistic evaluation hinders fair comparison and misrepresents real-world performance. We propose a clinically grounded methodology for defining evaluation tasks and metrics, and built a software framework for constructing standardised evaluation pipelines. We evaluate state-of-the-art algorithms across heterogeneous and complex tasks and observe that (i) minimising information loss when processing user interactions is critical for model robustness, (ii) adaptive-zooming mechanisms boost robustness and speed convergence, (iii) performance drops if validation prompting behaviour/budgets differ from training, (iv) 2D methods perform well with slab-like images and coarse targets, but 3D context helps with large or irregularly shaped targets, (v) performance of non-medical-domain models (e.g. SAM2) degrades with poor contrast and complex shapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09499 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A methodology for clinically driven interactive segmentation evaluation Esmaeili, Parhom Fernandez, Virginia Borges, Pedro Gibson, Eli Ourselin, Sebastien Cardoso, M. Jorge Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Interactive segmentation is a promising strategy for building robust, generalisable algorithms for volumetric medical image segmentation. However, inconsistent and clinically unrealistic evaluation hinders fair comparison and misrepresents real-world performance. We propose a clinically grounded methodology for defining evaluation tasks and metrics, and built a software framework for constructing standardised evaluation pipelines. We evaluate state-of-the-art algorithms across heterogeneous and complex tasks and observe that (i) minimising information loss when processing user interactions is critical for model robustness, (ii) adaptive-zooming mechanisms boost robustness and speed convergence, (iii) performance drops if validation prompting behaviour/budgets differ from training, (iv) 2D methods perform well with slab-like images and coarse targets, but 3D context helps with large or irregularly shaped targets, (v) performance of non-medical-domain models (e.g. SAM2) degrades with poor contrast and complex shapes. |
| title | A methodology for clinically driven interactive segmentation evaluation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.09499 |