EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908929709047808 |
|---|---|
| author | Tagscherer, Jan de Boer, Sarah Philipp, Lena van der Graaf, Fennie Peeters, Dré Bosma, Joeran Leijten, Lars Obreja, Bogdan Smit, Ewoud Hering, Alessa |
| author_facet | Tagscherer, Jan de Boer, Sarah Philipp, Lena van der Graaf, Fennie Peeters, Dré Bosma, Joeran Leijten, Lars Obreja, Bogdan Smit, Ewoud Hering, Alessa |
| contents | Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03811 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging Tagscherer, Jan de Boer, Sarah Philipp, Lena van der Graaf, Fennie Peeters, Dré Bosma, Joeran Leijten, Lars Obreja, Bogdan Smit, Ewoud Hering, Alessa Computer Vision and Pattern Recognition Machine Learning Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks. |
| title | EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2601.03811 |