Benchmarking CXR Foundation Models With Publicly Available MIMIC-CXR and NIH-CXR14 Datasets
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_ | 1866914182928007168 |
|---|---|
| author | Shin, Jiho Marshall, Dominic Komorowski, Matthieu |
| author_facet | Shin, Jiho Marshall, Dominic Komorowski, Matthieu |
| contents | Recent foundation models have demonstrated strong performance in medical image representation learning, yet their comparative behaviour across datasets remains underexplored. This work benchmarks two large-scale chest X-ray (CXR) embedding models (CXR-Foundation (ELIXR v2.0) and MedImagelnsight) on public MIMIC-CR and NIH ChestX-ray14 datasets. Each model was evaluated using a unified preprocessing pipeline and fixed downstream classifiers to ensure reproducible comparison. We extracted embeddings directly from pre-trained encoders, trained lightweight LightGBM classifiers on multiple disease labels, and reported mean AUROC, and F1-score with 95% confidence intervals. MedImageInsight achieved slightly higher performance across most tasks, while CXR-Foundation exhibited strong cross-dataset stability. Unsupervised clustering of MedImageIn-sight embeddings further revealed a coherent disease-specific structure consistent with quantitative results. The results highlight the need for standardised evaluation of medical foundation models and establish reproducible baselines for future multimodal and clinical integration studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06014 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking CXR Foundation Models With Publicly Available MIMIC-CXR and NIH-CXR14 Datasets Shin, Jiho Marshall, Dominic Komorowski, Matthieu Computer Vision and Pattern Recognition Recent foundation models have demonstrated strong performance in medical image representation learning, yet their comparative behaviour across datasets remains underexplored. This work benchmarks two large-scale chest X-ray (CXR) embedding models (CXR-Foundation (ELIXR v2.0) and MedImagelnsight) on public MIMIC-CR and NIH ChestX-ray14 datasets. Each model was evaluated using a unified preprocessing pipeline and fixed downstream classifiers to ensure reproducible comparison. We extracted embeddings directly from pre-trained encoders, trained lightweight LightGBM classifiers on multiple disease labels, and reported mean AUROC, and F1-score with 95% confidence intervals. MedImageInsight achieved slightly higher performance across most tasks, while CXR-Foundation exhibited strong cross-dataset stability. Unsupervised clustering of MedImageIn-sight embeddings further revealed a coherent disease-specific structure consistent with quantitative results. The results highlight the need for standardised evaluation of medical foundation models and establish reproducible baselines for future multimodal and clinical integration studies. |
| title | Benchmarking CXR Foundation Models With Publicly Available MIMIC-CXR and NIH-CXR14 Datasets |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.06014 |