{"ID":2833491,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.06014","arxiv_id":"2512.06014","title":"Benchmarking CXR Foundation Models With Publicly Available MIMIC-CXR and NIH-CXR14 Datasets","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.06014","url_pdf":"https://arxiv.org/pdf/2512.06014v1","authors":"[\"Jiho Shin\",\"Dominic Marshall\",\"Matthieu Komorowski\"]","published":"2025-12-03T12:55:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}