BrainFedFM is a structural brain MRI foundation model that was federatively pretrained on 164,707 3‑D scans from 42 sites using a dual‑priority approach that emphasizes informative anatomical regions locally and prioritizes site contributions globally. The model outperformed seven baseline models—including four centralized foundation models—across 20 downstream tasks (classification, regression, segmentation), achieving a mean rank of 1.68 and a 50% performance gain, especially in classification and regression and among underrepresented populations. These results demonstrate the model’s generalizability and show that federated pretraining can effectively develop neuroimaging foundation models without pooling raw images.
By Zhen Yu, Yang Liu, Xiahai Zhuang, Qingchao Chen
arXiv:2603. 28387v2 Announce Type: replace Abstract: Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts.
By Doan Nam Long Vu, Simone Balloccu
The study presents an explainable multimodal deep‑learning framework that combines a 3D CNN for T1‑weighted MRI with a feedforward network for harmonized clinical and demographic data to diagnose Alzheimer’s disease. Using 6,479 ADNI records and 1,703 OASIS‑3 records, the authors compare various model configurations on three‑way and pairwise diagnostic tasks, finding that performance and explanations vary by task, modality, fusion strategy, and cohort. SHAP and Integrated Gradients consistently highlight the MMSE score as the most influential tabular feature, while CAM‑based explanations differ across model setups and cohorts, indicating that explainability is not a stable property under cohort shift.
By Yusuf Brima, Marcellin Atemkeng, Lakshmana Rao Namamula, Antoine Vacavant
The study evaluates whether disease can be identified from reactive, non‑lesional brain tissue in intracranial biopsies. Using four foundation‑model encoders within an attention‑based multiple‑instance learning framework on 245 whole‑slide images, the authors find that disease labels remain predictive even after controlling for slide size and sampling bias, and that performance is similar across all encoders. Signed instance‑contribution maps and expert review confirm that predictive signals localize to reactive parenchyma rather than artifacts such as blood.
"whyItMatters":"The findings demonstrate that weakly supervised models can recover disease signals from tissue traditionally considered non‑diagnostic, highlighting the need for provenance‑only baselines in computational pathology benchmarks."
By Jan Schnorrenberg, Jan Ernsting, Enrico K\"ullenberg, Tim Hahn, Benjamin Risse, Christian Thomas
The paper introduces Neuro‑JEPA, a sparse multimodal foundation model that learns unified representations of brain MRI across T1w, T2w, and FLAIR sequences using a latent predictive objective and a Mixture‑of‑Experts architecture. It was pretrained on over 1.5 million scans from 428,647 studies and systematically evaluates architectural, masking, objective, and sparsity choices for robust multimodal representation learning. Across 47 tasks from three health systems and 12 public datasets, Neuro‑JEPA consistently outperforms a simple CNN baseline, demonstrating its effectiveness for both clinical and research applications.
By Haoxu Huang, Long Chen, Jingyun Chen, Jinu Hyun, James Ryan Loftus, Kara Melmed, Daniel Orringer, Jennifer Frontera, Seena Dehkharghani, Arjun Masurkar, Narges Razavian
arXiv:2603.28387v3 Announce Type: replace-cross
Abstract: Trustworthy clinical AI must use real evidence and avoid relying on surface-level artifacts. We evaluate 12 open-weight vision-language model...
By Doan Nam Long Vu, Simone Balloccu
arXiv:2604. 27277v3 Announce Type: replace-cross Abstract: Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substantial labeled data.
By Yizhou Wu, Shansong Wang, Yuheng Li, Mojtaba Safari, Mingzhe Hu, Chih-Wei Chang, Harini Veeraraghavan, Xiaofeng Yang
The study investigates whether a compact, supervised 3D CNN pretrained for brain‑age prediction can act as a reusable foundation model for various Alzheimer's‑related neuroimaging tasks. By freezing the 7.18 million weights and adding only ~1 % of trainable parameters via Low‑Rank Adaptation, the model achieved high performance across six experiments, including dementia classification, MCI progression prediction, amyloid positivity detection, and volume estimation of hippocampal and white matter hypointensities. The results demonstrate that the pretrained brain‑age model generalizes well to new datasets without retraining, offering a data‑efficient alternative to larger networks.
By Reza Rajabli, D. Louis Collins
The study evaluates whether disease can be identified from reactive, non‑lesional brain tissue in intracranial biopsies. Using four foundation‑model encoders as frozen patch encoders within an attention‑based multiple‑instance learning framework, the authors benchmark performance on 245 whole‑slide images from 186 patients. They find that coarse disease‑category prediction can be largely explained by slide size, but finer diagnostic distinctions remain predictive above chance, with no significant difference among the encoders, suggesting weak morphological signals can be recovered even from tissue traditionally considered non‑diagnostic.
arXiv:2609.15888v1 Announce Type: cross
Abstract: Deep networks trained on structural MRI for Alzheimer's disease (AD) staging often reach reasonable accuracy while attending to anatomically irreleva...
By Paul-Gabriel Nicolae, Irina Georgiana Mocanu
arXiv:2607. 16325v1 Announce Type: cross Abstract: Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms.
By Wei Zhang
arXiv:2607. 24519v1 Announce Type: cross Abstract: Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear.
By Marzieh Zare