Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

• URL: http://arxiv.org/abs/2604.11679v1
• Date: Mon, 13 Apr 2026 16:23:46 GMT
• Title: Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge
• Abstract summary: We organized the FOMO25 challenge as a satellite event at MICCAI 2025.<n>We provided participants with a large pretraining dataset, FOMO60K, and evaluated models on data sourced directly from clinical labels.<n>19 foundation models from sixteen teams were evaluated using a standardized containerized pipeline.
• Score: 33.95846433611413
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obtain. Self-supervised learning (SSL) can address this by leveraging the vast amounts of unlabeled data produced in clinical workflows to train robust \textit{foundation models} that adapt out-of-domain with minimal supervision. However, the development of foundation models for brain MRI has been limited by small pretraining datasets and in-domain benchmarking focused on high-quality, research-grade data. To address this gap, we organized the FOMO25 challenge as a satellite event at MICCAI 2025. FOMO25 provided participants with a large pretraining dataset, FOMO60K, and evaluated models on data sourced directly from clinical workflows in few-shot and out-of-domain settings. Tasks covered infarct classification, meningioma segmentation, and brain age regression, and considered both models trained on FOMO60K (method track) and any data (open track). Nineteen foundation models from sixteen teams were evaluated using a standardized containerized pipeline. Results show that (a) self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained \textit{out-of-domain} surpassing supervised baselines trained \textit{in-domain}. (b) No single pretraining objective benefits all tasks: MAE favors segmentation, hybrid reconstruction-contrastive objectives favor classification, and (c) strong performance was achieved by small pretrained models, and improvements from scaling model size and training duration did not yield reliable benefits.

Related papers

• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement [81.27196033392559]
  We propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis.<n>COME injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training.<n>Our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline.
  arXiv  Detail & Related papers  (2026-07-24T04:26:47Z)
• Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study [1.8964402635820148]
  This work focuses on foundation models for electrocardiography (ECG) data, one of the most widely captured physiological time series world-wide.<n>We present a comprehensive assessment of pretraining methodologies, covering five different contrastive and non-contrastive self-supervised learning objectives for ECG foundation models.<n>We investigate their scaling behavior with pretraining dataset sizes up to 11M input samples, exclusively from publicly available sources.
  arXiv  Detail & Related papers  (2026-05-12T15:10:15Z)
• On Predicting the Post-training Potential of Pre-trained LLMs [60.07459271263409]
  We introduce a new task of predicting post-training potential - forecasting a base model's performance before post-training.<n>We propose RuDE, a unified framework that bypasses the generation gap of base models by leveraging response discrimination.<n>Experiments demonstrate a correlation greater than 90% with post-training performance.
  arXiv  Detail & Related papers  (2026-05-12T11:33:49Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Federated Foundation Model for GI Endoscopy Images [7.9528382609447545]
  Foundation models offer a promising solution by learning general-purpose representations, which can be finetuned for specific tasks.<n>Foundation model training typically requires extensive datasets, and while hospitals generate large volumes of data, privacy restrictions prevent direct data sharing.<n>We propose a FL framework for training foundation models for gastroendoscopy imaging, enabling data to remain within local hospital environments while contributing to a shared model.
  arXiv  Detail & Related papers  (2025-05-30T01:18:17Z)
• FACT: Foundation Model for Assessing Cancer Tissue Margins with Mass Spectrometry [1.0183055506531902]
  FACT is an adaptation of a foundation model originally designed for text-audio association, pretrained using our proposed supervised contrastive approach based on triplet loss.<n>Results: Our proposed model significantly improves the classification performance, achieving state-of-the-art performance with an AUROC of $82.4% pm 0.8$.
  arXiv  Detail & Related papers  (2025-04-15T16:36:03Z)
• FedEFM: Federated Endovascular Foundation Model with Unseen Data [11.320026809291239]
  This paper proposes a new method to train a foundation model in a decentralized federated learning setting for endovascular intervention.<n>We tackle the unseen data issue using differentiable Earth Mover's Distance within a knowledge distillation framework.<n>Our approach achieves new state-of-the-art results, contributing to advancements in endovascular intervention and robotic-assisted surgery.
  arXiv  Detail & Related papers  (2025-01-28T14:46:38Z)
• Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation [113.5002649181103]
  Training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
  arXiv  Detail & Related papers  (2024-03-12T18:12:02Z)
• A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records [2.83988353856908]
  Foundation models hold promise for transforming AI in healthcare by providing modular components that are easily adaptable to downstream healthcare tasks. This study examined the adaptability of a recently released structured EHR foundation model ($FM_SM$) trained on longitudinal medical record data from 2.57M Stanford Medicine patients. Our findings show that adapting shared EHR foundation models across hospitals provides improved prediction performance at less cost.
  arXiv  Detail & Related papers  (2023-11-20T01:58:27Z)
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models [69.9178140563928]
  Colonoscopy analysis is essential for assisting clinical diagnosis and treatment. The scarcity of annotated data limits the effectiveness and generalization of existing methods. We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-03T07:55:46Z)
• SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models [48.07469930813923]
  This work aims to forecast the demand for healthcare services, by predicting the number of patient visits to healthcare facilities. We introduce SANSformer, an attention-free sequential model designed with specific inductive biases to cater for the unique characteristics of EHR data. Our results illuminate the promising potential of tailored attention-free models and self-supervised pretraining in refining healthcare utilization predictions across various patient demographics.
  arXiv  Detail & Related papers  (2021-08-31T08:23:56Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.