Brain Imaging Foundation Models, Are We There Yet? A Systematic Review of Foundation Models for Brain Imaging and Biomedical Research

2025-06-16

AI Summary

Existing surveys on medical imaging foundation models largely overlook neuroimaging, failing to address its unique challenges—namely multimodal fusion, heterogeneous data integration, and clinical task diversity. Method: We systematically curate 161 neuroimaging datasets and 86 foundation model architectures, conducting the first comprehensive literature analysis focused specifically on brain imaging requirements—spanning self-supervised pretraining, cross-modal alignment, and few-shot fine-tuning. Contribution/Results: We introduce the first neuroimaging-specific foundation model development roadmap, distilling optimal model lineages per clinical task, identifying key performance bottlenecks and critical evaluation gaps. We explicitly characterize current research blind spots and propose clinically actionable adaptation pathways. Our work establishes an authoritative benchmark and practical implementation roadmap for both algorithmic innovation and clinical translation in neuroimaging foundation models.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Other Foundations of Computer Vision
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Foundation models (FMs), large neural networks pretrained on extensive and diverse datasets, have revolutionized artificial intelligence and shown significant promise in medical imaging by enabling robust performance with limited labeled data. Although numerous surveys have reviewed the application of FM in healthcare care, brain imaging remains underrepresented, despite its critical role in the diagnosis and treatment of neurological diseases using modalities such as MRI, CT, and PET. Existing reviews either marginalize brain imaging or lack depth on the unique challenges and requirements of FM in this domain, such as multimodal data integration, support for diverse clinical tasks, and handling of heterogeneous, fragmented datasets. To address this gap, we present the first comprehensive and curated review of FMs for brain imaging. We systematically analyze 161 brain imaging datasets and 86 FM architectures, providing information on key design choices, training paradigms, and optimizations driving recent advances. Our review highlights the leading models for various brain imaging tasks, summarizes their innovations, and critically examines current limitations and blind spots in the literature. We conclude by outlining future research directions to advance FM applications in brain imaging, with the aim of fostering progress in both clinical and research settings.

Problem

• Reviewing underrepresented brain imaging foundation models in medical AI
• Analyzing FM challenges in multimodal brain data integration
• Identifying gaps and future directions for brain imaging FMs

Innovation

• Systematic review of 161 brain imaging datasets
• Analysis of 86 FM architectures and optimizations
• First comprehensive FM review for brain imaging