Large-scale AI and foundation models for neuroscience: A comprehensive review
10 affiliations
- 1Stevens Institute of Technology, Department of Systems Engineering, Hoboken, 07030, NJ, USA
- 2University of California San Francisco, Department of Neurology and Weill Institute for Neurosciences, San Francisco, 94143, CA, USA
- 3Duke University, Duke Institute for Brain Sciences, Durham, 27708, NC, USA
- 4Boston University, Division of Systems Engineering and Department of Electrical and Computer Engineering, Boston, 02215, MA, USA
- 5Monash University, Department of Neuroscience, School of Translational Medicine, Melbourne, 3800, VIC, Australia
- 6Alfred Hospital, Department of Neurology, Melbourne, 3004, VIC, Australia
- 7University of California San Francisco, Department of Radiology and Biomedical Imaging, San Francisco, 94143, CA, USA
- 8Stanford Institute for Human-Centered AI, Stanford University, Stanford, 94305, CA, USA
- 9Stanford University School of Medicine, Department of Psychiatry and Behavioral Sciences, Stanford, 94305, CA, USA
- 10Wu Tsai Neurosciences Institute, Stanford University, Stanford, 94305, CA, USA
Abstract
The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw brain signals and neural data. In this paper, we review applications of large-scale AI models across four major neuroscience domains: neu- roimaging and data processing, brain-computer interfaces and neural decoding, clinical decision support and translational frameworks, and disease-specific applications across neurological and psychiatric disorders. These models show potential to address major computational neuroscience challenges, including multimodal neural data integration, spatiotemporal pattern interpretation, and the development of translational frameworks for clinical research. Moreover, the interaction between neuroscience and AI has become increasingly reciprocal, as biologically informed architectural constraints are now incorporated to develop more interpretable and computationally efficient models. This review highlights both the promise of such technologies and critical implementation considerations, with particular emphasis on rigorous evaluation frameworks, effective integration of domain knowledge, prospective clinical validation, and comprehensive ethical guidelines. Finally, a systematic listing of critical neuroscience datasets used to develop and evaluate large-scale AI models across diverse research applications is provided.
Related
- Comprehensive Phenological Documentation of Idesia polycarpa Using the BBCH Scale: From Bud Development to Dormancy
- Re-evaluating the benefit of pretraining scale in cell foundation models
- ALHENA, an H&E encoder distilled from transcriptomic foundation models for multi-scale slide analysis
- Learning from tandem mass spectra at scale with a self-supervised foundation model for proteomics
- ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models
BibTeX
@article{yang2026largescale,
title = {{Large-scale AI and foundation models for neuroscience: A comprehensive review}},
author = {Shihao Yang and Xiying Huang and Danilo Bernardo and Jun-En Ding and Andrew Michael and Jingmei Yang and Jingmei Yang and Alison Anderson and Dinesh Giritharan and Patrick Kwan and Ashish Raj and Yu Zhang and Feng Liu},
journal = {Meta-Radiology},
year = {2026},
month = jun,
doi = {10.1016/j.metrad.2026.100224},
url = {https://doi.org/10.1016/j.metrad.2026.100224},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Large-scale AI and foundation models for neuroscience: A comprehensive review
AU - Shihao Yang
AU - Xiying Huang
AU - Danilo Bernardo
AU - Jun-En Ding
AU - Andrew Michael
AU - Jingmei Yang
AU - Jingmei Yang
AU - Alison Anderson
AU - Dinesh Giritharan
AU - Patrick Kwan
AU - Ashish Raj
AU - Yu Zhang
AU - Feng Liu
PY - 2026
DA - 2026/06/04
JO - Meta-Radiology
DO - 10.1016/j.metrad.2026.100224
UR - https://doi.org/10.1016/j.metrad.2026.100224
AB - The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw brain signals and neural data. In this paper, we review applications of large-scale AI models across four major neuroscience domains: neu- roimaging and data processing, brain-computer interfaces and neural decoding, clinical decision support and translational frameworks, and disease-specific applications across neurological and psychiatric disorders. These models show potential to address major computational neuroscience challenges, including multimodal neural data integration, spatiotemporal pattern interpretation, and the development of translational frameworks for clinical research. Moreover, the interaction between neuroscience and AI has become increasingly reciprocal, as biologically informed architectural constraints are now incorporated to develop more interpretable and computationally efficient models. This review highlights both the promise of such technologies and critical implementation considerations, with particular emphasis on rigorous evaluation frameworks, effective integration of domain knowledge, prospective clinical validation, and comprehensive ethical guidelines. Finally, a systematic listing of critical neuroscience datasets used to develop and evaluate large-scale AI models across diverse research applications is provided.
SN - 2950-1628
ER -