Stanford Psychiatry’s Vinod Menon Awarded Grant Focused on Foundation Models for Human Functional Neuroimaging with Applications to Psychiatric Disorders

We are pleased to announce that Stanford Psychiatry’s Vinod Menon, the Rachael L. and Walter F. Nichols, MD, professor of psychiatry and behavioral sciences, and by courtesy, of education and of neurology and neurological sciences, has received a grant from the National Institute of Mental Health focused on foundation models for human functional neuroimaging with applications to psychiatric disorders.

In recent years, a successful new paradigm for building artificial intelligence systems has emerged: train a single model on a vast amount of heterogeneous, unlabeled data and adapt it to various applications. While such foundation models have demonstrated unprecedented capabilities in fields as diverse as natural language processing and medicine, their potential for decoding the complexities of human functional brain imaging data remains largely untapped.

Building on promising preliminary results, Dr. Menon and the study team will address the challenges of conventional data analysis methods for functional brain imaging by developing an integrated framework that will be used to analyze large open-source human brain imaging datasets and phenotypic data across multiple psychiatric disorders. These innovative foundation models will provide a robust framework for effectively integrating heterogeneous datasets and addressing the recurrent issue of class imbalance in clinical brain imaging studies.

By pioneering state-of-the-art foundation models tailored for functional brain imaging, the study team aims to equip researchers with a transformative toolset for investigating the neurobiology of a range of psychiatric disorders within a unified framework. Moreover, the open sharing of foundation models and associated data analysis code will catalyze future research, significantly amplifying the impact and scope of our work.

“We will analyze large-scale human brain imaging and phenotypic data from the Human Connectome Project and related datasets to identify personalized neurobiological markers and predict symptom severity across multiple conditions,” says Dr. Menon. “By creating powerful and adaptable computational tools, this research will lay the groundwork for more precise diagnostic and treatment strategies, potentially transforming mental healthcare outcomes.”

The Stanford Cognitive and Systems Neuroscience Laboratory (SCSNL), directed by Dr. Menon, aims to advance fundamental knowledge of human brain function and to use this knowledge to help children and adults with psychiatric and neurological disorders. Recent publications related to this work include:

• Ryali, S., Zhang, Y., de los Angeles, C., Supekar, K. & Menon, V. (2024). Deep learning models reveal replicable, generalizable, and behaviorally relevant sex differences in human functional brain organization. Proceedings of the National Academy of Sciences, 121(9), e2310012121.  PubMed
  
• Supekar, K., de los Angeles, C., Ryali, S., Kushan, L., Schleifer, C., Repetto, G., Crossley, N., Simon, T., Bearden, C., & Menon, V. (2024). Robust and Replicable functional brain signatures of 22q11.2 deletion syndrome and associated psychosis: A deep neural network-based multi-cohort study. Molecular Psychiatry, 1-16. PubMed 

More Information

For more details about this project, visit NIH RePORTER.