Published on: Nov 04, 2025
For the first time, scientists at the Mark and Mary Stevens Neuroimaging and Informatics Institute (Stevens INI) at the Keck School of Medicine of USC have mapped the genetic architecture of the corpus callosum—the thick bundle of nerve fibers connecting the brain’s left and right hemispheres. The groundbreaking findings, published in Nature Communications, open new opportunities to better understand and treat mental illnesses, neurological disorders, and other diseases tied to abnormalities in this critical brain structure.
The corpus callosum plays a vital role in nearly every brain function, from coordinating limb movement and integrating sensory information to enabling complex thinking and decision-making. Alterations in its size or shape have been linked to conditions such as ADHD, bipolar disorder, and Parkinson’s disease, yet its genetic foundations have remained largely unknown—until now.
Using a powerful AI-based tool developed at the Stevens INI, the researchers analyzed brain scans and genetic data from over 50,000 individuals spanning childhood to late adulthood.
We developed an AI tool that identifies the corpus callosum across various MRI scans and automatically measures its structure, explained Shruti P. Gadewar, co-first author and research specialist at Stevens INI.
With this innovation, the team pinpointed dozens of genetic regions that influence both the size and thickness of the corpus callosum and its subregions.
These findings provide a genetic blueprint for one of the brain’s most essential communication networks, said Dr. Ravi R. Bhatt, co-first author and postdoctoral scholar at the INI’s Imaging Genetics Center. “By revealing how specific genes shape the corpus callosum, we can begin to understand why structural differences in this region are associated with various neurological and psychiatric conditions.
The study also showed that distinct gene sets control the area and thickness of the corpus callosum—two features that evolve throughout life and play different roles in brain connectivity. Many of the identified genes are active during prenatal brain development, influencing processes such as cell growth, programmed cell death, and nerve fiber wiring between hemispheres.
This research highlights the power of AI and large-scale data to uncover the genetic drivers of brain development, noted Dr. Neda Jahanshad, associate professor of neurology and senior author of the study. By linking genes to brain structure, we can better understand the biological mechanisms that may contribute to psychiatric and neurological disorders.
The analysis further revealed genetic overlaps between the corpus callosum and the cerebral cortex—the brain’s outer layer responsible for memory, attention, and language—as well as with disorders like ADHD and bipolar disorder.
These connections suggest that some of the same genetic factors shaping the brain’s communication bridge may also increase vulnerability to certain mental health conditions, Dr. Jahanshad added.
Arthur W. Toga, PhD, director of the Stevens INI, emphasized the broader significance of this work:
This study represents a landmark in understanding how the human brain is built. It not only deepens our knowledge of normal brain development but also points to new directions for diagnosing and potentially treating disorders that affect millions worldwide.
To accelerate global research, the team has made their AI tool publicly available. The software automatically detects and measures the corpus callosum from MRI scans, enabling large-scale analyses that would otherwise take years to complete manually.
As a global leader in AI-driven neuroscience, the Stevens INI continues to develop and share cutting-edge computational tools that are reshaping how scientists study the brain.
Artificial intelligence is transforming brain research, and Stevens INI is leading that transformation,”said Dr. Toga. “By creating and openly sharing AI tools, we’re enabling researchers around the world to make discoveries about brain structure and disease faster than ever before.
Back to News© 2025 SciInov. All Rights Reserved.