AI Tracks Vital White Matter Pathways in the Brainstem

New algorithm segments and analyzes key neural bundles affected by trauma and disease

Published on Feb. 11, 2026

Got story updates? Submit your updates here. ›

Researchers at MIT, Harvard, and Massachusetts General Hospital have developed an AI-powered software tool called BrainStem Bundle Tool (BSBT) that can automatically segment and analyze eight distinct bundles of white matter fibers in the brainstem from diffusion MRI scans. The tool has revealed distinct patterns of structural changes in patients with Parkinson's disease, multiple sclerosis, traumatic brain injury, and Alzheimer's disease, and has also shown potential to track recovery in coma patients.

Why it matters

The brainstem is a crucial but largely unexplored region of the brain that controls many essential functions like consciousness, sleep, breathing, heart rate, and motion. Imaging the brainstem's complex white matter structure has been challenging, leaving researchers and doctors with limited ability to assess how it is affected by trauma or neurodegeneration. This new AI-powered tool provides a powerful new way to analyze the brainstem's white matter pathways, which could lead to novel biomarkers and insights into a range of neurological conditions.

The details

The BrainStem Bundle Tool (BSBT) works by tracing fiber bundles that extend from neighboring brain regions into the brainstem, creating a "probabilistic fiber map." A convolutional neural network then combines this map with multiple imaging channels to distinguish and segment eight individual white matter bundles within the brainstem. The tool was trained on 30 diffusion MRI scans from the Human Connectome Project and validated against post-mortem brain dissections. Tests showed BSBT could reliably identify the same bundles in repeat scans of the same patients.

  • The study was published on February 6, 2026 in the Proceedings of the National Academy of Sciences.

The players

Mark Olchanyi

A doctoral candidate in MIT's Medical Engineering and Medical Physics Program and the lead author of the study.

Emery N. Brown

The Edward Hood Taplin Professor of Computational Neuroscience and Medical Engineering at MIT, an anesthesiologist at Massachusetts General Hospital, and a professor at Harvard Medical School. He is also Olchanyi's thesis supervisor and a co-senior author of the study.

Juan Eugenio Iglesias

A co-senior author of the study.

Brian Edlow

A co-senior author of the study.

Got photos? Submit your photos here. ›

What they’re saying

“The brainstem is a region of the brain that is essentially not explored because it is tough to image. People don't really understand its makeup from an imaging perspective. We need to understand what the organization of the white matter is in humans and how this organization breaks down in certain disorders.”

— Mark Olchanyi, Doctoral Candidate, MIT (Mirage News)

“The brainstem is one of the body's most important control centers. Mark's algorithms are a significant contribution to imaging research and to our ability to the understand regulation of fundamental physiology. By enhancing our capacity to image the brainstem, he offers us new access to vital physiological functions such as control of the respiratory and cardiovascular systems, temperature regulation, how we stay awake during the day and how sleep at night.”

— Emery N. Brown, Professor, MIT (Mirage News)

What’s next

The researchers plan to further validate and refine the BrainStem Bundle Tool, with the goal of making it a widely-used diagnostic and research tool for assessing neurological conditions that affect the brainstem.

The takeaway

This new AI-powered imaging tool provides an unprecedented level of detail and insight into the brainstem's complex white matter structure, which could lead to the discovery of novel biomarkers and a better understanding of how various neurological diseases and injuries impact this crucial region of the brain.