Imaging Epilepsy Sources with Biophysically Constrained Deep Neural Networks
Funded at Carnegie-Mellon University · NIH-11326838 · Data updated 2026-11-12
A new brain-imaging method uses physics-guided deep learning to help doctors pinpoint seizure sources in people with difficult-to-treat focal epilepsy.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Carnegie-Mellon University NIH-funded |
| Lab location | 1 site (Pittsburgh, United States) |
| Project start | June 15, 2023 |
| Project end | May 31, 2027 |
| Funding year | 2026 |
| Award (this year) | $593,749 |
| NIH project number | 5R01NS127849-04 |
| Project ID | NIH-11326838 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults with drug-resistant focal epilepsy being considered for surgical intervention.
✕Less likely to help
Patients whose seizures are not focal or who are not surgical candidates may not benefit directly.
What this research studies
This project aims to create an advanced electrophysiological source imaging tool that combines biophysics with deep neural networks to locate the epileptogenic zone. The method should work with EEG data from patients and provide clear, objective brain source maps without manual tuning for each patient. The goal is to improve the accuracy and reliability of surgical planning for epilepsy by giving clinicians better visualizations of where seizures originate.
Why it matters
Potential benefit: If successful, the approach could lead to more precise brain surgery, potentially increasing seizure freedom and reducing neurological risks for patients.
How similar studies have gone: Prior imaging approaches exist, but this BioDNN method aims to be more objective and user-friendly in clinical settings.
Where this research is happening
-
Carnegie-Mellon University
Pittsburgh, United States Active
Researchers
- Principal investigator: He, Bin — Carnegie-Mellon University
- Study coordinator: He, Bin
Related research
Other NIH-funded projects on the same topics.
-
Scaling Up Task-Shifted Epilepsy Care for Children in Africa
A study to help children with epilepsy in Africa get diagnosed and receive seizure care through trained community health workers.
-
Closed-loop control of interneuron timing to influence seizures and memory in epilepsy
A study tests a brain-quieting system that uses light to precisely time certain brain cells in epilepsy-prone mice to see if this can lessen seizures and improve memory.
-
Epilepsy Data Ecosystem: A Big-Data Sharing Platform for Better Care
A national effort to collect and share large, multi‑modal brain data from people with medication‑resistant epilepsy to speed discoveries and improve treatment options.
-
Exploring epilepsy genes in zebrafish to understand human brain seizures
A study in zebrafish will model human epilepsy genes to help explain how certain brain mutations contribute to seizures.
-
New MRI tools to better plan pediatric epilepsy surgery
A new MRI-based approach helps doctors decide the best time to surgically remove brain tissue in children with difficult-to-control seizures.
-
Sahel Epilepsy Study: finding patterns in epilepsy in rural Africa and its links to genes
A plan to study epilepsy in rural Nigeria to discover how common it is, what factors affect risk, and how genetics may influence it, with results that could improve care for people with epilepsy.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.