Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SlicerTMS: Real-Time Visualization of Transcranial Magnetic Stimulation for Mental Health Treatment

Loraine Franke, Tae Young Park, Jie Luo, Yogesh Rathi, Steve Pieper, Lipeng Ning, Daniel Haehn

TL;DR

A real-time visualization system for Transcranial Magnetic Stimulation (TMS), a non-invasive neuromodulation technique for treating various brain disorders and mental health diseases, that rapidly predicts electric field distributions in 0.2 seconds for precise and effective brain stimulation.

Abstract

We present a real-time visualization system for Transcranial Magnetic Stimulation (TMS), a non-invasive neuromodulation technique for treating various brain disorders and mental health diseases. Our solution targets the current challenges of slow and labor-intensive practices in treatment planning. Integrating Deep Learning (DL), our system rapidly predicts electric field (E-field) distributions in 0.2 seconds for precise and effective brain stimulation. The core advancement lies in our tool's real-time neuronavigation visualization capabilities, which support clinicians in making more informed decisions quickly and effectively. We assess our system's performance through three studies: First, a real-world use case scenario in a clinical setting, providing concrete feedback on applicability and usability in a practical environment. Second, a comparative analysis with another TMS tool focusing on computational efficiency across various hardware platforms. Lastly, we conducted an expert user study to measure usability and influence in optimizing TMS treatment planning. The system is openly available for community use and further development on GitHub: \url{https://github.com/lorifranke/SlicerTMS}.

SlicerTMS: Real-Time Visualization of Transcranial Magnetic Stimulation for Mental Health Treatment

TL;DR

A real-time visualization system for Transcranial Magnetic Stimulation (TMS), a non-invasive neuromodulation technique for treating various brain disorders and mental health diseases, that rapidly predicts electric field distributions in 0.2 seconds for precise and effective brain stimulation.

Abstract

We present a real-time visualization system for Transcranial Magnetic Stimulation (TMS), a non-invasive neuromodulation technique for treating various brain disorders and mental health diseases. Our solution targets the current challenges of slow and labor-intensive practices in treatment planning. Integrating Deep Learning (DL), our system rapidly predicts electric field (E-field) distributions in 0.2 seconds for precise and effective brain stimulation. The core advancement lies in our tool's real-time neuronavigation visualization capabilities, which support clinicians in making more informed decisions quickly and effectively. We assess our system's performance through three studies: First, a real-world use case scenario in a clinical setting, providing concrete feedback on applicability and usability in a practical environment. Second, a comparative analysis with another TMS tool focusing on computational efficiency across various hardware platforms. Lastly, we conducted an expert user study to measure usability and influence in optimizing TMS treatment planning. The system is openly available for community use and further development on GitHub: \url{https://github.com/lorifranke/SlicerTMS}.
Paper Structure (12 sections, 4 figures, 2 tables)

This paper contains 12 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Implementation
  3. Neuronavigation Visualization Component
  4. Deep Learning Pipeline for E-Field Prediction
  5. AR Component with WebXR
  6. Real-world Use Case Scenario
  7. Performance Evaluation
  8. Technical Performance Experiments of SlicerTMS
  9. Comparative Performance Analysis
  10. Expert User Study
  11. Discussion
  12. Conclusion and Future Work

Figures (4)

  • Figure 1: a) Components: Neural Network (left) predicts E-field and transfers it to SlicerTMS via OpenIGTLinkIF. WebSocket supports browser connection to WebXR to interact with visualization in AR (right). b) Neuronavigation Visualization: Incoming magnetic vector field images are transformed according to coil position, then overlayed with the brain mesh. Consistent rotation of vector direction in each voxel as rigid transform is critical. The 3D coil can be moved interactively while sending new coil positioning matrices back to neural network generating a new field.
  • Figure 2: Gallery of example visualizations: Brain Mesh vs. Volume Rendering vs. Fiber Tractography in SlicerTMS. E-field in 3D on gray matter with a figure-8 coil (Left), E-field on MRI volumetric data (Center), and E-field on full-brain tractography fibers with adjustable ROI and 2D slices in various directions (Right).
  • Figure 3: TMS Clinic and Output in SlicerTMS. Researcher administering treatment by standing behind patient and adjusting the TMS coil to target the right brain areas, meanwhile SlicerTMS is running in with a remote connection to server to predict the electric field in real-time on the brain mesh shown in the UI.
  • Figure 4: SlicerTMS vs. SimNIBS E-Field Visualization.Left: SlicerTMS E-field with movable Figure 8 coil, color legend indicates strength of E-field and axes with directions. Right: SimNIBS E-field on brain surface with coil direction (green handle).