Advanced Surface-Guided Radiation Therapy
Transforming surface guided radiation therapy with low-cost RGB cameras and neural networks for real-time patient tracking and internal anatomy estimation.
Back to ProjectsProject Overview
Surface-Guided Radiation Therapy (SGRT) is an advanced technique that uses optical surface imaging to monitor patient positioning and motion during radiation treatment. Our research focuses on developing a next-generation SGRT system using low-cost RGB cameras and advanced neural networks.
The Challenge
Traditional SGRT systems rely on expensive, proprietary hardware with limited adaptability. These systems often cannot account for internal anatomy movement based on external surface changes, leading to potential targeting inaccuracies during treatment.
Our Approach
We are developing an innovative system that combines:
- Low-cost RGB cameras for external surface tracking
- Neural networks for real-time patient pose estimation
- Deformation models that correlate external surfaces with internal anatomy
- Machine learning algorithms that predict internal organ movement based on external surface changes
Expected Outcomes
Our advanced SGRT system aims to:
- Improve access to simulation-free treatment for ~50% of patients currently excluded
- Reduce the number of required clinic visits by leveraging diagnostic CTs
- Enhance treatment precision by modeling skeletal and soft tissue shifts
- Lower the cost of SGRT implementation, making it accessible to more clinics
Current Status
This project is in active development with promising initial results. We have successfully demonstrated the feasibility of using RGB cameras for surface tracking and are now refining our neural network models for internal anatomy estimation.
Research Team
Dr. David Thomas
Principal Investigator
William Frantz
PhD Student