A physics- and spatially informed diffusion model accelerates Monte Carlo–level dose estimation for CyberKnife radiotherapy using planning CT and anatomical data.
Key Details
- 1The PSIDMViT model integrates planning CT, finite-size pencil beam dose distributions, and distance maps for dose prediction.
- 2Tested retrospectively in 251 CyberKnife patients (117 head-and-neck, 76 lung, 58 liver).
- 3Achieved 3D Gamma passing rates of 98.0% for head-and-neck, 94.0% for lung, and 95.0% for liver cases (1%/1 mm/10% criterion).
- 4Reduced dose computation time from about 1 hour to 18 minutes per plan versus Monte Carlo methods.
- 5Outperformed conventional finite-size pencil beam and baseline deep-learning models in accuracy.
- 6External and multi-institutional validation remains needed.
Why It Matters
Fast, Monte Carlo–consistent dose prediction can make accurate, individualized radiotherapy planning more feasible in clinical routine, improving workflow efficiency for high-precision treatments. This approach illustrates how integrating imaging, physics, and AI can address major clinical bottlenecks.
Source
EurekAlert
Related News
•EurekAlert
NYU AI Model Improves 5-Year Breast Cancer Risk Prediction via 3D Mammograms
NYU researchers developed an AI model using longitudinal 3D mammograms that outperforms single-scan and 2D-based tools in predicting 5-year breast cancer risk.
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.