Particle dose determination method and device based on pet signal nuclide decomposition, equipment, medium and program product
By using a method based on PET signal nuclide decomposition, Monte Carlo particle transport simulation and deep learning model, the PET signal is decomposed to predict the signal ratio of nuclides and the three-dimensional dose distribution. This solves the problem of insufficient accuracy in dose verification in existing radiotherapy and realizes accurate reconstruction and rapid prediction of particle dose distribution.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CAS ION MEDICAL TECHNOLOGY CO LTD
- Filing Date
- 2025-12-19
- Publication Date
- 2026-07-21
AI Technical Summary
Existing radiotherapy dose verification methods cannot reflect the real-time position of the particle beam in the body and the actual dose distribution. They are also greatly affected by factors such as tissue heterogeneity, scattering and nuclear reactions, resulting in insufficient dose delivery accuracy.
A method based on PET signal nuclide decomposition is adopted. CT images are simulated using Monte Carlo particle transport simulation technology, a training dataset is constructed and a deep learning model is trained, and the PET signal is decomposed to predict the signal ratio of nuclides and the three-dimensional dose distribution. The dose is then predicted by combining CT images with beam parameters.
It achieves accurate reconstruction of particle dose distribution, reduces systematic errors caused by signal aliasing, improves the accuracy and interpretability of dose assessment, is applicable to different energy beams, tissue compositions and scanning time conditions, and has fast reasoning ability and good generalization ability.
Smart Images

Figure CN121819183B_ABST