Fast 3D whole-body occupational dose estimation in interventional radiology using physics-informed deep learning.

Occupational radiation exposure in interventional radiology is spatially heterogeneous and inadequately captured by conventional point-based dosimetry. This study proposes a physics-informed deep learning framework for fast prediction of three-dimensional (3D) physician dose distributions from scattered radiation. Graphics processing unit (GPU)-accelerated Monte Carlo (MC) simulations were performed using the GPU Geant4-based Monte Carlo Simulation platform to generate 3D dose maps under varying X-ray energies, C-arm angulations, and physician configurations. These data were used to train residual and transformer-based 3D U-Net architectures. Model performance was evaluated using voxel-wise error metrics, gamma analysis, and clinically relevant personal dose equivalents. The residual 3D U-Net achieved the best performance, with mean absolute errors below 0.06 nGy and gamma passing rates exceeding 90%. Predicted personal dose equivalents showed close agreement with MC references, enabling anatomically resolved dose estimation for superficial and deep tissues. Average inference time was approximately 0.2 s per sample. This framework enables fast, accurate, and anatomically detailed estimation of occupational dose, addressing key limitations of conventional dosimetry. The results support its potential integration into real-time radiation awareness and guidance systems for improved operator radiation protection in interventional practice.