Phys Med Biol. 2023 Feb 27. doi: 10.1088/1361-6560/acbf9a. Online ahead of print.
ABSTRACT
Range uncertainty is a major concern affecting delivery precision in proton therapy. The Compton camera (CC)-based prompt-gamma (PG) imaging is a promising technique to provide 3D in-vivo range verification. However, conventional back-projected PG images suffer from severe distortions due to the limited view of CC, significantly limiting its clinical utility. Deep learning has demonstrated effectiveness in enhancing medical images from limited-view measurements. But different from other medical images with abundant anatomical structures, PGs emitted from a proton pencil beam take up an extremely low portion of the 3D image space, presenting both the attention and the imbalance challenge for deep learning. To solve these issues, we proposed a two-tier deep learning-based method with a novel weighted axis-projection loss to generate precise 3D PG images for proton range verification. This method consists of two models: first, a localization model is trained to define a region-of-interest (ROI) in the distorted back-projected PG image that contains the proton pencil beam; second, an enhancement model is trained to restore the true PG emissions with ROI attention. In this study, we simulated proton pencil beams delivered at clinical dose rates and levels in a tissue-equivalent phantom using Monte-Carlo (MC). PG detection with a CC was simulated using the MC-Plus-Detector-Effects model. Images were reconstructed using kernel-weighted-back-projection algorithm, and were then enhanced by the proposed method. Results demonstrated that the method effectively restored the 3D shape of PGs with proton pencil beam range clearly visible in all testing cases. Range errors were within 2 pixels (4 mm) in all directions in most cases at a dose level of 10^9 protons/beam. The method is fully automatic and nearly real-time. Overall, the preliminary study demonstrated the feasibility of the proposed method to generate accurate 3D PG images, providing a powerful tool for high-precision in-vivo range verification of proton therapy.
PMID:36848674 | DOI:10.1088/1361-6560/acbf9a
