Learning-Based Stopping Power Mapping on Dual Energy CT for Proton Radiation Therapy

• Type of Material: Article
• Authors: Tonghe Wang, Emory University; Yang Lei, Emory University; Joseph Harms, Emory University; Beth Ghavidel, Emory University; Liyong Lin, Emory University; Jonathan J Beitler, Emory University; Mark McDonald, Emory University; Walter J Curran, Emory University; Tian Liu, Emory University; Xiaofeng Yang, Emory University
• Language: English
• Date: 2020-03-20
• Publisher: Cornell University
• Publication Version: Preprint (Prior to Peer Review)
• Copyright Statement: Cornell University 2020
• Final Published Version (URL): https://arxiv.org/abs/2003.09058v1
• Title of Journal or Parent Work: Medical Physics
• ISSN: 0094-2405
• Grant/Funding Information: This research is supported in part by the National Cancer Institute of the National Institutes of Health under Award Number R01CA215718, and Emory Winship Pilot Grant.
• Keywords: Medical Physics; proton therapy; stopping power; Dual-energy CT; machine learning
• Research Categories: Health Sciences, Radiology

Abstract

Purpose: Dual-energy CT (DECT) has been used to derive relative stopping power (RSP) map by obtaining the energy dependence of photon interactions. The DECT-derived RSP maps could potentially be compromised by image noise levels and the severity of artifacts when using physics-based mapping techniques, which would affect subsequent clinical applications. This work presents a noise-robust learning-based method to predict RSP maps from DECT for proton radiation therapy. Methods: The proposed method uses a residual attention cycle-consistent generative adversarial (CycleGAN) network. CycleGAN were used to let the DECT-to-RSP mapping be close to a one-to-one mapping by introducing an inverse RSP-to-DECT mapping. We retrospectively investigated 20 head-and-neck cancer patients with DECT scans in proton radiation therapy simulation. Ground truth RSP values were assigned by calculation based on chemical compositions, and acted as learning targets in the training process for DECT datasets, and were evaluated against results from the proposed method using a leave-one-out cross-validation strategy. Results: The predicted RSP maps showed an average normalized mean square error (NMSE) of 2.83% across the whole body volume, and average mean error (ME) less than 3% in all volumes of interest (VOIs). With additional simulated noise added in DECT datasets, the proposed method still maintained a comparable performance, while the physics-based stoichiometric method suffered degraded inaccuracy from increased noise level. The average differences in DVH metrics for clinical target volumes (CTVs) were less than 0.2 Gy for D95% and Dmax with no statistical significance. Conclusion: These results strongly indicate the high accuracy of RSP maps predicted by our machine-learning-based method and show its potential feasibility for proton treatment planning and dose calculation.