MRI-based treatment planning for liver stereotactic body radiotherapy: validation of a deep learning-based synthetic CT generation method

• Type of Material: Article
• Authors: Yingzi Liu, Emory University; Yang Lei, Emory University; Tonghe Wang, Emory University; Oluwatosin Kayode, Emory University; Sibo Tian, Emory University; Tian Liu, Emory University; Pretesh Patel, Emory University; Walter Curran Jr, Emory University; Lei Ren, Duke University; Xiaofeng Yang, Emory University
• Language: English
• Date: 2019-01-01
• Publisher: BRITISH INST RADIOLOGY
• Publication Version: Final Published Version
• Copyright Statement: © 2019 The Authors. Published by the British Institute of Radiology
• Final Published Version (URL): http://dx.doi.org/10.1259/bjr.20190067
• Title of Journal or Parent Work: BRITISH JOURNAL OF RADIOLOGY
• Volume: 92
• Issue: 1100
• Start Page: 20190067
• End Page: 20190067
• Grant/Funding Information: This research is supported in part by the National Cancer Institute of the National Institutes of Health under Award Number R01CA215718 (Yang) and R01CA184173 (Ren), the Dunwoody Golf Club Prostate Cancer Research Award (Yang), a philanthropic award provided by the Winship Cancer Institute of Emory University.
• Keywords: Radiology, Nuclear Medicine & Medical Imaging; Life Sciences & Biomedicine; GEOMETRIC DISTORTION; FEASIBILITY; NECK; IMAGES; BRAIN MRI; Science & Technology; PSEUDO-CT; HEAD
• Research Categories: Biology, Neuroscience; Health Sciences, Radiology; Physics, Electricity and Magnetism

Abstract

Objective: The purpose of this work is to develop and validate a learning-based method to derive electron density from routine anatomical MRI for potential MRI-based SBRT treatment planning. Methods: We proposed to integrate dense block into cycle generative adversarial network (GAN) to efec-tively capture the relationship between the CT and MRI for CT synthesis. A cohort of 21 patients with co-registered CT and MR pairs were used to evaluate our proposed method by the leave-one-out cross-validation. Mean absolute error, peaksignal-to-noise ratio and normalized cross-correlation were used to quantify the imaging diferences between the synthetic CT (sCT) and CT. The accuracy of Hounsfeld unit (HU) values in sCT for dose calculation was evaluated by comparing the dose distribution in sCT-based and CT-based treatment planning. Clinically relevant dose-volume histogram metrics were then extracted from the sCT-based and CT-based plans for quantitative comparison. results: The mean absolute error, peaksignal-to-noise ratio and normalized cross-correlation of the sCT were 72.87 ± 18.16 HU, 22.65 ± 3.63 dB and 0.92 ± 0.04, respectively. No signifcant diferences were observed in the majority of the planning target volume and organ at risk dose-volume histogram metrics ( p > 0.05). The average pass rate of analysis was over 99% with 1%/1 mm acceptance criteria on the coronal plane that intersects with isocenter. Conclusion: The image similarity and dosimetric agreement between sCT and original CT warrant further development of an MRI-only workfow for liver stereo-tactic body radiation therapy. advances in knowledge: This work is the frst deep-learning-based approach to generating abdominal sCT through dense-cycle-GAN. This method can successfully generate the small bony structures such as the rib bones and is able to predict the HU values for dose calculation with comparable accuracy to reference CT images.