Feasibility of synthetic computed tomography generated with an adversarial network for multi-sequence magnetic resonance-based brain radiotherapy. (10th December 2019)

• Record Type: Journal Article
• Authors: Koike, Yuhei; Akino, Yuichi; Sumida, Iori; Shiomi, Hiroya; Mizuno, Hirokazu; Yagi, Masashi; Isohashi, Fumiaki; Seo, Yuji; Suzuki, Osamu; Ogawa, Kazuhiko
• Is Part Of: Journal of radiation research. Volume 61:Number 1(2020:Jan.)
• Page Start: 92
• Page End: 103
• Publication Date: 2019-12-10
• Subjects: synthetic computed tomography -- deep learning -- generative adversarial network -- dose calculation -- treatment planning; Radiology, Medical -- Periodicals; Radiobiology -- Periodicals; Radiation -- Periodicals; 616.0757
• DOI: 10.1093/jrr/rrz063
• Languages: English
• ISSNs: 0449-3060

Abstract

ABSTRACT: The aim of this work is to generate synthetic computed tomography (sCT) images from multi-sequence magnetic resonance (MR) images using an adversarial network and to assess the feasibility of sCT-based treatment planning for brain radiotherapy. Datasets for 15 patients with glioblastoma were selected and 580 pairs of CT and MR images were used. T1-weighted, T2-weighted and fluid-attenuated inversion recovery MR sequences were combined to create a three-channel image as input data. A conditional generative adversarial network (cGAN) was trained using image patches. The image quality was evaluated using voxel-wise mean absolute errors (MAEs) of the CT number. For the dosimetric evaluation, 3D conformal radiotherapy (3D-CRT) and volumetric modulated arc therapy (VMAT) plans were generated using the original CT set and recalculated using the sCT images. The isocenter dose and dose–volume parameters were compared for 3D-CRT and VMAT plans, respectively. The equivalent path length was also compared. The mean MAEs for the whole body, soft tissue and bone region were 108.1 ± 24.0, 38.9 ± 10.7 and 366.2 ± 62.0 hounsfield unit, respectively. The dosimetric evaluation revealed no significant difference in the isocenter dose for 3D-CRT plans. The differences in the dose received by 2% of the volume ( D 2% ), D 50% and D 98% relative to the prescribed dose were <1.0%. The overall equivalent path length was shorter than that for real CT by 0.6 ± 1.9 mm. A treatment planning study using generated sCT detected only small, clinically negligible differences. These findings demonstrated the feasibility of generating sCT images for MR-only radiotherapy from multi-sequence MR images using cGAN.