Synthetic CT generation from non-attenuation corrected PET images for whole-body PET imaging

• Type of Material: Article
• Authors: Xue Dong, Emory University; Tonghe Wang, Emory University; Yang Lei, Emory University; Kristin Higgins, Emory University; Tian Liu, Emory University; Walter Curran Jr, Emory University; Hui Mao, Emory University; Jonathon Nye, Emory University; Xiaofeng Yang, Emory University
• Language: English
• Date: 2019-11-01
• Publisher: IOP PUBLISHING LTD
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: 2019
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1088/1361-6560/ab4eb7
• Title of Journal or Parent Work: PHYSICS IN MEDICINE AND BIOLOGY
• Volume: 64
• Issue: 21
• Start Page: 215016
• End Page: 215016
• Grant/Funding Information: This research was supported in part by the National Cancer Institute of the National Institutes of Health Award Number R01CA215718 and the Emory Winship Cancer Institute pilot grant.
• Keywords: QUANTITATIVE-EVALUATION; Science & Technology; GUIDED ATTENUATION; MRI; CHALLENGES; Radiology, Nuclear Medicine & Medical Imaging; attenuation correction; SEGMENTATION; deep learning; PET/MRI; Life Sciences & Biomedicine; Engineering; Engineering, Biomedical; ATLAS; Technology; CLASSIFICATION; whole-body PET
• Research Categories: Health Sciences, Radiology; Engineering, General; Engineering, Biomedical

Abstract

Attenuation correction (AC) of PET/MRI faces challenges including inter-scan motion, image artifacts such as truncation and distortion, and erroneous transformation of structural voxel-intensities to PET mu-map values. We propose a deep-learning-based method to derive synthetic CT (sCT) images from non-attenuation corrected PET (NAC PET) images for AC on whole-body PET/MRI imaging. A 3D cycle-consistent generative adversarial networks (CycleGAN) framework was employed to synthesize CT images from NAC PET. The method learns a transformation that minimizes the difference between sCT, generated from NAC PET, and true CT. It also learns an inverse transformation such that cycle NAC PET image generated from the sCT is close to true NAC PET image. A self-attention strategy was also utilized to identify the most informative component and mitigate the disturbance of noise. We conducted a retrospective study on a total of 119 sets of whole-body PET/CT, with 80 sets for training and 39 sets for testing and evaluation. The whole-body sCT images generated with proposed method demonstrate great resemblance to true CT images, and show good contrast on soft tissue, lung and bony tissues. The mean absolute error (MAE) of sCT over true CT is less than 110 HU. Using sCT for whole-body PET AC, the mean error of PET quantification is less than 1% and normalized mean square error (NMSE) is less than 1.4%. Average normalized cross correlation on whole body is close to one, and PSNR is larger than 42 dB. We proposed a deep learning-based approach to generate sCT from whole-body NAC PET for PET AC. sCT generated with proposed method shows great similarity to true CT images both qualitatively and quantitatively, and demonstrates great potential for whole-body PET AC in the absence of structural information.