%0 Journal Article
%T Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.
%A Ma KC
%A Mena E
%A Lindenberg L
%A Lay NS
%A Eclarinal P
%A Citrin DE
%A Pinto PA
%A Wood BJ
%A Dahut WL
%A Gulley JL
%A Madan RA
%A Choyke PL
%A Turkbey IB
%A Harmon SA
%J Oncotarget
%V 15
%N 0
%D 2024 May 7
%M 38712741
暂无%R 10.18632/oncotarget.28583
%X <B>OBJECTIVE: </B>Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans.<BR><B>METHODS: </B>A deep learning algorithm based on 2D Pix-2-Pix generative adversarial network (GAN) architecture was developed from paired AC-PET and NAC-PET images. 18F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (n = 183, 60, 59, respectively). Models were trained with two normalization strategies: Standard Uptake Value (SUV)-based and SUV-Nyul-based. Scan-level performance was evaluated by normalized mean square error (NMSE), mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Lesion-level analysis was performed in regions-of-interest prospectively from nuclear medicine physicians. SUV metrics were evaluated using intraclass correlation coefficient (ICC), repeatability coefficient (RC), and linear mixed-effects modeling.<BR><B>RESULTS: </B>Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUVmax and SUVmean were 0.88 and 0.89, which indicated a high correlation between original and AI-generated quantitative imaging markers. Lesion location, density (Hounsfield units), and lesion uptake were all shown to impact relative error in generated SUV metrics (all p < 0.05).<BR><B>CONCLUSIONS: </B>The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.