Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN

• Published in: Oncotarget 2024-05, Vol.15 (1), p.288-300
• Main Authors: Ma, Kevin C, Mena, Esther, Lindenberg, Liza, Lay, Nathan S, Eclarinal, Phillip, Citrin, Deborah E, Pinto, Peter A, Wood, Bradford J, Dahut, William L, Gulley, James L, Madan, Ravi A, Choyke, Peter L, Turkbey, Ismail Baris, Harmon, Stephanie A
• Format: Article
• Language: English
• Subjects: Aged; Algorithms; Antigens, Surface - metabolism; Deep Learning; Glutamate Carboxypeptidase II - metabolism; Humans; Image Processing, Computer-Assisted - methods; Male; Middle Aged; Positron Emission Tomography Computed Tomography - methods; Prostatic Neoplasms - diagnostic imaging; Prostatic Neoplasms - pathology; Radiopharmaceuticals; Reproducibility of Results; Research Paper
• ISSN: 1949-2553; 1949-2553
• DOI: 10.18632/oncotarget.28583

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. 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. F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts ( = 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. Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUV and SUV 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 < 0.05). 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.