{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["15"],"submitter":["Ma KC"],"pubmed_abstract":["<h4>Purpose</h4>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.<h4>Methods</h4>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. <sup>18</sup>F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (<i>n</i> = 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.<h4>Results</h4>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<sub>max</sub> and SUV<sub>mean</sub> 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 <i>p</i> < 0.05).<h4>Conclusion</h4>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."],"journal":["Oncotarget"],"pagination":["288-300"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11075367"],"repository":["biostudies-literature"],"pubmed_title":["Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN."],"pmcid":["PMC11075367"],"pubmed_authors":["Citrin DE","Dahut WL","Wood BJ","Ma KC","Choyke PL","Eclarinal P","Pinto PA","Madan RA","Mena E","Gulley JL","Lindenberg L","Harmon SA","Lay NS","Turkbey IB"],"additional_accession":[]},"is_claimable":false,"name":"Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.","description":"<h4>Purpose</h4>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.<h4>Methods</h4>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. <sup>18</sup>F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (<i>n</i> = 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.<h4>Results</h4>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<sub>max</sub> and SUV<sub>mean</sub> 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 <i>p</i> < 0.05).<h4>Conclusion</h4>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.","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 May","modification":"2026-06-01T17:26:24.163Z","creation":"2026-04-08T14:12:41.118Z"},"accession":"S-EPMC11075367","cross_references":{"pubmed":["38712741"],"doi":["10.18632/oncotarget.28583"]}}