Synthesizing [18F]PSMA-1007 PET bone images from CT images with GAN for early detection of prostate cancer bone metastases: a pilot validation study

• Published in: BMC cancer Vol. 25; no. 1; pp. 907 - 9
• Main Authors: Chai, Liming, Yao, Xiaolong, Yang, Xiaofeng, Na, Renhua, Yan, Wei, Jiang, Mingzheng, Zhu, Haixu, Sun, Canwen, Dai, Zeqiang, Yang, Xueying
• Format: Journal Article
• Language: English
• Published: London BioMed Central 21.05.2025; BioMed Central Ltd; BMC
• Subjects: [18F]PSMA-1007; Aged; Artificial intelligence; Biomedical and Life Sciences; Biomedicine; Bone cancer; Bone metastases; Bone Neoplasms - diagnostic imaging; Bone Neoplasms - secondary; Bones; Cancer; Cancer Research; Clinical medicine; Complications and side effects; Computed tomography; CT imaging; Deep Learning; Diagnosis; Early Detection of Cancer - methods; Fluorine; Fluorine Radioisotopes; Health aspects; Health Promotion and Disease Prevention; Humans; Image synthesis; Lesions; Male; Medical imaging; Medical imaging equipment; Medicine/Public Health; Metastases; Metastasis; Middle Aged; Neural networks; Niacinamide - analogs & derivatives; Oligopeptides; Oncology; Oncology, Experimental; Patients; PET imaging; PET/CT; Pilot Projects; Positron Emission Tomography Computed Tomography - methods; Prostate; Prostate cancer; Prostatic Neoplasms - diagnostic imaging; Prostatic Neoplasms - pathology; Radiation; Radiation hazards; Radiopharmaceuticals; Retrospective Studies; Risk factors; Surgical Oncology; China; Germany; Xinjiang China; Deep learning; F]PSMA-1007; Image synthesis; PET/CT; [; Prostate cancer; Bone metastases; [18F]PSMA-1007
• ISSN: 1471-2407; 1471-2407
• DOI: 10.1186/s12885-025-14301-x

Background [ 18 F]FDG PET/CT scan combined with [ 18 F]PSMA-1007 PET/CT scan is commonly conducted for detecting bone metastases in prostate cancer (PCa). However, it is expensive and may expose patients to more radiation hazards. This study explores deep learning (DL) techniques to synthesize [ 18 F]PSMA-1007 PET bone images from CT bone images for the early detection of bone metastases in PCa, which may reduce additional PET/CT scans and relieve the burden on patients. Methods We retrospectively collected paired whole-body (WB) [ 18 F]PSMA-1007 PET/CT images from 152 patients with clinical and pathological diagnosis results, including 123 PCa and 29 cases of benign lesions. The average age of the patients was 67.48 ± 10.87 years, and the average lesion size was 8.76 ± 15.5 mm. The paired low-dose CT and PET images were preprocessed and segmented to construct the WB bone structure images. 152 subjects were randomly stratified into training, validation, and test groups in the number of 92:41:19. Two generative adversarial network (GAN) models—Pix2pix and Cycle GAN—were trained to synthesize [ 18 F]PSMA-1007 PET bone images from paired CT bone images. The performance of two synthesis models was evaluated using quantitative metrics of mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index metrics (SSIM), as well as the target-to-background ratio (TBR). Results The results of DL-based image synthesis indicated that the synthesis of [ 18 F]PSMA-1007 PET bone images from low-dose CT bone images was highly feasible. The Pix2pix model performed better with an SSIM of 0.97, PSNR of 44.96, MSE of 0.80, and MAE of 0.10, respectively. The TBRs of bone metastasis lesions calculated on DL-synthesized PET bone images were highly correlated with those of real PET bone images (Pearson’s r  > 0.90) and had no significant differences ( p  < 0.05). Conclusions It is feasible to generate synthetic [ 18 F]PSMA-1007 PET bone images from CT bone images by using DL techniques with reasonable accuracy, which can provide information for early detection of PCa bone metastases.