Cascaded deep learning for synthesis of 18F-FDG PET from 18F-octreotide: model parameter optimization and performance evaluation

ObjectiveTo investigate a cascaded conditional generative adversarial network (cGAN)–based method for synthesizing 18F-FDG PET images from 18F-octreotide, optimize model parameter configurations, and evaluate the quality of the synthesized images.MethodsImaging data from 71 tumor patients who underwent dual-tracer PET/CT examinations with 18F-FDG and 18F-octreotide between May 2022 and November 2025 were retrospectively collected. A cascaded deep learning architecture (first stage: 3D U-Net; second stage: self-attention 3D V-Net) was employed to evaluate the effects of image preprocessing, resampling size, and patch size on synthesis quality. Three preprocessing strategies (log transformation, normalization, and a combined approach) were compared. Image quality was assessed using five objective metrics (SSIM, PSNR, MSE, MAE, and NMI) and Likert 5-point ratings from three nuclear medicine physicians; liver and lesion-level SUV agreement were further evaluated.ResultsIn the held-out test cohort (n = 14), the combined preprocessing method (log transformation + normalization) significantly outperformed the individual methods (SSIM: 0.8454 ± 0.0328 vs. 0.7831 ± 0.0337 vs. 0.7438 ± 0.0362, P < 0.001). On the identical held-out test cohort (n = 14), the Group 2 parameter configuration (resampling size: 256 × 256 × 512; patch size: 128 × 128 × 128) outperformed Group 1, with an SSIM of 0.8854 ± 0.0455 and a PSNR of 28.15 ± 3.35 dB, representing relative improvements of 19.1% and 83.5%, respectively, over Group 1 (paired-samples t-test, both P < 0.001). The mean Likert score was 4.53 ± 0.19. Quantitative analysis of liver SUVmean showed no significant difference between synthesized and real images (P = 0.967, paired t-test). Lesion-level quantitative analysis demonstrated high agreement between synthetic and real 18F-FDG images, with Pearson correlation coefficients of 1.0000, 0.9995, and 0.9991 for SUVmax and SUVmean (n = 14) and SUVpeak (n = 13), respectively (all P < 0.001), no significant differences on paired t-tests (all P > 0.05), and all Bland–Altman differences within the 95% limits of agreement.ConclusionThe cascaded deep learning model enabled cross-tracer synthesis from 18F-octreotide to 18F-FDG PET images. In this exploratory, single-center pilot cohort, the optimized configuration demonstrated promising quantitative and visual performance, supporting image-synthesis feasibility and potential clinical utility of a single-injection, dual-parameter molecular imaging approach for neuroendocrine tumors. Prospective multicenter validation is warranted before any clinical application.