Research Article: Cascaded deep learning for synthesis of 18 F-FDG PET from 18 F-octreotide: model parameter optimization and performance evaluation
Abstract:
To investigate a cascaded conditional generative adversarial network (cGAN)–based method for synthesizing 18 F-FDG PET images from 18 F-octreotide, optimize model parameter configurations, and evaluate the quality of the synthesized images.
Imaging data from 71 tumor patients who underwent dual-tracer PET/CT examinations with 18 F-FDG and 18 F-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.
In 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 18 F-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.
The cascaded deep learning model enabled cross-tracer synthesis from 18 F-octreotide to 18 F-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.
Introduction:
Positron emission tomography (PET) is a sophisticated molecular imaging modality with indispensable applications in cancer diagnosis, staging, therapeutic monitoring, and prognostic evaluation. 18 F-fluorodeoxyglucose ( 18 F-FDG), currently the most commonly used PET tracer, enables the detection of malignancies by assessing tissue glucose metabolism. Nevertheless, 18 F-FDG PET has several intrinsic limitations: certain tumors exhibit low metabolic activity and consequently low FDG uptake, which may reduce…
Read more