Whole-Body Image-to-Image Translation for a Virtual Scanner in a Healthcare Digital Twin

TL;DR

This work tackles the challenge of translating whole-body CT scans to synthetic PET images by addressing anatomical heterogeneity through district-specific models. It segments the body into four districts and trains dedicated 3D GANs (Pix2Pix and CycleGAN) for each district, followed by patch-based stitching to reconstruct a full-body PET volume. Across district, lesion, and oncological-condition evaluations, district-specific GANs, particularly Pix2Pix, consistently outperform a baseline whole-body GAN, achieving lower MAE and higher PSNR/SSIM. The approach supports healthcare Digital Twins by enabling accurate, virtual PET representations from CT data with potential reductions in radiation exposure and cost, and is extensible to finer segmentation and explainable AI enhancements in the future.

Abstract

Generating positron emission tomography (PET) images from computed tomography (CT) scans via deep learning offers a promising pathway to reduce radiation exposure and costs associated with PET imaging, improving patient care and accessibility to functional imaging. Whole-body image translation presents challenges due to anatomical heterogeneity, often limiting generalized models. We propose a framework that segments whole-body CT images into four regions-head, trunk, arms, and legs-and uses district-specific Generative Adversarial Networks (GANs) for tailored CT-to-PET translation. Synthetic PET images from each region are stitched together to reconstruct the whole-body scan. Comparisons with a baseline non-segmented GAN and experiments with Pix2Pix and CycleGAN architectures tested paired and unpaired scenarios. Quantitative evaluations at district, whole-body, and lesion levels demonstrated significant improvements with our district-specific GANs. Pix2Pix yielded superior metrics, ensuring precise, high-quality image synthesis. By addressing anatomical heterogeneity, this approach achieves state-of-the-art results in whole-body CT-to-PET translation. This methodology supports healthcare Digital Twins by enabling accurate virtual PET scans from CT data, creating virtual imaging representations to monitor, predict, and optimize health outcomes.

Figures (2)

• Figure 1: Pipeline of the presented methodology.
• Figure 2: Comparison of real and synthetic PET images across different anatomical districts.