Whole-Body Image-to-Image Translation for a Virtual Scanner in a Healthcare Digital Twin
This work addresses the challenge of anatomical heterogeneity in whole-body image translation for healthcare Digital Twins, enabling accurate virtual PET scans from CT data to improve patient care and accessibility, though it is incremental as it builds on existing GAN methods.
The paper tackled the problem of generating whole-body PET images from CT scans to reduce radiation exposure and costs, achieving state-of-the-art results by using a framework that segments CT images into regions and applies district-specific GANs for translation, with Pix2Pix yielding superior metrics in quantitative evaluations.
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.