Motivation: The medical imaging diagnosis of Alzheimer's disease (AD) often relies on multi-modal images, yet obtaining these can be challenging due to high costs and short-lived tracers. Goal(s): This research aims to address this limitation by developing a generative model that utilizes MRI to enhance the transformation from 18F-FDG PET to 18F-AV-45 PET images. Approach: Using MRI as an enhancement modality, our approach enables faster acquisition of images to aid clinical diagnosis. Results: The experimental results demonstrate the effectiveness and superiority of our method, offering a viable solution for more accessible and efficient AD diagnosis. Impact: This method significantly enhances diagnostic efficiency in Alzheimer's disease by enabling quick, cost-effective image generation, reducing reliance on expensive, short-lived tracers, and providing accessible support for clinicians, ultimately advancing multi-modal medical imaging practices in neurodegenerative diseases.
Fu et al. (2025) studied this question.