A Generative Whole-Brain Segmentation approach for PET/MR imaging via deep learning

Motivation: Segmentation of brain tissues plays a significant role in quantifying and visualizing anatomical structures based on PET/MRI systems. Goal(s): However, most of the current methods focus on MR images with high soft-tissue contrast or employ MR images as a priori information to increase the segmentation accuracy of brain PET images. Approach: In this paper, we proposed a generative whole-brain segmentation model for PET images to achieve automatic and accurate segmentation. Results: The numerical experimental results demonstrate that the proposed method can incorporate multimodal information with the efficient and accurate segmentation performance achieved, allowing for better visualization and quantification results. Impact: This study enables precise brain PET segmentation without MR data, benefiting clinical diagnostics and neuroscience by advancing our understanding of brain metabolism and activity, potentially leading to new therapies and improved patient outcomes.