Modality-projection universal model for comprehensive full-body medical imaging segmentation
Open Access
- 24 October 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-14
Abstract
The integration of deep learning in medical imaging has significantly advanced diagnostic, therapeutic, and research outcomes. However, applying universal models across multiple modalities remains challenging due to inherent inter-modality variability. Here we present the Modality Projection Universal Model (MPUM), trained on 861 subjects, which dynamically adapts to diverse imaging modalities through a modality-projection strategy. MPUM achieves state-of-the-art, whole-body organ segmentation, providing rapid localization for computer-aided diagnosis and precise anatomical quantification to support clinical decision-making. A controller-based convolutional layer further enables saliency map visualization, enhancing model interpretability for clinical use. Beyond segmentation, MPUM reveals metabolic correlations along the brain-body axis and between distinct brain regions, providing insights into systemic and physiological interactions from a whole-body perspective. Here we show that this universal framework accelerates diagnosis, facilitates large-scale imaging analysis, and bridges anatomical and metabolic information, enabling discovery of cross-organ disease mechanisms and advancing integrative brain-body research.Keywords
All Related Versions
This publication has 65 references indexed in Scilit:
- Influence of diabetes mellitus on metabolic networks in lung cancer patients: an analysis using dynamic total-body PET/CT imagingEuropean Journal of Nuclear Medicine and Molecular Imaging, 2025
- LUCIDA: Low-Dose Universal-Tissue CT Image Domain Adaptation for Medical Segmentation2024
- CT-Based Brain Ventricle Segmentation via Diffusion Schrödinger Bridge without target domain ground truths2024
- Voxel Scene Graph for Intracranial Hemorrhage2024
- Individual‐specific metabolic network based on 18F‐FDG PET revealing multi‐level aberrant metabolisms in Parkinson's diseaseHuman Brain Mapping, 2024
- UniSeg: A Prompt-Driven Universal Segmentation Model as Well as A Strong Representation Learner2023
- Identifying the individual metabolic abnormities from a systemic perspective using whole-body PET imagingEuropean Journal of Nuclear Medicine and Molecular Imaging, 2022
- Individual brain metabolic connectome indicator based on Kullback-Leibler Divergence Similarity Estimation predicts progression from mild cognitive impairment to Alzheimer’s dementiaEuropean Journal of Nuclear Medicine and Molecular Imaging, 2020
- Dementia spectrum disorders: lessons learnt from decades with PET researchJournal of Neural Transmission, 2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015