Bridging Modalities on the Cortex: Surface-based MRI to PET Translation with a Diffusion Bridge
DB-SUiT is a surface-based diffusion bridge generating synthetic FDG-PET from MRI on the cortical manifold, lifting dementia classification 14.2% over MRI.
Researchers introduce DB-SUiT, a surface-based diffusion bridge framework for MRI-to-PET translation operating natively on the folded cortical geometry, built around a conditional Spherical U-shaped vision Transformer (SUiT) with spherical convolutional encoders and bottleneck Transformers. On dementia classification, synthesized PET surfaces improved performance by 14.2% over MRI and 11.3% over volumetric PET, and a blinded reader study achieved 85.5% diagnostic accuracy versus 95.2% for real PET. The model generalized to an external cohort including an unseen dementia subtype without retraining, with code released on GitHub.
- Conditional Spherical U-shaped vision Transformer preserves cortical surface topology
- Synthetic PET surfaces improve dementia classification by 14.2% over MRI
- Blinded reader study: 85.5% accuracy vs 95.2% for real PET
- Generalizes cross-cohort to an unseen dementia subtype without retraining
- AI models
- DB-SUiT
From the original article
1 min read at arxiv.orgCortical hypometabolism measured by Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a highly sensitive biomarker for dementia diagnosis. However, high costs, radiation exposure, and limited accessibility constrain its clinical utility.
By Yitong Li · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.