DIReCT++ synthesizes high-fidelity 18F-AV-45 and 18F-FDG PET images from MRI using a domain-informed rectified flow model modulated by BiomedCLIP, enabling precise MCI stratification when combined with MRI.
Swin-unet:Unet-likepuretransformer for medical image segmentation.ArXiv Prepr
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Precision Synthesis of Multi-Tracer PET via VLM-Modulated Rectified Flow for Stratifying Mild Cognitive Impairment
DIReCT++ synthesizes high-fidelity 18F-AV-45 and 18F-FDG PET images from MRI using a domain-informed rectified flow model modulated by BiomedCLIP, enabling precise MCI stratification when combined with MRI.