5 papers
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
Zhenxuan Zhang, Lipei Zhang, Yanqi Cheng +10
In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially und…
ReDiff: Reliability-Guided Diffusion for Trustworthy Ultra-Low-Field to High-Field MRI Synthesis
Zhenxuan Zhang, Peiyuan Jing, Ruicheng Yuan +9
Low-field to high-field MRI synthesis has emerged as a promising strategy to improve image quality when access to high-field scanners is limited. However, in ultra-low-field settin…
Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis
Zhenxuan Zhang, Peiyuan Jing, Zi Wang +12
Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor sign…
Task-oriented Uncertainty Collaborative Learning for Label-Efficient Brain Tumor Segmentation
Zhenxuan Zhang, Hongjie Wu, Jiahao Huang +5
Multi-contrast magnetic resonance imaging (MRI) plays a vital role in brain tumor segmentation and diagnosis by leveraging complementary information from different contrasts. Each…
Pretext Task Adversarial Learning for Unpaired Low-field to Ultra High-field MRI Synthesis
Zhenxuan Zhang, Peiyuan Jing, Coraline Beitone +4
Given the scarcity and cost of high-field MRI, the synthesis of high-field MRI from low-field MRI holds significant potential when there is limited data for training downstream tas…