Lipeng Ning

This paper introduces DIFFUSE, a framework for joint k-q-TE image reconstruction in diffusion MRI, showing improved error reduction and multi-contrast reconstruction.

ROVER-dMRI improves high-SNR whole-brain mesoscale diffusion MRI with reduced scan time and preserved fiber details.

This paper introduces FCG, a technique that corrects spatiotemporal-varying phase errors in EPI using an MLP, improving image quality on high-performance systems.

MaxEnt-DTD estimates diffusion tensor distributions from dMRI data, providing reliable joint fiber-orientation and microstructure analysis.

This study compares multi-echo and time-division multiplexing sequences for relaxation-diffusion MRI, finding TDM provides more accurate T2 estimates and microstructure measures with faster acquisition.

This paper introduces a domain-agnostic MR reconstruction framework using a randomly weighted neural network that achieves performance comparable to state-of-the-art methods with minimal training data.

This paper introduces a method to model combined relaxation diffusion MRI data by characterizing b-value dependent T2 relaxation rates to improve neurite microstructure characterization.

This paper develops a deep learning method to segment brain tissue from diffusion MRI without anatomical registration, achieving high accuracy on both HCP and clinical data.

This paper introduces REDIM, a method to compute joint moments of relaxation-diffusion to characterize neural microstructure, showing it can distinguish fiber bundles with similar orientations but different relaxation rates.

This paper presents a diffusion MRI harmonization method that removes scanner-specific effects across sites while preserving inter-subject variability, validated on two clinical cohorts.