activity
20182021
most citedLORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space

44 citations · 46 across the 4 of their papers we have counts for

collaborators

9 papers

physics.med-ph2021

A Technical Primer on the Physical Modeling of Diffusion-Encoded Magnetic Resonance Experiments: A Random Process Perspective

Justin P. Haldar

Diffusion-encoded magnetic resonance (MR) experiments can provide important insights into the microstructural characteristics of a variety of biological tissues and other fluid- or…

eess.SP20202 cited

PALMNUT: An Enhanced Proximal Alternating Linearized Minimization Algorithm with Application to Separate Regularization of Magnitude and Phase

Yunsong Liu, Justin P. Haldar

We introduce a new algorithm for complex image reconstruction with separate regularization of the image magnitude and phase. This optimization problem is interesting in many differ…

eess.IV2020

3D Phase Retrieval at Nano-Scale via Accelerated Wirtinger Flow

Zalan Fabian, Justin Haldar, Richard Leahy +1

Imaging 3D nano-structures at very high resolution is crucial in a variety of scientific fields. However, due to fundamental limitations of light propagation we can only measure th…

eess.IV2019

Optimal Sampling & Reconstruction: Theory and Applications

Justin P. Haldar

The optimization of MRI data sampling and image reconstruction methods has been a priority for the MRI community since the very early days of the field. Designing an "optimal" meth…

eess.IV2019

Fast Sub-millimeter Diffusion MRI using gSlider-SMS and SNR-Enhancing Joint Reconstruction

Justin P. Haldar, Qiuyun Fan, Kawin Setsompop

We evaluate a new approach for achieving diffusion MRI data with high spatial resolution, large volume coverage, and fast acquisition speed. A recent method called gSlider-SMS enab…

eess.IV201944 cited

LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space

Tae Hyung Kim, Pratyush Garg, Justin P. Haldar

We propose and evaluate a new MRI reconstruction method named LORAKI that trains an autocalibrated scan-specific recurrent neural network (RNN) to recover missing k-space data. Met…