8X Accelerated Intervertebral Disc Compositional Evaluation with Recurrent Encoder-Decoder Deep Learning Network

Ablation Studies in 3D Encoder-Decoder Networks for Brain MRI-to-PET Cerebral Blood Flow Transformation

Accelerated cardiac T1 mapping using attention-gated neural networks

Accelerating 3D MULTIPLEX MRI Reconstruction with Deep Learning

Accelerating perfusion quantification using ASL-MRI with a neural network based forward model

Author:Yechuan Zhang  Michael Chappell  

Session Type:Oral  

Session Date:Tuesday, 18 May 2021  

Topic:Machine Learning for Quantitative Imaging  

Session Name:Machine Learning for Quantitative Imaging  

Program Number:0335  

Room Session:Concurrent 1  

Institution:University of Nottingham  University of Oxford  

Accurate quantitative parameter maps reconstruction method for tsDESPOT using Low Rank approximated Unet ADMM

Automated quantitative evaluation of deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI

Bidirectional Translation Between Multi-Contrast Images and Multi-Parametric Maps Using Deep Learning

BUDA-STEAM: A rapid parameter estimation method for T1, T2, M0, B0 and B1 using three-90° pulse sequence

Comparison of deformable registration techniques for real-time MR-based motion correction in PET/MR

CONN-NLM: a novel CONNectome-based Non-Local Means filter for PET-MRI denoising

Correction of Image Distortions Arising from RF Encoding with Nonlinear Fields

Deep Learning Enhanced T1 Mapping and Reconstruction Framework with Spatial-temporal and Physical Constraint

Deep learning for fast 3D low field MRI

Deep Learning Reconstruction of MR Fingerprinting for simultaneous T1, T2* mapping and generation of WM, GM and WM lesion probability maps

Deep unrolled network with optimal sampling pattern to accelerate multi-echo GRE acquisition for quantitative susceptibility mapping

DeepTSE-T2: Deep learning-powered T2 mapping with B1+ estimation using a product double-echo Turbo Spin Echo sequence

Development and Evaluation of a software for Parametric Patlak mapping using PET/MRI input function (CALIPER).

Development of a Numerical Bloch Solver for Low-Field Pulse Sequence Modeling

Fast and Accurate Modeling of Transient-state Sequences by Recurrent Neural Networks

Author:Hongyan Liu  Oscar van der Heide  Cornelis van den Berg  Alessandro Sbrizzi  

Session Type:Oral  

Session Date:Tuesday, 18 May 2021  

Topic:Machine Learning for Quantitative Imaging  

Session Name:Machine Learning for Quantitative Imaging  

Program Number:0329  

Room Session:Concurrent 1  

Institution:UMC Utrecht  

First-Principle Image SNR Synthesis Depending on Field Strength

Free-breathing Abdomen T2 mapping via Single-shot Multiple Overlapping-echo Acquisition and Deep Neural Network Reconstruction

Free-Breathing MR-based Attenuation Correction for Whole-Body PET/MR Exams

Generalizing Ultra-low-dose PET/MRI Networks Across Radiotracers: From Amyloid to Tau

Global and Local Deep Dictionary Learning Network for Accelerating the Quantification of Myelin Water Content

Author:Quan Chen  Huajun She  Zhijun Wang  Yiping Du  

Session Type:Digital Poster  

Session Date:Tuesday, 18 May 2021  

Topic:Machine Learning for Quantitative Imaging  

Session Name:Machine Learning for Quantitative Imaging  

Program Number:2163  

Room Session:Concurrent 1  

Institution:Shanghai Jiao Tong University  

High resolution PET image denoising using anatomical priors by K-nearest neighborhood method in the feature space

Impact of motion on simultaneously acquired PET/MRI of myocardial infarcted heart.

In-Vivo evaluation of high resolution T2 mapping using Bloch simulations and MP-PCA image denoising

Learned Proximal Convolutional Neural Network for Susceptibility Tensor Imaging

Low-field MR imaging using multiplicative regularization

MoG-QSM: A Model-basedGenerative Adversarial DeepLearning Network for Quantitative Susceptibility Mapping

MR-based motion correction and anatomical guidance for improved PET image reconstruction in cardiac PET-MR imaging

Myelin water fraction determination from relaxation times and proton density through deep learning neural network

qMTNet+: artificial neural network with residual connection for accelerated quantitative magnetization transfer imaging

Rapid MR Parametric Mapping using Deep Learning

A self-supervised deep learning approach to synthesize weighted images and T1, T2, and PD parametric maps based on MR physics priors

Self-supervised Deep Learning for Rapid Quantitative Imaging

Author:Fang Liu  Li Feng  

Session Type:Oral  

Session Date:Tuesday, 18 May 2021  

Topic:Machine Learning for Quantitative Imaging  

Session Name:Machine Learning for Quantitative Imaging  

Program Number:0332  

Room Session:Concurrent 1  

Institution:Harvard Medical School  Icahn School of Medicine at Mount Sinai  

Synthesizing large scale datasets for training deep neural networks in quantitative mapping of myelin waterfraction

Track-To-Learn: A general framework for tractography with deep reinforcement learning

Using an ANN to estimate Initial Values for Mapping of the Oxygen Extraction Fraction with combined QSM and qBOLD