paper-with-me

Papers

Learning Bloch Simulations for MR Fingerprinting by Invertible Neural Networks

2020-08-10 · Fabian Balsiger, Alain Jungo, Olivier Scheidegger, Benjamin Marty, Mauricio Reyes

Magnetic resonance fingerprinting (MRF) enables fast and multiparametric MR imaging. Despite fast acquisition, the state-of-the-art reconstruction of MRF based on dictionary matching is slow and lacks scalability. To overcome these limitations, neural network (NN) approaches estimating MR parameters from fingerprints have been proposed recently. Here, we revisit NN-based MRF reconstruction to jointly learn the forward process from MR parameters to fingerprints and the backward process from fingerprints to MR parameters by leveraging invertible neural networks (INNs). As a proof-of-concept, we perform various experiments showing the benefit of learning the forward process, i.e., the Bloch simulations, for improved MR parameter estimation. The benefit especially accentuates when MR parameter estimation is difficult due to MR physical restrictions. Therefore, INNs might be a feasible alternative to the current solely backward-based NNs for MRF reconstruction.

📄 PDF Abstract BibTeX arXiv:2008.04139

Code (1)

fabianbalsiger/mrf-reconstruction-mlmir2020 공식 구현 tf

Tasks

Magnetic Resonance Fingerprintingparameter estimation

Similar Papers 제목 키워드 기반

Accurate parameter estimation using scan-specific unsupervised deep learning for relaxometry and MR fingerprinting

2021-12-07 · Mengze Gao, Huihui Ye, Tae Hyung Kim, Zijing Zhang 외

We propose an unsupervised convolutional neural network (CNN) for relaxation parameter estimation. This network incorporates signal relaxation and Bloch simulations while taking advantage of residual learning and spatial…

parameter estimation

Game of Learning Bloch Equation Simulations for MR Fingerprinting

2020-04-05 · Mingrui Yang, Yun Jiang, Dan Ma, Bhairav B. Mehta 외

Purpose: This work proposes a novel approach to efficiently generate MR fingerprints for MR fingerprinting (MRF) problems based on the unsupervised deep learning model generative adversarial networks (GAN). Methods: The …

Deep Image Priors for Magnetic Resonance Fingerprinting with pretrained Bloch-consistent denoising autoencoders

2024-07-29 · Perla Mayo, Matteo Cencini, Ketan Fatania, Carolin M. Pirkl 외

The estimation of multi-parametric quantitative maps from Magnetic Resonance Fingerprinting (MRF) compressed sampled acquisitions, albeit successful, remains a challenge due to the high underspampling rate and artifacts …

DenoisingImage ReconstructionMagnetic Resonance Fingerprinting

An off-the-grid approach to multi-compartment magnetic resonance fingerprinting

2020-11-23 · Mohammad Golbabaee, Clarice Poon

We propose a novel numerical approach to separate multiple tissue compartments in image voxels and to estimate quantitatively their nuclear magnetic resonance (NMR) properties and mixture fractions, given magnetic resona…

Magnetic Resonance Fingerprinting

Deep Unrolling for Magnetic Resonance Fingerprinting

2022-01-23 · Dongdong Chen, Mike E. Davies, Mohammad Golbabaee

Magnetic Resonance Fingerprinting (MRF) has emerged as a promising quantitative MR imaging approach. Deep learning methods have been proposed for MRF and demonstrated improved performance over classical compressed sensin…

compressed sensingMagnetic Resonance FingerprintingRolling Shutter Correction