Fast and accurate calculation of myocardial T<sub>1</sub> and T<sub>2</sub> values using deep learning Bloch equation simulations (DeepBLESS)

Shao, Jiaxin; Ghodrati, Vahid; Nguyen, Kim‐Lien; Hu, Peng

doi:10.1002/mrm.28321

Cited by 31 publications

(38 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another recent technique is DeepBLESS, which is a deep learning reconstruction for simultaneous cardiac T 1 -T 2 mapping using a non-fingerprinting sequence. 21 Similar to this study, it is trained to be robust to arbitrary F I G U R E 4 cMRF T 1 and T 2 maps in 2 healthy subjects at 1.5T. T 1 and T 2 maps are shown corresponding to dictionary-based pattern matching and the deep learning reconstruction, along with difference maps.…”

Section: Discussionmentioning

confidence: 96%

“…Whereas a U‐net may introduce blurring, the network used here operates voxelwise and, therefore, does not induce spatial smoothing. Another recent technique is DeepBLESS, which is a deep learning reconstruction for simultaneous cardiac T 1 –T 2 mapping using a non‐fingerprinting sequence 21 . Similar to this study, it is trained to be robust to arbitrary cardiac rhythms.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T₁ and T₂ mapping

Hamilton

Currey

Rajagopalan

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

To develop a deep learning method for rapidly reconstructing T 1 and T 2 maps from undersampled electrocardiogram (ECG) triggered cardiac magnetic resonance fingerprinting (cMRF) images. Methods: A neural network was developed that outputs T 1 and T 2 values when given a measured cMRF signal time course and cardiac RR interval times recorded by an ECG. Over 8 million cMRF signals, corresponding to 4000 random cardiac rhythms, were simulated for training. The training signals were corrupted by simulated k-space undersampling artifacts and random phase shifts to promote robust learning. The deep learning reconstruction was evaluated in Monte Carlo simulations for a variety of cardiac rhythms and compared with dictionary-based pattern matching in 58 healthy subjects at 1.5T. Results: In simulations, the normalized root-mean-square error (nRMSE) for T 1 was below 1% in myocardium, blood, and liver for all tested heart rates. For T 2 , the nRMSE was below 4% for myocardium and liver and below 6% for blood for all heart rates. The difference in the mean myocardial T 1 or T 2 observed in vivo between dictionary matching and deep learning was 3.6 ms for T 1 and −0.2 ms for T 2. Whereas dictionary generation and pattern matching required more than 4 min per slice, the deep learning reconstruction only required 336 ms. Conclusion: A neural network is introduced for reconstructing cMRF T 1 and T 2 maps directly from undersampled spiral images in under 400 ms and is robust to arbitrary cardiac rhythms, which paves the way for rapid online display of cMRF maps. K E Y W O R D S deep learning, magnetic resonance fingerprinting, neural network, T 1 mapping, T 2 mapping, tissue characterization 2128 | HAMILTON eT AL.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 99%

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T₁ and T₂ mapping

Hamilton

Currey

Rajagopalan

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

show abstract

“…119 For estimating T1 and T2 values using a MOLLI sequence, 120 a DNN was used to approximate a function that received a time series of 1-dimensional signals and time stamps as the inputs, and produced T1 and T2 values as the outputs. 121 DNNs were used for estimating electrical properties tomography (EPT) by approximating functions, which produce EPT from B1+ amplitudes, transceiver phase, and existence of tissue. 122,123 A DNN was also used to approximate a function that produces a map of quantitative susceptibility mapping (QSM) from a local field map.…”

Section: Parameter Mappingmentioning

confidence: 99%

Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview

Takeshima

2022

magn reson med sci

View full text Add to dashboard Cite

This article presents an overview of deep learning (DL) and its applications to function approximation for MR in medicine. The aim of this article is to help readers develop various applications of DL. DL has made a large impact on the literature of many medical sciences, including MR. However, its technical details are not easily understandable for non-experts of machine learning (ML).The first part of this article presents an overview of DL and its related technologies, such as artificial intelligence (AI) and ML. AI is explained as a function that can receive many inputs and produce many outputs. ML is a process of fitting the function to training data. DL is a kind of ML, which uses a composite of many functions to approximate the function of interest. This composite function is called a deep neural network (DNN), and the functions composited into a DNN are called layers. This first part also covers the underlying technologies required for DL, such as loss functions, optimization, initialization, linear layers, non-linearities, normalization, recurrent neural networks, regularization, data augmentation, residual connections, autoencoders, generative adversarial networks, model and data sizes, and complex-valued neural networks.The second part of this article presents an overview of the applications of DL in MR and explains how functions represented as DNNs are applied to various applications, such as RF pulse,

show abstract

“…Therefore, the network can learn the T 1 mapping bias caused by this system imperfection during training, and then generate an accurate T 1 map during network inference without explicitly outputting the B 1 map. This method was also adopted in the previous study 38 . Random

e_{1}

and

e_{2}

values were generated from random Gaussian noise images with the mean value of 0.9 and the variance of 0.05 and filtered with a 20 × 20 mean filter, as

e_{1}

and

e_{2}

maps should be smooth 37,38 .…”

Section: Theorymentioning

confidence: 99%

Deep learning–enhanced T₁ mapping with spatial‐temporal and physical constraint

Wang

et al. 2021

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To propose a reconstruction framework to generate accurate T1 maps for a fast MR T1 mapping sequence. Methods A deep learning–enhanced T1 mapping method with spatial‐temporal and physical constraint (DAINTY) was proposed. This method explicitly imposed low‐rank and sparsity constraints on the multiframe T1‐weighted images to exploit the spatial‐temporal correlation. A deep neural network was used to efficiently perform T1 mapping as well as denoise and reduce undersampling artifacts. Additionally, the physical constraint was used to build a bridge between low‐rank and sparsity constraint and deep learning prior, so the benefits of constrained reconstruction and deep learning can be both available. The DAINTY method was trained on simulated brain data sets, but tested on real acquired phantom, 6 healthy volunteers, and 7 atherosclerosis patients, compared with the narrow‐band k‐space‐weighted image contrast filter conjugate‐gradient SENSE (NK‐CS) method, kt‐sparse‐SENSE (kt‐SS) method, and low‐rank plus sparsity (L+S) method with least‐squares T1 fitting and direct deep learning mapping. Results The DAINTY method can generate more accurate T1 maps and higher‐quality T1‐weighted images compared with other methods. For atherosclerosis patients, the intraplaque hemorrhage can be successfully detected. The computation speed of DAINTY was 10 times faster than traditional methods. Meanwhile, DAINTY can reconstruct images with comparable quality using only 50% of k‐space data. Conclusion The proposed method can provide accurate T1 maps and good‐quality T1‐weighted images with high efficiency.

show abstract

Fast and accurate calculation of myocardial T₁ and T₂ values using deep learning Bloch equation simulations (DeepBLESS)

Cited by 31 publications

References 38 publications

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T₁ and T₂ mapping

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T₁ and T₂ mapping

Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview

Deep learning–enhanced T₁ mapping with spatial‐temporal and physical constraint

Contact Info

Product

Resources

About

Fast and accurate calculation of myocardial T1 and T2 values using deep learning Bloch equation simulations (DeepBLESS)

Cited by 31 publications

References 38 publications

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T1 and T2 mapping

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T1 and T2 mapping

Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview

Deep learning–enhanced T1 mapping with spatial‐temporal and physical constraint

Contact Info

Product

Resources

About

Fast and accurate calculation of myocardial T₁ and T₂ values using deep learning Bloch equation simulations (DeepBLESS)

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T₁ and T₂ mapping

Deep learning reconstruction for cardiac magnetic resonance fingerprinting T₁ and T₂ mapping

Deep learning–enhanced T₁ mapping with spatial‐temporal and physical constraint