Deep model-based magnetic resonance parameter mapping network (DOPAMINE) for fast T1 mapping using variable flip angle method

Quantitative tissue characteristics, which provide valuable diagnostic information, can be represented by magnetic resonance (MR) parameter maps using magnetic resonance imaging (MRI); however, a long scan time is necessary to acquire them, which prevents the application of quantitative MR parameter mapping to real clinical protocols. For fast MR parameter mapping, we propose a deep model-based MR parameter mapping network called DOPAMINE that combines a deep learning network with a model-based method to reconstruct MR parameter maps from undersampled multi-channel k-space data. DOPAMINE consists of two networks: 1) an MR parameter mapping network that uses a deep convolutional neural network (CNN) that estimates initial parameter maps from undersampled k-space data (CNN-based mapping), and 2) a reconstruction network that removes aliasing artifacts in the parameter maps with a deep CNN (CNN-based reconstruction) and an interleaved data consistency layer by an embedded MR model-based optimization procedure. We demonstrated the performance of DOPAMINE in brain T1 map reconstruction with a variable flip angle (VFA) model. To evaluate the performance of DOPAMINE, we compared it with conventional parallel imaging, low-rank based reconstruction, model-based reconstruction, and state-of-the-art deep-learning-based mapping methods for three different reduction factors (R = 3, 5, and 7) and two different sampling patterns (1D Cartesian and 2D Poisson-disk). Quantitative metrics indicated that DOPAMINE outperformed other methods in reconstructing T1 maps for all sampling patterns and reduction factors. DOPAMINE exhibited quantitatively and qualitatively superior performance to that of conventional methods in reconstructing MR parameter maps from undersampled multi-channel k-space data. The proposed method can thus reduce the scan time of quantitative MR parameter mapping that uses a VFA model.

[1]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[2]  Taeseong Kim,et al.  KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images , 2018, Magnetic resonance in medicine.

[3]  Andreas K. Maier,et al.  Deep Learning for Magnetic Resonance Fingerprinting: A New Approach for Predicting Quantitative Parameter Values from Time Series , 2017, GMDS.

[4]  T. Pock,et al.  Second order total generalized variation (TGV) for MRI , 2011, Magnetic resonance in medicine.

[5]  Jong Chul Ye,et al.  ${k}$ -Space Deep Learning for Accelerated MRI , 2020, IEEE Transactions on Medical Imaging.

[6]  Christine L. Tardif,et al.  B1 mapping for bias‐correction in quantitative T1 imaging of the brain at 3T using standard pulse sequences , 2017, Journal of magnetic resonance imaging : JMRI.

[7]  Ali Bilgin,et al.  T2 mapping from highly undersampled data by reconstruction of principal component coefficient maps using compressed sensing , 2012, Magnetic resonance in medicine.

[8]  M. Lustig,et al.  Compressed Sensing MRI , 2008, IEEE Signal Processing Magazine.

[9]  Daniel K Sodickson,et al.  Rapid and accurate T2 mapping from multi–spin‐echo data using Bloch‐simulation‐based reconstruction , 2015, Magnetic resonance in medicine.

[10]  Zhi-Pei Liang,et al.  Accelerated MR parameter mapping with low‐rank and sparsity constraints , 2015, Magnetic resonance in medicine.

[11]  Mathews Jacob,et al.  Model-Based Deep Learning for Reconstruction of Joint k-q Under-sampled High Resolution Diffusion MRI , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[12]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[13]  Mark D Does,et al.  Fast T2 mapping with multiple echo, caesar cipher acquisition and model‐based reconstruction , 2015, Magnetic resonance in medicine.

[14]  J. Duerk,et al.  Magnetic Resonance Fingerprinting , 2013, Nature.

[15]  Bo Zhu,et al.  MR fingerprinting Deep RecOnstruction NEtwork (DRONE) , 2017, Magnetic resonance in medicine.

[16]  Stella X. Yu,et al.  Better than real: Complex-valued neural nets for MRI fingerprinting , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[17]  Sairam Geethanath,et al.  Magnetic Resonance Fingerprinting Reconstruction via Spatiotemporal Convolutional Neural Networks , 2018, MLMIR@MICCAI.

[18]  Yonina C. Eldar,et al.  HYDRA: Hybrid Deep Magnetic Resonance Fingerprinting , 2019, Medical physics.

[19]  Mariya Doneva,et al.  Compressed sensing reconstruction for magnetic resonance parameter mapping , 2010, Magnetic resonance in medicine.

[20]  Robin M Heidemann,et al.  Generalized autocalibrating partially parallel acquisitions (GRAPPA) , 2002, Magnetic resonance in medicine.

[21]  A. Lutti,et al.  Establishing intra‐ and inter‐vendor reproducibility of T1 relaxation time measurements with 3T MRI , 2018, Magnetic resonance in medicine.

[22]  Ravinder R Regatte,et al.  Rapid 3D‐T1 mapping of cartilage with variable flip angle and parallel imaging at 3.0T , 2008, Journal of magnetic resonance imaging : JMRI.

[23]  R. Deichmann,et al.  Quantitative T1 and T2 mapping in recurrent glioblastomas under bevacizumab: earlier detection of tumor progression compared to conventional MRI , 2014, Neuroradiology.

[24]  Li Feng,et al.  MANTIS: Model‐Augmented Neural neTwork with Incoherent k‐space Sampling for efficient MR parameter mapping , 2019, Magnetic resonance in medicine.

[25]  Andrea Vedaldi,et al.  Instance Normalization: The Missing Ingredient for Fast Stylization , 2016, ArXiv.

[26]  Yang Yang,et al.  A Myocardial T1-Mapping Framework with Recurrent and U-Net Convolutional Neural Networks , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[27]  Mathews Jacob,et al.  MoDL: Model-Based Deep Learning Architecture for Inverse Problems , 2017, IEEE Transactions on Medical Imaging.

[28]  R. Otazo,et al.  Accelerating 3D‐T1ρ mapping of cartilage using compressed sensing with different sparse and low rank models , 2018, Magnetic resonance in medicine.

[29]  Steen Moeller,et al.  Scan‐specific robust artificial‐neural‐networks for k‐space interpolation (RAKI) reconstruction: Database‐free deep learning for fast imaging , 2018, Magnetic resonance in medicine.

[30]  Kristian Bredies,et al.  Rapid T1 quantification from high resolution 3D data with model‐based reconstruction , 2018, Magnetic resonance in medicine.

[31]  J. Pauly,et al.  Accelerating parameter mapping with a locally low rank constraint , 2015, Magnetic resonance in medicine.

[32]  Jaejun Yoo,et al.  Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks , 2018, IEEE Transactions on Biomedical Engineering.

[33]  Li Feng,et al.  SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction , 2018, ArXiv.

[34]  Daniel Rueckert,et al.  A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[35]  P. Boesiger,et al.  SENSE: Sensitivity encoding for fast MRI , 1999, Magnetic resonance in medicine.

[36]  Dafna Ben Bashat,et al.  T1 Mapping using variable flip angle SPGR data with flip angle correction , 2014, Journal of magnetic resonance imaging : JMRI.

[37]  F. Barkhof,et al.  Whole-brain T1 mapping in multiple sclerosis: global changes of normal-appearing gray and white matter. , 2006, Radiology.

[38]  Jae Myung Kim,et al.  Exploring linearity of deep neural network trained QSM: QSMnet+ , 2019, NeuroImage.

[39]  Thomas Pock,et al.  Learning a variational network for reconstruction of accelerated MRI data , 2017, Magnetic resonance in medicine.

[40]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[41]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Kawin Setsompop,et al.  Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model , 2019, Magnetic resonance in medicine.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[44]  Kawin Setsompop,et al.  Quantitative susceptibility mapping using deep neural network: QSMnet , 2018, NeuroImage.

[45]  Taeseong Kim,et al.  Parallel imaging in time‐of‐flight magnetic resonance angiography using deep multistream convolutional neural networks , 2019, Magnetic resonance in medicine.

[46]  Michael Elad,et al.  ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA , 2014, Magnetic resonance in medicine.

[47]  Christine L. Tardif,et al.  On the accuracy of T1 mapping: Searching for common ground , 2015, Magnetic resonance in medicine.

[48]  Jeffrey A. Fessler,et al.  Dictionary-Free MRI PERK: Parameter Estimation via Regression with Kernels , 2017, IEEE Transactions on Medical Imaging.

[49]  Taejoon Eo,et al.  Accelerating Cartesian MRI by domain-transform manifold learning in phase-encoding direction , 2020, Medical Image Anal..

[50]  Jens Frahm,et al.  Fast T2 Mapping With Improved Accuracy Using Undersampled Spin-Echo MRI and Model-Based Reconstructions With a Generating Function , 2014, IEEE Transactions on Medical Imaging.

[51]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  John Homer,et al.  Driven-equilibrium single-pulse observation of T1 relaxation. A reevaluation of a rapid “new” method for determining NMR spin-lattice relaxation times , 1985 .

[53]  K. T. Block,et al.  Undersampled radial MRI with multiple coils. Iterative image reconstruction using a total variation constraint , 2007, Magnetic resonance in medicine.

[54]  B. Rutt,et al.  Rapid combined T1 and T2 mapping using gradient recalled acquisition in the steady state , 2003, Magnetic resonance in medicine.

[55]  Jason Craft,et al.  Water–fat separation and parameter mapping in cardiac MRI via deep learning with a convolutional neural network , 2019, Journal of magnetic resonance imaging : JMRI.

[56]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[57]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[58]  Ralf Deichmann,et al.  Quantitative mapping of T1 and T2* discloses nigral and brainstem pathology in early Parkinson's disease , 2010, NeuroImage.

[59]  Maria Drangova,et al.  Conditional generative adversarial network for 3D rigid‐body motion correction in MRI , 2019, Magnetic resonance in medicine.

[60]  Jens Frahm,et al.  Model-based myocardial T1 mapping with sparsity constraints using single-shot inversion-recovery radial FLASH cardiovascular magnetic resonance , 2019, Journal of Cardiovascular Magnetic Resonance.

[61]  Bin Yang,et al.  Retrospective correction of motion‐affected MR images using deep learning frameworks , 2019, Magnetic resonance in medicine.

[62]  Jens Frahm,et al.  Model-Based Iterative Reconstruction for Radial Fast Spin-Echo MRI , 2009, IEEE Transactions on Medical Imaging.

[63]  Holden H. Wu,et al.  Recommendations towards standards for quantitative MRI (qMRI) and outstanding needs , 2019, Journal of magnetic resonance imaging : JMRI.

[64]  Bruce R. Rosen,et al.  Image reconstruction by domain-transform manifold learning , 2017, Nature.

[65]  Bejoy Thomas,et al.  Principles, techniques, and applications of T2*-based MR imaging and its special applications. , 2009, Radiographics : a review publication of the Radiological Society of North America, Inc.

[66]  Dong-Hyun Kim,et al.  qMTNet: Accelerated quantitative magnetization transfer imaging with artificial neural networks , 2020, Magnetic resonance in medicine.

[67]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.