A multi-scale variational neural network for accelerating motion-compensated whole-heart 3D coronary MR angiography.

PURPOSE To enable fast reconstruction of undersampled motion-compensated whole-heart 3D coronary magnetic resonance angiography (CMRA) by learning a multi-scale variational neural network (MS-VNN) which allows the acquisition of high-quality 1.2 × 1.2 × 1.2 mm isotropic volumes in a short and predictable scan time. METHODS Eighteen healthy subjects and one patient underwent free-breathing 3D CMRA acquisition with variable density spiral-like Cartesian sampling, combined with 2D image navigators for translational motion estimation/compensation. The proposed MS-VNN learns two sets of kernels and activation functions for the magnitude and phase images of the complex-valued data. For the magnitude, a multi-scale approach is applied to better capture the small calibre of the coronaries. Ten subjects were considered for training and validation. Prospectively undersampled motion-compensated data with 5-fold and 9-fold accelerations, from the remaining 9 subjects, were used to evaluate the framework. The proposed approach was compared to Wavelet-based compressed-sensing (CS), conventional VNN, and to an additional fully-sampled (FS) scan. RESULTS The average acquisition time (m:s) was 4:11 for 5-fold, 2:34 for 9-fold acceleration and 18:55 for fully-sampled. Reconstruction time with the proposed MS-VNN was ~14 s. The proposed MS-VNN achieves higher image quality than CS and VNN reconstructions, with quantitative right coronary artery sharpness (CS:43.0%, VNN:43.9%, MS-VNN:47.0%, FS:50.67%) and vessel length (CS:7.4 cm, VNN:7.7 cm, MS-VNN:8.8 cm, FS:9.1 cm) comparable to the FS scan. CONCLUSION The proposed MS-VNN enables 5-fold and 9-fold undersampled CMRA acquisitions with comparable image quality that the corresponding fully-sampled scan. The proposed framework achieves extremely fast reconstruction time and does not require tuning of regularization parameters, offering easy integration into clinical workflow.

[1]  René M. Botnar,et al.  Five‐minute whole‐heart coronary MRA with sub‐millimeter isotropic resolution, 100% respiratory scan efficiency, and 3D‐PROST reconstruction , 2018, Magnetic resonance in medicine.

[2]  Di Guo,et al.  Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator , 2014, Medical Image Anal..

[3]  Debiao Li,et al.  Contrast-enhanced whole-heart coronary magnetic resonance angiography at 3.0-T: a comparative study with X-ray angiography in a single center. , 2009, Journal of the American College of Cardiology.

[4]  Markus Henningsson,et al.  CMRA with 100% navigator efficiency with 3D self navigation and interleaved scanning , 2014, Journal of Cardiovascular Magnetic Resonance.

[5]  Mehmet Akçakaya,et al.  Accelerated isotropic sub‐millimeter whole‐heart coronary MRI: Compressed sensing versus parallel imaging , 2014, Magnetic resonance in medicine.

[6]  Daniel Rueckert,et al.  Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

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

[8]  Thomas Pock,et al.  Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems , 2016, SIAM J. Imaging Sci..

[9]  René M. Botnar,et al.  “Soap‐Bubble” visualization and quantitative analysis of 3D coronary magnetic resonance angiograms , 2002, Magnetic resonance in medicine.

[10]  Guang Yang,et al.  DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction , 2018, IEEE Transactions on Medical Imaging.

[11]  Darius Burschka,et al.  Isotropic Reconstruction of MR Images Using 3D Patch-Based Self-Similarity Learning , 2018, IEEE Transactions on Medical Imaging.

[12]  Daniel K Sodickson,et al.  Assessment of the generalization of learned image reconstruction and the potential for transfer learning , 2019, Magnetic resonance in medicine.

[13]  Jian Sun,et al.  Deep ADMM-Net for Compressive Sensing MRI , 2016, NIPS.

[14]  Markus Henningsson,et al.  Highly efficient respiratory motion compensated free‐breathing coronary mra using golden‐step Cartesian acquisition , 2015, Journal of magnetic resonance imaging : JMRI.

[15]  Morteza Mardani,et al.  Deep Generative Adversarial Neural Networks for Compressive Sensing MRI , 2019, IEEE Transactions on Medical Imaging.

[16]  Jeffrey A. Fessler,et al.  Convolutional Dictionary Learning: Acceleration and Convergence , 2017, IEEE Transactions on Image Processing.

[17]  Markus Henningsson,et al.  Highly efficient nonrigid motion‐corrected 3D whole‐heart coronary vessel wall imaging , 2016, Magnetic resonance in medicine.

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

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

[20]  Tobias Schaeffter,et al.  Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI With Limited Training Data , 2019, IEEE Transactions on Medical Imaging.

[21]  Vahid Tarokh,et al.  Low‐dimensional‐structure self‐learning and thresholding: Regularization beyond compressed sensing for MRI Reconstruction , 2011, Magnetic resonance in medicine.

[22]  Masaaki Ito,et al.  Prognostic value of coronary magnetic resonance angiography for prediction of cardiac events in patients with suspected coronary artery disease. , 2012, Journal of the American College of Cardiology.

[23]  Markus Henningsson,et al.  100% Efficient three‐dimensional coronary MR angiography with two‐dimensional beat‐to‐beat translational and bin‐to‐bin affine motion correction , 2015, Magnetic resonance in medicine.

[24]  Mehmet Akçakaya,et al.  Accelerated contrast‐enhanced whole‐heart coronary MRI using low‐dimensional‐structure self‐learning and thresholding , 2012, Magnetic resonance in medicine.

[25]  Vivek Muthurangu,et al.  Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning–proof of concept in congenital heart disease , 2018, Magnetic resonance in medicine.

[26]  Graham A. Wright,et al.  Factors affecting the correlation coefficient template matching algorithm with application to real-time 2-D coronary artery MR imaging , 2003, IEEE Transactions on Medical Imaging.

[27]  Vahid Tarokh,et al.  Compressed sensing reconstruction for whole‐heart imaging with 3D radial trajectories: A graphics processing unit implementation , 2013, Magnetic resonance in medicine.

[28]  John W. Paisley,et al.  Compressed Sensing MRI Using a Recursive Dilated Network , 2018, AAAI.

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

[30]  Won-Ki Jeong,et al.  Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss , 2017, IEEE Transactions on Medical Imaging.

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

[32]  Osman Ratib,et al.  OsiriX: An Open-Source Software for Navigating in Multidimensional DICOM Images , 2004, Journal of Digital Imaging.

[33]  Claudia Prieto,et al.  Simultaneous bright‐ and black‐blood whole‐heart MRI for noncontrast enhanced coronary lumen and thrombus visualization , 2017, Magnetic resonance in medicine.

[34]  Lei Zhang,et al.  Image Restoration: From Sparse and Low-Rank Priors to Deep Priors [Lecture Notes] , 2017, IEEE Signal Processing Magazine.

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

[36]  E. Wellnhofer,et al.  A prospective study for comparison of MR and CT imaging for detection of coronary artery stenosis. , 2011, JACC. Cardiovascular imaging.

[37]  René M. Botnar,et al.  Technical note: Accelerated nonrigid motion‐compensated isotropic 3D coronary MR angiography , 2017, Medical physics.

[38]  Erich Kobler,et al.  Variational Adversarial Networks for Accelerated MR Image Reconstruction , 2018 .

[39]  Michael J. Black,et al.  Fields of Experts , 2009, International Journal of Computer Vision.

[40]  René M. Botnar,et al.  Detection of Intracoronary Thrombus by Magnetic Resonance Imaging in Patients With Acute Myocardial Infarction , 2011, Circulation.

[41]  Jonathan I. Tamir,et al.  Variable-Density Single-Shot Fast Spin-Echo MRI with Deep Learning Reconstruction by Using Variational Networks. , 2018, Radiology.

[42]  René M. Botnar,et al.  3D whole-heart phase sensitive inversion recovery CMR for simultaneous black-blood late gadolinium enhancement and bright-blood coronary CMR angiography , 2017, Journal of Cardiovascular Magnetic Resonance.

[43]  M. McConnell,et al.  Comparison of respiratory suppression methods and navigator locations for MR coronary angiography. , 1997, AJR. American journal of roentgenology.

[44]  René M. Botnar,et al.  Delayed-enhancement cardiovascular magnetic resonance coronary artery wall imaging: comparison with multislice computed tomography and quantitative coronary angiography. , 2007, Journal of the American College of Cardiology.

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

[46]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[47]  M. McConnell,et al.  Prospective navigator correction of image position for coronary MR angiography. , 1997, Radiology.

[48]  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.

[49]  Thoralf Niendorf,et al.  Toward single breath‐hold whole‐heart coverage coronary MRA using highly accelerated parallel imaging with a 32‐channel MR system , 2006, Magnetic resonance in medicine.

[50]  Holden H. Wu,et al.  High‐resolution variable‐density 3D cones coronary MRA , 2015, Magnetic resonance in medicine.

[51]  Markus Henningsson,et al.  Prospective respiratory motion correction for coronary MR angiography using a 2D image navigator , 2013, Magnetic resonance in medicine.

[52]  Tal Geva,et al.  Three‐dimensional heart locator and compressed sensing for whole‐heart MR angiography , 2016, Magnetic resonance in medicine.