DEMO: Deep MR Parametric Mapping with Unsupervised Multi-Tasking Framework
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Compressed sensing (CS) has been investigated in magnetic resonance (MR) parametric mapping to reduce scan time. However, the relatively long reconstruction time restricts its widespread applications in the clinic. Recently, deep learningbased methods have shown great potential in accelerating reconstruction time and improving imaging quality in fast MR imaging, although their adaptation to parametric mapping is still in an early stage. In this paper, we proposed a novel deep learningbased framework DEMO for fast and robust MR parametric mapping. Different from current deep learning-based methods, DEMO trains the network in an unsupervised way, which is more practical given that it is difficult to acquire large fully sampled training data of parametric-weighted images. Specifically, a CS-based loss function is used in DEMO to avoid the necessity of using fully sampled k-space data as the label, thus making it an unsupervised learning approach. DEMO reconstructs parametric weighted images and generates a parametric map simultaneously by unrolling an interaction approach in conventional fast MR parametric mapping, which enables multi-tasking learning. Experimental results showed promising performance of the proposed DEMO framework in quantitative MR T1ρ mapping.
Abstract
Compressed sensing (CS) has been investigated in magnetic resonance (MR) parametric mapping to reduce scan time. However, the relatively long reconstruction time restricts its widespread applications in the clinic. Recently, deep learningbased methods have shown great potential in accelerating reconstruction time and improving imaging quality in fast MR imaging, although their adaptation to parametric mapping is still in an early stage. In this paper, we proposed a novel deep learningbased framework DEMO for fast and robust MR parametric mapping. Different from current deep learning-based methods, DEMO trains the network in an unsupervised way, which is more practical given that it is difficult to acquire large fully sampled training data of parametric-weighted images. Specifically, a CS-based loss function is used in DEMO to avoid the necessity of using fully sampled k-space data as the label, thus making it an unsupervised learning approach. DEMO reconstructs parametric weighted images and generates a parametric map simultaneously by unrolling an interaction approach in conventional fast MR parametric mapping, which enables multi-tasking learning. Experimental results showed promising performance of the proposed DEMO framework in quantitative MR T1ρ mapping.
참고문헌 (47)
- MacKay A, "In vivo visualization of myelin water in brain by magnetic resonance", Magn Reson Med, 31, pp.673~677 (1994)
- Sibley CT, "T1 Mapping in cardiomyopathy at cardiac MR : comparison with endomyocardial biopsy", Radiology, 265, pp.724~732 (2012)
- Duvvuri U, "Human knee: in vivo T1(rho)-weighted MR imaging at 1.5 T--preliminary experience", Radiology, 220, pp.822~826 (2001)
- Regatte RR, "T1rho relaxation mapping in human osteoarthritis(OA)cartilage : comparison of T1rho with T2", J Magn Reson Imaging, 23, pp.547~553 (2006)
- Petzschner FH, "Fast MR parameter mapping using k-t principal component analysis", Magn Reson Med, 66, pp.706~716 (2011)
- Velikina JV, "Accelerating MR parameter mapping using sparsity-promoting regularization in parametric dimension", Magn Reson Med, 70, pp.1263~1273 (2013)
- Zhou Y, "Accelerating T1rho cartilage imaging using compressed sensing with iterative locally adapted support detection and JSENSE", Magn Reson Med, 75, pp.1617~1629 (2016)
- Pandit P, "Accelerated T1rho acquisition for knee cartilage quantification using compressed sensing and data-driven parallel imaging : a feasibility study", Magn Reson Med, 75, pp.1256~1261 (2016)
- Pedersen H, "k-t PCA : temporally constrained k-t BLAST reconstruction using principal component analysis", Magn Reson Med, 62, pp.706~716 (2009)
- Zhang T, "Accelerating parameter mapping with a locally low rank constraint", Magn Reson Med, 73, pp.655~661 (2015)
- Zhao B, "Accelerated MR parameter mapping with low-rank and sparsity constraints", Magn Reson Med, 74, pp.489~498 (2015)
- Block KT, "Model-based iterative reconstruction for radial fast spin-echo MRI", IEEE Trans Med Imaging, 28, pp.1759~1769 (2009)
- Sumpf TJ, "Model-based nonlinear inverse reconstruction for T2 mapping using highly undersampled spin-echo MRI", J Magn Reson Imaging, 34, pp.420~428 (2011)
- Welsh CL, "Model-based reconstruction of undersampled diffusion tensor k-space data", Magn Reson Med, 70, pp.429~440 (2013)
- Tran-Gia J, "Modelbased acceleration of parameter mapping(MAP)for saturation prepared radially acquired data", Magn Reson Med, 70, pp.1524~1534 (2013)
- Zhu Y, "Direct diffusion tensor estimation using a model-based method with spatial and parametric constraints", Med Phys, 44, pp.570~580 (2017)
- Peng X, "Accelerated exponential parameterization of T2 relaxation with modeldriven low rank and sparsity priors(MORASA)", Magn Reson Med, 76, pp.1865~1878 (2016)
- Chu ML, "A single-shot T2mapping protocol based on echo-split gradient-spin-echo acquisition and parametric multiplexed sensitivity encoding based on projection onto convex sets reconstruction", Magn Reson Med, 79, pp.383~393 (2018)
- Zhu Y, "SCOPE : signal compensation for low-rank plus sparse matrix decomposition for fast parameter mapping", Phys Med Biol, 63, pp.185009~ (2018)
- Zhu B, "Image reconstruction by domain-transform manifold learning", Nature, 555, pp.487~492 (2018)
- Quan TM, "Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss", IEEE Trans Med Imaging, 37, pp.1488~1497 (2018)
- Mardani M, "Deep generative adversarial neural networks for compressive sensing MRI", IEEE Trans Med Imaging, 38, pp.167~179 (2019)
- Han Y, "Deep learning with domain adaptation for accelerated projectionreconstruction MR", Magn Reson Med, 80, pp.1189~1205 (2018)
- Lee D, "Deep residual learning for accelerated MRI using magnitude and phase networks", IEEE Trans Biomed Eng, 65, pp.1985~1995 (2018)
- Wang S, "DIMENSION : dynamic MR imaging with both k-space and spatial prior knowledge obtained via multi-supervised network training", NMR Biomed, pp.e4131~ (2019)
- Eo T, "KIKI-net : crossdomain convolutional neural networks for reconstructing undersampled magnetic resonance images", Magn Reson Med, 80, pp.2188~2201 (2018)
- Yang Y, "ADMM-CSNet : a deep learning approach for image compressive sensing", IEEE Trans Pattern Anal Mach Intell, 42, pp.521~538 (2020)
- Hammernik K, "Learning a variational network for reconstruction of accelerated MRI data", Magn Reson Med, 79, pp.3055~3071 (2018)
- Aggarwal HK, "MoDL : model-based deep learning architecture for inverse problems", IEEE Trans Med Imaging, 38, pp.394~405 (2019)
- Schlemper J, "A deep cascade of convolutional neural networks for dynamic MR image reconstruction", IEEE Trans Med Imaging, 37, pp.491~503 (2018)
- Adler J, "Learned primal-dual reconstruction", IEEE Trans Med Imaging, 37, pp.1322~1332 (2018)
- Qin C, "Convolutional recurrent neural networks for dynamic MR image reconstruction", IEEE Trans Med Imaging, 38, pp.280~290 (2019)
- Cai C, "Single-shot T2 mapping using overlapping-echo detachment planar imaging and a deep convolutional neural network", Magn Reson Med, 80, pp.2202~2214 (2018)
- Liu F, "MANTIS : Model-Augmented Neural neTwork with Incoherent k-space Sampling for efficient MR parameter mapping", Magn Reson Med, 82, pp.174~188 (2019)
- Cohen O, "MR fingerprinting Deep RecOnstruction NEtwork(DRONE)", Magn Reson Med, 80, pp.885~894 (2018)
- Yang J, "A fast alternating direction method for TVL1-L2 signal reconstruction from partial Fourier data", IEEE J Sel Top Signal Process, 4, pp.288~297 (2010)
- Lingala SG, "Accelerated dynamic MRI exploiting sparsity and low-rank structure : k-t SLR", IEEE Trans Med Imaging, 30, pp.1042~1054 (2011)
- Cheng J, "Learning reconstruction without ground-truth data: an unsupervised way for fast MR imaging", Proceedings of the 28th Annual Meeting of ISMRM, pp.3634~ (2020)
- Lustig M, "Sparse MRI : the application of compressed sensing for rapid MR imaging", Magn Reson Med, 58, pp.1182~1195 (2007)
- Lustig M, "Compressed sensing MRI", IEEE Signal Process Mag, 25, pp.72~82 (2008)
- Liang D, "Accelerating SENSE using compressed sensing", Magn Reson Med, 62, pp.1574~1584 (2009)
- Liang D, "Deep magnetic resonance image reconstruction : inverse problems meet neural networks", IEEE Signal Process Mag, 37, pp.141~151 (2020)
- Cheng J, "Model learning: primal dual networks for fast MR imaging", Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, 22nd International Conference, pp.21~29 (2019)
- Walsh DO, "Adaptive reconstruction of phased array MR imagery", Magn Reson Med, 43, pp.682~690 (2000)
- Baboli R, "Isotropic morphometry and multicomponent T1 rho mapping of human knee articular cartilage in vivo at 3T", J Magn Reson Imaging, 48, pp.1707~1716 (2018)
- Sharafi A, "Biexponential T1rho relaxation mapping of human knee cartilage in vivo at 3 T", NMR Biomed, 30 (2017)
- Zhu Y, "Bio-SCOPE : fast biexponential T1rho mapping of the brain using signalcompensated low-rank plus sparse matrix decomposition", Magn Reson Med, 83, pp.2092~2106 (2020)