Improving Quantitative Magnetic Resonance Imaging Using Deep Learning

Abstract

Deep learning methods have shown promising results for accelerating quantitative musculoskeletal (MSK) magnetic resonance imaging (MRI) for T2 and T1ρ relaxometry. These methods have been shown to improve musculoskeletal tissue segmentation on parametric maps, allowing efficient and accurate T2 and T1ρ relaxometry analysis for monitoring and predicting MSK diseases. Deep learning methods have shown promising results for disease detection on quantitative MRI with diagnostic performance superior to conventional machine-learning methods for identifying knee osteoarthritis.

Keywords

deep learning - magnetic resonance imaging - quantitative imaging - rapid imaging - relaxometry

Financial Disclosure

Fang Liu receives funding support from National Institutes of Health grants NIH P41-EB022544 and R01-CA165221.

Publikationsverlauf

Artikel online veröffentlicht:
29. September 2020

• References

• 1 LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521 (7553): 436-444
• 2 Wernick MN, Yang Y, Brankov JG, Yourganov G, Strother SC. Machine learning in medical imaging. IEEE Signal Process Mag 2010; 27 (04) 25-38
• 3 Giger ML. Machine learning in medical imaging. J Am Coll Radiol 2018; 15 (3 Pt B): 512-520
• 4 Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics 2017; 37 (02) 505-515
• 5 Abadi M, Agarwal A, Barham P. , et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems. Available at: https://arxiv.org/pdf/1603.04467.pdf . Accessed May 20, 2020
• 6 Litjens G, Kooi T, Bejnordi BE. , et al. A survey on deep learning in medical image analysis. Med Image Anal 2017; 42: 60-88
• 7 Shen D, Wu G, Suk H-I. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017; 19: 221-248
• 8 Suzuki K. Overview of deep learning in medical imaging. Radiological Phys Technol 2017; 10 (03) 257-273
• 9 Liu F, Zhou Z, Jang H, Samsonov A, Zhao G, Kijowski R. Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging. Magn Reson Med 2018; 79 (04) 2379-2391
• 10 Zhou Z, Zhao G, Kijowski R, Liu F. Deep convolutional neural network for segmentation of knee joint anatomy. Magn Reson Med 2018; 80 (06) 2759-2770
• 11 Norman B, Pedoia V, Majumdar S. Use of 2D U-Net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry. Radiology 2018; 288 (01) 177-185
• 12 Liu F. SUSAN: Segment unannotated image structure using adversarial network. Magn Reson Med 2019; 81 (05) 3330-3345
• 13 Byra M, Wu M, Zhang X. , et al. Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-Net with transfer learning. Magn Reson Med 2020; 83 (03) 1109-1122
• 14 Deniz CM, Xiang S, Hallyburton RS. , et al. Segmentation of the proximal femur from MR images using deep convolutional neural networks. Sci Rep 2018; 8 (01) 16485
• 15 Gaj S, Yang M, Nakamura K, Li X. Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks. Magn Reson Med 2019 ; December 2 (Epub ahead of print)
• 16 Liu F, Samsonov A, Chen L, Kijowski R, Feng L. SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction. Magn Reson Med 2019; 82 (05) 1890-1904
• 17 Hammernik K, Klatzer T, Kobler E. , et al. Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med 2018; 79 (06) 3055-3071
• 18 Liu F, Feng L, Kijowski R. MANTIS: Model-Augmented Neural neTwork with Incoherent k-space Sampling for efficient MR parameter mapping. Magn Reson Med 2019; 82 (01) 174-188
• 19 Kijowski R, Liu F, Caliva F, Pedoia V. Deep learning for lesion detection, progression, and prediction of musculoskeletal disease. J Magn Reson Imaging 2019 ; November 25 (Epub ahead of print)
• 20 Li X, Benjamin Ma C, Link TM. , et al. In vivo T(1rho) and T(2) mapping of articular cartilage in osteoarthritis of the knee using 3 T MRI. Osteoarthritis Cartilage 2007; 15 (07) 789-797
• 21 Zarins ZA, Bolbos RI, Pialat JB. , et al. Cartilage and meniscus assessment using T1rho and T2 measurements in healthy subjects and patients with osteoarthritis. Osteoarthritis Cartilage 2010; 18 (11) 1408-1416
• 22 Menezes NM, Gray ML, Hartke JR, Burstein D. T2 and T1rho MRI in articular cartilage systems. Magn Reson Med 2004; 51 (03) 503-509
• 23 Duvvuri U, Reddy R, Patel SD, Kaufman JH, Kneeland JB, Leigh JS. T1rho-relaxation in articular cartilage: effects of enzymatic degradation. Magn Reson Med 1997; 38 (06) 863-867
• 24 Liu F, Choi KW, Samsonov A. , et al. Articular cartilage of the human knee joint: In vivo multicomponent T2 analysis at 3.0 T. Radiology 2015; 277 (02) 477-488
• 25 Eckstein F, Burstein D, Link TM. Quantitative MRI of cartilage and bone: degenerative changes in osteoarthritis. NMR Biomed 2006; 19 (07) 822-854
• 26 Liu F, Chaudhary R, Hurley SA. , et al. Rapid multicomponent T2 analysis of the articular cartilage of the human knee joint at 3.0T. J Magn Reson Imaging 2014; 39 (05) 1191-1197
• 27 Kim M, Chan Q, Anthony MP, Cheung KMC, Samartzis D, Khong PL. Assessment of glycosaminoglycan distribution in human lumbar intervertebral discs using chemical exchange saturation transfer at 3 T: feasibility and initial experience. NMR Biomed 2011; 24 (09) 1137-1144
• 28 Du J, Carl M, Bydder M, Takahashi A, Chung CB, Bydder GM. Qualitative and quantitative ultrashort echo time (UTE) imaging of cortical bone. J Magn Reson 2010; 207 (02) 304-311
• 29 Bae WC, Chen PC, Chung CB, Masuda K, D'Lima D, Du J. Quantitative ultrashort echo time (UTE) MRI of human cortical bone: correlation with porosity and biomechanical properties. J Bone Miner Res 2012; 27 (04) 848-857
• 30 Liu F, Kijowski R. Deep learning in musculoskeletal imaging. Clin. Radiol. 2019; 1: 83-94
• 31 Griswold MA, Jakob PM, Heidemann RM. , et al. Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn Reson Med 2002; 47 (06) 1202-1210
• 32 Sodickson DK, Manning WJ. Simultaneous acquisition of spatial harmonics (SMASH): fast imaging with radiofrequency coil arrays. Magn Reson Med 1997; 38 (04) 591-603
• 33 Jakob PM, Griswold MA, Edelman RR, Sodickson DK. AUTO-SMASH: a self-calibrating technique for SMASH imaging. SiMultaneous Acquisition of Spatial Harmonics. MAGMA 1998; 7 (01) 42-54
• 34 Samsonov AA, Kholmovski EG, Parker DL, Johnson CR. POCSENSE: POCS-based reconstruction for sensitivity encoded magnetic resonance imaging. Magn Reson Med 2004; 52 (06) 1397-1406
• 35 Lustig M, Donoho D, Pauly JM. Sparse MRI: The application of compressed sensing for rapid MR imaging. Magn Reson Med 2007; 58 (06) 1182-1195
• 36 Lustig M, Pauly JM. SPIRiT: Iterative self-consistent parallel imaging reconstruction from arbitrary k-space. Magn Reson Med 2010; 64 (02) 457-471
• 37 Kijowski R, Rosas H, Samsonov A, King K, Peters R, Liu F. Knee imaging: Rapid three-dimensional fast spin-echo using compressed sensing. J Magn Reson Imaging 2017; 45 (06) 1712-1722
• 38 Zibetti MVW, Sharafi A, Otazo R, Regatte RR. Compressed sensing acceleration of biexponential 3D-T_1ρ relaxation mapping of knee cartilage. Magn Reson Med 2019; 81 (02) 863-880
• 39 Bratke G, Rau R, Weiss K. , et al. Accelerated MRI of the lumbar spine using compressed sensing: quality and efficiency. J Magn Reson Imaging 2019; 49 (07) e164-e175
• 40 Yi J, Lee YH, Hahn S, Albakheet SS, Song HT, Suh JS. Fast isotropic volumetric magnetic resonance imaging of the ankle: acceleration of the three-dimensional fast spin echo sequence using compressed sensing combined with parallel imaging. Eur J Radiol 2019; 112: 52-58
• 41 Chaudhari AS, Kogan F, Pedoia V, Majumdar S, Gold GE, Hargreaves BA. Rapid knee MRI acquisition and analysis techniques for imaging osteoarthritis. J Magn Reson Imaging 2019 ; November 21 (Epub ahead of print)
• 42 Garwood ER, Recht MP, White LM. Advanced imaging techniques in the knee: benefits and limitations of new rapid acquisition strategies for routine knee MRI. AJR Am J Roentgenol 2017; 209 (03) 552-560
• 43 Li H, Yang M, Kim J. , et al. Ultra-fast simultaneous T1rho and T2 mapping using deep learning. Paper presented at: ISMRM Annual Meeting; August 8–13, 2020
• 44 Zibetti MVW, Sharafi A, Hammernik K, Knoll F, Regatte RR. Comparing learned variational networks and compressed sensing for T1rho mapping of knee cartilage. Paper presented at: ISMRM Workshop on Machine Learning, Part II; May 18, 2018; Washington, DC
• 45 Zibetti MVW, Sharafi A, Hammernik K, Knoll F, Regatte RR. Variational Networks for Accelerating Biexponential 3D–T1rho Mapping of Knee Cartilage. Paper presented at: ISMRM Annual Meeting; August 8–13, 2020
• 46 Chaudhari AS, Fang Z, Kogan F. , et al. Super-resolution musculoskeletal MRI using deep learning. Magn Reson Med 2018; 80 (05) 2139-2154
• 47 Chaudhari AS, Stevens KJ, Wood JP. , et al. Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers. J Magn Reson Imaging 2020; 51 (03) 768-779
• 48 Chaudhari AS, Black MS, Eijgenraam S. , et al. Five-minute knee MRI for simultaneous morphometry and T₂ relaxometry of cartilage and meniscus and for semiquantitative radiological assessment using double-echo in steady-state at 3T. J Magn Reson Imaging 2018; 47 (05) 1328-1341
• 49 Pedoia V, Majumdar S, Link TM. Segmentation of joint and musculoskeletal tissue in the study of arthritis. MAGMA 2016; 29 (02) 207-221
• 50 Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. Available at: https://arxiv.org/pdf/1511.00561.pdf
• 51 Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF. , eds. Medical Image Computing and Computer-Assisted Intervention. MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015. Proceedings, Part III. Cham, Switzerland: Springer; 2015: 234-241
• 52 Kellgren JH, Lawrence JS. Radiological assessment of osteo-arthrosis. Ann Rheum Dis 1957; 16 (04) 494-502
• 53 Liu F, Zhou Z, Samsonov A. , et al. Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection. Radiology 2018; 289 (01) 160-169
• 54 Liu F, Guan B, Zhou Z. , et al. Fully automated diagnosis of anterior cruciate ligament tears on knee MR images by using deep learning. Radiol Artif Intell 2019; 1 (03) 180091
• 55 Pedoia V, Norman B, Mehany SN, Bucknor MD, Link TM, Majumdar S. 3D convolutional neural networks for detection and severity staging of meniscus and PFJ cartilage morphological degenerative changes in osteoarthritis and anterior cruciate ligament subjects. J Magn Reson Imaging 2019; 49 (02) 400-410
• 56 Roblot V, Giret Y, Bou Antoun M. , et al. Artificial intelligence to diagnose meniscus tears on MRI. Diagn Interv Imaging 2019; 100 (04) 243-249
• 57 Bien N, Rajpurkar P, Ball RL. , et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet. PLOS Med 2018; 15: e1002699
• 58 Pedoia V, Lee J, Norman B, Link TM, Majumdar S. Diagnosing osteoarthritis from T₂ maps using deep learning: an analysis of the entire Osteoarthritis Initiative baseline cohort. Osteoarthritis Cartilage 2019; 27 (07) 1002-1010
• 59 Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. 2016 ; ArXiv.org/abs/1608.06993
• 60 Pedoia V, Li X, Su F, Calixto N, Majumdar S. Fully automatic analysis of the knee articular cartilage T1ρ relaxation time using voxel-based relaxometry. J Magn Reson Imaging 2016; 43 (04) 970-980