Share this content in WeChat
Research progress of osteoarthritis of the knee using MRI: based on deep learning
GAO Xi  XIE Xi  WANG Wentao 

Cite this article as: GAO X, XIE X, WANG W T. Research progress of osteoarthritis of the knee using MRI: based on deep learning[J]. Chin J Magn Reson Imaging, 2023, 14(6): 192-197. DOI:10.12015/issn.1674-8034.2023.06.035.

[Abstract] Currently, the prevalence rate of knee osteoarthritis (KOA) is increasing year by year, and the evaluation of KOA is mainly conducted by MRI. However, the structure of the knee joint itself is complex. At present, clinical experts rely on their experience to diagnose and distinguish knee joint MRI images, which not only has low efficiency but may also result in low accuracy due to the difficulty of identifying tiny lesions with the naked eye. In recent years, deep learning has developed rapidly and has made significant achievements in the field of computer vision, such as image segmentation and synthesis. People have begun to use deep learning methods to process complex medical images such as MRI, CT, and X-ray images, thus improving the accuracy and efficiency of clinical diagnosis and treatment. Nowadays, many relevant studies have introduced deep learning to assist in the diagnosis of KOA by processing knee joint MRI images. We summarized and organized these studies, summarized the research progress of deep learning in KOA MRI image segmentation, reconstruction, synthesis, and analyzed the limitations of existing studies in this paper, in order to provide new ideas for the diagnosis and treatment of KOA in the future.
[Keywords] deep learning;magnetic resonance imaging;osteoarthritis of the knee;review;neural networks;image segmentation;image synthesis

GAO Xi1*   XIE Xi2   WANG Wentao2  

1 Fourth Department of Orthopaedics, the First Affiliated Hospital of Heilongjiang University of Traditional Chinese Medicine, Harbin 150040, China

2 First Clinical Medical College, Heilongjiang University of Chinese Medicine, Harbin 150040, China

Corresponding author: Gao X, E-mail:

Conflicts of interest   None.

ACKNOWLEDGMENTS Natural Science Foundation of Heilongjiang Province (No. LH2021H092).
Received  2023-01-07
Accepted  2023-05-06
DOI: 10.12015/issn.1674-8034.2023.06.035
Cite this article as: GAO X, XIE X, WANG W T. Research progress of osteoarthritis of the knee using MRI: based on deep learning[J]. Chin J Magn Reson Imaging, 2023, 14(6): 192-197. DOI:10.12015/issn.1674-8034.2023.06.035.

LIU Z C, ZHUANG Y, FANG L F, et al. Breakthrough of extracellular vesicles in pathogenesis, diagnosis and treatment of osteoarthritis[J]. Bioact Mater, 2023, 22: 423-452. DOI: 10.1016/j.bioactmat.2022.10.012.
VERONESE N, HONVO G, BRUYÈRE O, et al. Knee osteoarthritis and adverse health outcomes: an umbrella review of meta-analyses of observational studies[J]. Aging Clin Exp Res, 2023, 35(2): 245-252. DOI: 10.1007/s40520-022-02289-4.
LUO P, HU W, JIANG L, et al. Evaluation of articular cartilage in knee osteoarthritis using hybrid multidimensional MRI[J/OL]. Clin Radiol, 2022, 77(7): e518-e525 [2023-01-06]. DOI: 10.1016/j.crad.2022.03.002.
DUAN L T, WANG Q, HU M H, et al. Comparison and analysis on the diagnostic value of ultrasound, X-ray and MRI for knee-joint osteoarthritis[J]. Chin J Ultrasound Med, 2016, 32(3)255-258. DOI: 10.3969/j.issn.1002-0101.2016.03.022
ALMAJALID R, ZHANG M, SHAN J. Fully automatic knee bone detection and segmentation on three-dimensional MRI[J/OL]. Diagnostics (Basel), 2022, 12(1): 123 [2023-01-06]. DOI: 10.3390/diagnostics12010123.
LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. DOI: 10.1038/nature14539.
SUGANYADEVI S, SEETHALAKSHMI V, BALASAMY K. A review on deep learning in medical image analysis[J]. Int J Multimed Inf Retr, 2022, 11(1): 19-38. DOI: 10.1007/s13735-021-00218-1.
SIOURAS A, MOUSTAKIDIS S, GIANNAKIDIS A, et al. Knee injury detection using deep learning on MRI studies: a systematic review[J/OL]. Diagnostics (Basel), 2022, 12(2): 537 [2023-01-06]. DOI: 10.3390/diagnostics12020537.
HUBEL D H, WIESEL T N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex[J]. J Physiol, 1962, 160(1): 106-154. DOI: 10.1113/jphysiol.1962.sp006837.
FUKUSHIMA K. Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biol Cybern, 1980, 36(4): 193-202. DOI: 10.1007/BF00344251.
LIU F, ZHOU Z Y, SAMSONOV A, et al. Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection[J]. Radiology, 2018, 289(1): 160-169. DOI: 10.1148/radiol.2018172986.
SANAAT A, SHIRI I, FERDOWSI S, et al. Robust-deep: a method for increasing brain imaging datasets to improve deep learning models' performance and robustness[J]. J Digit Imaging, 2022, 35(3): 469-481. DOI: 10.1007/s10278-021-00536-0.
GUO M G, GONG H. Research on AlexNet improvement and optimization method[J]. Comput Eng Appl, 2020, 56(20): 124-131. DOI: 10.3778/j.issn.1002-8331.1907-0135
KHAN A, SOHAIL A, ZAHOORA U, et al. A survey of the recent architectures of deep convolutional neural networks[J].Artif Intell Rev, 2020, 53(8): 5455-5516. DOI: 10.1007/s10462-020-09825-6.
DHILLON A, VERMA G K. Convolutional neural network: a review of models, methodologies and applications to object detection[J].Prog Artif Intell, 2020, 9(2): 85-112. DOI: 10.1007/s13748-019-00203-0.
ATIKA L, NURMAINI S, PARTAN R U, et al. Image segmentation for mitral regurgitation with convolutional neural network based on UNet, resnet, vnet, FractalNet and SegNet: a preliminary study[J/OL]. Big Data Cogn Comput, 2022, 6(4): 141 [2023-01-06]. DOI: 10.3390/bdcc6040141.
LEE B, YAMANAKKANAVAR N, CHOI J Y. Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture[J/OL]. PLoS One, 2020, 15(8): e0236493 [2023-01-06]. DOI: 10.1371/journal.pone.0236493.
CHAN H P, HADJIISKI L M, SAMALA R K. Computer-aided diagnosis in the era of deep learning[J/OL]. Med Phys, 2020, 47(5): e218-e227 [2023-014-06]. DOI: 10.1002/mp.13764.
DU G T, CAO X, LIANG J M, et al. Medical Image Segmentation based on U-Net: A Review[J/OL]. J Imaging Sci Techn, 2020, 64(2) [2023-01-06]. DOI: 10.2352/J.ImagingSci.Technol.2020.64.2.020508.
BI H, SUN J W, JIANG Y B, et al. Structure boundary-preserving U-Net for prostate ultrasound image segmentation[J/OL]. Front Oncol, 2022, 12: 900340 [2023-01-06]. DOI: 10.3389/fonc.2022.900340.
YU N B, LIU J N, GAO L, et al. Auto-segmentation method based on deep learning for the knee joint in MR images[J]. Chin J Sci Instrum, 2020, 41(6): 140-149. DOI: 10.19650/j.cnki.cjsi.J2006199.
BURTON W, MYERS C, RULLKOETTER P. Semi-supervised learning for automatic segmentation of the knee from MRI with convolutional neural networks[J/OL]. Comput Methods Programs Biomed, 2020, 189: 105328 [2023-01-06]. DOI: 10.1016/j.cmpb.2020.105328.
GAJ S, YANG M R, NAKAMURA K, et al. Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks[J]. Magn Reson Med, 2020, 84(1): 437-449. DOI: 10.1002/mrm.28111.
AWAN M J, RAHIM M S M, SALIM N, et al. Automated knee MR images segmentation of anterior cruciate ligament tears[J/OL]. Sensors (Basel), 2022, 22(4): 1552 [2023-01-06]. DOI: 10.3390/s22041552.
JOHNSON P M, LIN D J, ZBONTAR J, et al. Deep learning reconstruction enables prospectively accelerated clinical knee MRI[J/OL]. Radiology, 2023, 307(2): e220425 [2023-01-06]. DOI: 10.1148/radiol.220425.
HAMMERNIK K, KLATZER T, KOBLER E, et al. Learning a variational network for reconstruction of accelerated MRI data[J]. Magn Reson Med, 2018, 79(6): 3055-3071. DOI: 10.1002/mrm.26977.
YANG G, YU S M, DONG H, et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction[J]. IEEE Trans Med Imaging, 2018, 37(6): 1310-1321. DOI: 10.1109/TMI.2017.2785879.
CHAUDHARI A S, STEVENS K J, WOOD J P, et al. Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers[J]. J Magn Reson Imaging, 2020, 51(3): 768-779. DOI: 10.1002/jmri.26872.
HERRMANN J, KELLER G, GASSENMAIER S, et al. Feasibility of an accelerated 2D-multi-contrast knee MRI protocol using deep-learning image reconstruction: a prospective intraindividual comparison with a standard MRI protocol[J]. Eur Radiol, 2022, 32(9): 6215-6229. DOI: 10.1007/s00330-022-08753-z.
CHEN Y T, SCHÖNLIEB C B, LIÒ P, et al. AI-based reconstruction for fast MRI—a systematic review and meta-analysis[J]. Proc IEEE, 2022, 110(2): 224-245. DOI: 10.1109/JPROC.2022.3141367.
PAN K, LIU Q Q, TANG L L, et al. Study on acceleration efficiency and image quality of artificial intelligence compressed sensing and compressed sensing in knee MRI[J]. Chin J Magn Reson Imaging, 2022, 13(5): 94-98. DOI: 10.12015/issn.1674-8034.2022.05.017.
AKAI H, YASAKA K, SUGAWARA H, et al. Acceleration of knee magnetic resonance imaging using a combination of compressed sensing and commercially available deep learning reconstruction: a preliminary study[J/OL]. BMC Med Imaging, 2023, 23(1): 5 [2023-01-06]. DOI: 10.1186/s12880-023-00962-2.
GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144. DOI: 10.1145/3422622.
CAI Z P, XIONG Z B, XU H H, et al. Generative adversarial networks[J]. ACM Comput Surv, 2022, 54(6): 1-38. DOI: 10.1145/3459992.
DENCK J, GUEHRING J, MAIER A, et al. MR-contrast-aware image-to-image translations with generative adversarial networks[J]. Int J Comput Assist Radiol Surg, 2021, 16(12): 2069-2078. DOI: 10.1007/s11548-021-02433-x.
FRID-ADAR M, DIAMANT I, KLANG E, et al. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification[J/OL]. Neurocomputing, 2018, 321: 321-331 [2023-01-06]. DOI: 10.1016/j.neucom.2018.09.013.
LIU Y B, LIU M X, XI Y H, et al. Generating Dual-Energy Subtraction Soft-Tissue Images from Chest Radiographs via Bone Edge-Guided GAN[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2020: 678-687. DOI: 10.1007/978-3-030-59713-9_65
ZHAN B, ZHOU L P, LI Z A. D2FE-GAN: Decoupled dual feature extraction based GAN for MRI image synthesis[J/OL]. Knowl Based Syst, 2022, 252: 109362. DOI: 10.1016/j.knosys.2022.109362. [2023-01-06]. DOI: 10.1016/j.knosys.2022.109362.
HIRVASNIEMI J, RUNHAAR J, VAN DER HEIJDEN R A, et al. The KNee OsteoArthritis Prediction (KNOAP2020) challenge: an image analysis challenge to predict incident symptomatic radiographic knee osteoarthritis from MRI and X-ray images[J]. Osteoarthritis Cartilage, 2023, 31(1): 115-125. DOI: 10.1016/j.joca.2022.10.001.
LOPEZ SCHMIDT I, HAAG N, SHAHZADI I, et al. Diagnostic image quality of a low-field (0.55T) knee MRI protocol using deep learning image reconstruction compared with a standard (1.5T) knee MRI protocol[J/OL]. J Clin Med, 2023, 12(5): 1916 [2023-01-06]. DOI: 10.3390/jcm12051916.
HU Y, TANG J, ZHAO S H, et al. Deep learning-based multimodal 3 T MRI for the diagnosis of knee osteoarthritis[J/OL]. Comput Math Methods Med, 2022, 2022: 7643487 [2023-01-06]. DOI: 10.1155/2022/7643487.
SCHIRATTI J B, DUBOIS R, HERENT P, et al. A deep learning method for predicting knee osteoarthritis radiographic progression from MRI[J/OL]. Arthritis Res Ther, 2021, 23(1): 262 [2023-01-06]. DOI: 10.1186/s13075-021-02634-4.
KATZ J N, ARANT K R, LOESER R F. Diagnosis and treatment of hip and knee osteoarthritis[J/OL]. JAMA, 2021, 325(6): 568 [2023-01-06]. DOI: 10.1001/jama.2020.22171.
GUIDA C, ZHANG M, SHAN J. Knee osteoarthritis classification using 3D CNN and MRI[J/OL]. Appl Sci, 2021, 11(11): 5196 [2023-01-06]. DOI: 10.3390/app11115196.
TOLPADI A A, LEE J J, PEDOIA V, et al. Deep learning predicts total knee replacement from magnetic resonance images[J/OL]. Sci Rep, 2020, 10(1): 6371 [2023-01-06]. DOI: 10.1038/s41598-020-63395-9.
PEDOIA V, NORMAN B, MEHANY S N, et al. 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]. J Magn Reson Imaging, 2019, 49(2): 400-410. DOI: 10.1002/jmri.26246.
AROUCHE NUNES B A, FLAMENT I, SHAH R, et al. MRI-based multi-task deep learning for cartilage lesion severity staging in knee osteoarthritis[J/OL]. Osteoarthr Cartil, 2019, 27: S398-S399 [2023-01-06]. DOI: 10.1016/j.joca.2019.02.399.
ZHANG L Y, LI M F, ZHOU Y J, et al. Deep learning approach for anterior cruciate ligament lesion detection: evaluation of diagnostic performance using arthroscopy as the reference standard[J]. J Magn Reson Imaging, 2020, 52(6): 1745-1752. DOI: 10.1002/jmri.27266.
NAMIRI N K, LEE J, ASTUTO B, et al. Deep learning for large scale MRI-based morphological phenotyping of osteoarthritis[J/OL]. Sci Rep, 2021, 11(1): 10915 [2023-01-06]. DOI: 10.1038/s41598-021-90292-6.
CAI L, GAO J Y, ZHAO D. A review of the application of deep learning in medical image classification and segmentation[J/OL]. Ann Transl Med, 2020, 8(11): 713 [2023-01-06]. DOI: 10.21037/atm.2020.02.44.
PATHAK Y, SHUKLA P K, TIWARI A, et al. Deep transfer learning based classification model for COVID-19 disease[J]. IRBM, 2022, 43(2): 87-92. DOI: 10.1016/j.irbm.2020.05.003.

PREV Research progress of MRI on brain in patients with cervical spondylotic myelopathy
NEXT Principle and application progress of magnetic resonance reporter gene imaging

Tel & Fax: +8610-67113815    E-mail: