Share this content in WeChat
The research progress of diagnosing meniscus injury in MRI based on deep learning
HU Weiyi  SU Xianyan  KE Xiaoting  CHEN Yanfeng  LAI Qingquan 

Cite this article as: Hu WY, Su XY, Ke XT, et al. The research progress of diagnosing meniscus injury in MRI based on deep learning[J]. Chin J Magn Reson Imaging, 2022, 13(5): 167-170. DOI:10.12015/issn.1674-8034.2022.05.036.

[Abstract] Meniscus tear is a common type of knee injury. If not properly treated, it is easy to cause a series of clinical symptoms such as knee pain and osteoarthritis. Correct identification of meniscus lesions is an important prerequisite for patient education and clinical intervention. MRI is the most commonly used imaging method for clinical diagnosis of meniscus injury. It can accurately reflect the location, type and morphology of meniscus tear, and is the preferred imaging method for clinical diagnosis of meniscus tear. MRI disease detection based on deep learning is an emerging field of artificial intelligence, which may eventually translate into clinical practice with the continuous advancement of the clinical utility research of deep learning algorithm. This paper explores the progress of deep learning-based meniscal MRI diagnosis in meniscus injury binomial classification, tear location, tear direction, classification and region of interest segmentation from the two classifications of transfer learning and customized neural network, and point out some shortcomings of current research, in order to provide ideas for future research.
[Keywords] artificial intelligence;deep learning;convolutional neural network;transfer learning;meniscus injury;magnetic resonance imaging;dataset

HU Weiyi   SU Xianyan   KE Xiaoting   CHEN Yanfeng   LAI Qingquan*  

CT/MRI Room, the Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China

Lai QQ, E-mail:

Conflicts of interest   None.

Received  2021-10-26
Accepted  2022-04-29
DOI: 10.12015/issn.1674-8034.2022.05.036
Cite this article as: Hu WY, Su XY, Ke XT, et al. The research progress of diagnosing meniscus injury in MRI based on deep learning[J]. Chin J Magn Reson Imaging, 2022, 13(5): 167-170.DOI:10.12015/issn.1674-8034.2022.05.036

Fox AJ, Wanivenhaus F, Burge AJ, et al. The human meniscus: a review of anatomy, function, injury, and advances in treatment[J]. Clin Anat, 2015, 28(2): 269-287. DOI: 10.1002/ca.22456.
Cinque ME, DePhillipo NN, Moatshe G, et al. Clinical outcomes of inside-out meniscal repair according to anatomic zone of the meniscal tear[J]. Orthop J Sports Med, 2019, 7(7): 2325967119860806. DOI: 10.1177/2325967119860806.
Phelan N, Rowland P, Galvin R, et al. A systematic review and meta-analysis of the diagnostic accuracy of MRI for suspected ACL and meniscal tears of the knee[J]. Knee Surg Sports Traumatol Arthrosc, 2016, 24(5): 1525-1539. DOI: 10.1007/s00167-015-3861-8.
Lee CS, Nagy PG, Weaver SJ, et al. Cognitive and system factors contributing to diagnostic errors in radiology[J]. AJR Am J Roentgenol, 2013, 201(3): 611-617. DOI: 10.2214/AJR.12.10375.
He KM, Zhang XY, Ren SQ, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[J]. 2015 IEEE Int Conf Comput Vis ICCV, 2015: 1026-1034. DOI: 10.1109/ICCV.2015.123.
Huynh BQ, Li H, Giger ML. Digital mammographic tumor classification using transfer learning from deep convolutional neural networks[J]. J Med Imaging (Bellingham), 2016, 3(3): 034501. DOI: 10.1117/1.JMI.3.3.034501.
Tajbakhsh N, Shin JY, Gurudu SR, et al. Convolutional neural networks for medical image analysis: full training or fine tuning?[J]. IEEE Trans Med Imaging, 2016, 35(5): 1299-1312. DOI: 10.1109/TMI.2016.2535302.
Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge[J]. Int J Comput Vis, 2015, 115(3): 211-252. DOI: 10.1007/s11263-015-0816-y.
Bien N, Rajpurkar P, Ball RL, et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet[J]. PLoS Med, 2018, 15(11): e1002699. DOI: 10.1371/journal.pmed.1002699.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks[J]. Commun ACM, 2017, 60(6): 84-90. DOI: 10.1145/3065386.
Qiu XB, Liu ZW, Zhuang M, et al. Fusion of CNN1 and CNN2-based magnetic resonance image diagnosis of knee meniscus injury and a comparative analysis with computed tomography[J]. Comput Methods Programs Biomed, 2021, 211: 106297. DOI: 10.1016/j.cmpb.2021.106297.
Couteaux V, Si-Mohamed S, Nempont O, et al. Automatic knee meniscus tear detection and orientation classification with Mask-RCNN[J]. Diagn Interv Imaging, 2019, 100(4): 235-242. DOI: 10.1016/j.diii.2019.03.002.
He KM, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Trans Pattern Anal Mach Intell, 2020, 42(2): 386-397. DOI: 10.1109/TPAMI.2018.2844175.
Adams BG, Houston MN, Cameron KL. The epidemiology of Meniscus injury[J]. Sports Med Arthrosc Rev, 2021, 29(3): e24-e33. DOI: 10.1097/JSA.0000000000000329.
Roblot V, Giret Y, Bou Antoun M, et al. Artificial intelligence to diagnose meniscus tears on MRI[J]. Diagn Interv Imaging, 2019, 100(4): 243-249. DOI: 10.1016/j.diii.2019.02.007.
Rizk B, Brat H, Zille P, et al. Meniscal lesion detection and characterization in adult knee MRI: a deep learning model approach with external validation[J]. Phys Med, 2021, 83: 64-71. DOI: 10.1016/j.ejmp.2021.02.010.
Fritz B, Marbach G, Civardi F, et al. Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference[J]. Skeletal Radiol, 2020, 49(8): 1207-1217. DOI: 10.1007/s00256-020-03410-2.
Nguyen JC, de Smet AA, Graf BK, et al. MR imaging-based diagnosis and classification of meniscal tears[J]. Radiographics, 2014, 34(4): 981-999. DOI: 10.1148/rg.344125202.
Lecouvet F, van Haver T, Acid S, et al. Magnetic resonance imaging (MRI) of the knee: identification of difficult-to-diagnose meniscal lesions[J]. Diagn Interv Imaging, 2018, 99(2): 55-64. DOI: 10.1016/j.diii.2017.12.005.
Pedoia V, Norman B, Mehany SN, 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.
Astuto B, Flament I, Namiri N K, et al. Automatic deep learning-assisted detection and grading of abnormalities in knee MRI studies[J]. Radiol Artif Intell, 2021, 3(3): e200165. DOI: 10.1148/ryai.2021200165.
Rahman MM, Dürselen L, Seitz AM. Automatic segmentation of knee menisci—A systematic review[J]. Artif Intell Med, 2020, 105: 101849. DOI: 10.1016/j.artmed.2020.101849.
Tack A, Shestakov A, Lüdke D, et al. A multi-task deep learning method for detection of meniscal tears in MRI data from the osteoarthritis initiative database[J]. Front Bioeng Biotechnol, 2021, 9: 747217. DOI: 10.3389/fbioe.2021.747217.
Wang KP, Zheng MY, Wei HY, et al. Multi-modality medical image fusion using convolutional neural network and contrast pyramid[J]. Sensors (Basel), 2020, 20(8): E2169. DOI: 10.3390/s20082169.
Dai Y, Gao YF, Liu FY. TransMed: transformers advance multi-modal medical image classification[J]. Diagnostics (Basel), 2021, 11(8): 1384. DOI: 10.3390/diagnostics11081384.
Segura-Bedmar I, Raez P. Cohort selection for clinical trials using deep learning models[J]. J Am Med Inform Assoc, 2019, 26(11): 1181-1188. DOI: 10.1093/jamia/ocz139.
Adams BG, Houston MN, Cameron KL. The epidemiology of Meniscus injury[J]. Sports Med Arthrosc Rev, 2021, 29(3): e24-e33. DOI: 10.1097/JSA.0000000000000329.

PREV Application of radiomics in spinal diseases
NEXT Distribution characteristics and clinical value of U-fiber involvements in multiple sclerosis

Tel & Fax: +8610-67113815    E-mail: