Current status and perspectives of research on deep learning techniques in knee disorders

doi:10.3877/cma.j.issn.1674-134X.2023.05.019

Abstract

Abstract:

The knee joint is one of the most important joints in the human body, and the diagnosis and treatment of related diseases has been a hot research topic in the field of bone and joint surgery. Deep learning technology has the advantages of high efficiency, low cost and high consistency, and can theoretically solve a series of pain points in clinical treatment. However, as a new technology that has not yet fully matured, deep learning technology faces the obstacles of insufficient interpretability and lack of high-quality datasets in the process of clinical extension. This paper attempted to provide a brief overview of the current state of research on deep learning technology in knee diseases in terms of its current strengths, weaknesses and future directions.

Key words: Knee joint, Deep learning, Neural networks, computer

Ruiying Li, Wang Wei, Dazhi Wang, Zhibin Shi. Current status and perspectives of research on deep learning techniques in knee disorders[J]. Chinese Journal of Joint Surgery(Electronic Edition), 2023, 17(05): 722-725.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhgjwkzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1674-134X.2023.05.019

https://zhgjwkzz.cma-cmc.com.cn/EN/Y2023/V17/I05/722

References 45

[1]	Grawe B, SchroederAJ, Kakazu R, et al. Lateral collateral ligament injury about the knee: anatomy, evaluation, and management[J/OL]. J Am Acad Orthop Surg, 2018, 26(6): e120-e127. DOI: 10.5435/JAAOS-D-16-00028.
[2]	Pedoia V, Majumdar S, LinkTM. Segmentation of joint and musculoskeletal tissue in the study of arthritis[J]. Magma, 2016, 29(2): 207－221.
[3]	Norman B, Pedoia V, Majumdar S. Use of 2D U-net convolutional neural networks for automated cartilage and Meniscussegmentation of knee MR imaging data to determine relaxometry and morphometry[J]. Radiology, 2018, 288(1): 177－185.
[4]	Hubel DH, Wiesel TN. Receptive fields of single neurones in the cat’s striate cortex[J]. J Physiol, 1959, 148(3): 574－591.
[5]	LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J/OL]. Proc IEEE, 1998, 86(11): 2278－2324. DOI: 10.1109/5.726791.
[6]	LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436－444.
[7]	陈宁杰，赵卉，郝风云，等. 晚期膝骨关节炎滑膜MRI厚度与疼痛及功能评分相关性[J/CD]. 中华关节外科杂志(电子版), 2019, 13(4): 412－418.
[8]	中华医学会骨科学分会关节外科学组，中国医师协会骨科医师分会骨关节炎学组，国家老年疾病临床医学研究中心(湘雅医院), 等. 中国骨关节炎诊疗指南(2021年版)[J]. 中华骨科杂志，2021, 41(18): 1291－1314.
[9]	White LM, Schweitzer ME, Deely DM, et al. The effect of training and experience on the magnetic resonance imaging interpretation of meniscal tears[J]. Arthroscopy, 1997, 13(2): 224－228.
[10]	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.
[11]	Liu F, Zhou Z, 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.
[12]	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/OL]. Front Bioeng Biotechnol, 2021, 9: 747217. DOI: 10.3389/fbioe.2021.747217.
[13]	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.
[14]	Günther KP, Sun Y. Reliability of radiographic assessment in hip and knee osteoarthritis[J]. Osteoarthritis Cartilage, 1999, 7(2): 239－246.
[15]	Quatman CE, Hettrich CM, Schmitt LC, et al. The clinical utility and diagnostic performance of magnetic resonance imaging for identification of early and advanced knee osteoarthritis: a systematic review[J]. Am J Sports Med, 2011, 39(7): 1557－1568.
[16]	Pedoia V, Lee J, Norman B, et al. Diagnosing osteoarthritis from T₂ maps using deep learning: an analysis of the entire Osteoarthritis Initiative baseline cohort[J]. Osteoarthritis Cartilage, 2019, 27(7): 1002－1010.
[17]	Tiulpin A, Thevenot J, Rahtu E, et al. Automatic knee osteoarthritis diagnosis from plain radiographs: adeep learning-based approach[J/OL]. SciRep, 2018, 8(1): 1727. DOI: 10.1038/s41598-018-20132-7.
[18]	Norman B, Pedoia V, Noworolski A, et al. Applying densely connected convolutional neural networks for staging osteoarthritis severity from plain radiographs[J]. J Digit Imaging, 2019, 32(3): 471－477.
[19]	Namiri NK, 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. DOI: 10.1038/s41598-021-90292-6.
[20]	Chang PD, Wong TT, Rasiej MJ. Deep learning for detection of complete anterior cruciate ligament tear[J]. J Digit Imaging, 2019, 32(6): 980－986.
[21]	Liu F, Guan B, Zhou Z, et al. Fully automated diagnosis of anterior cruciate ligament tears on knee MR images by using deep learning[J/OL]. Radiol Artif Intell, 2019, 1(3): 180091. DOI: 10.1148/ryai.2019180091.
[22]	Razali MH, Sazwan SM, Mahmood M, et al. Anterior cruciate ligament (ACL) coronal view injury diagnosis system using convolutional neural network[C]//Proceedings of the 2019 2nd International Conference on Electronics and Electrical Engineering Technology. September 25 － 27, 2019, Penang, Malaysia. New York: ACM, 2019: 118－122.
[23]	Germann C, Marbach G, Civardi F, et al. Deep convolutional neural network-based diagnosis of anterior cruciate ligament tears: performance comparison of homogenous versus heterogeneous knee MRI cohorts with different pulse sequence protocols and 1.5-T and 3-T magnetic field strengths[J]. Invest Radiol, 2020, 55(8): 499－506.
[24]	Namiri NK, Flament I, Astuto B, et al. Deep learning for hierarchical severity staging of anterior cruciate ligament injuries from MRI[J/OL]. Radiol Artif Intell, 2020, 2(4): e190207. DOI: 10.1148/ryai.2020190207.
[25]	Tran A, Lassalle L, Zille P, et al. Deep learning to detect anterior cruciate ligament tear on knee MRI: multi-continental external validation[J]. Eur Radiol, 2022, 32(12): 8394－8403.
[26]	Sridhar S, Amutharaj J, Valsalan P, et al. A torn ACL mapping in knee MRI images using deep convolution neural network with inception-v3[J/OL]. J Healthc Eng, 2022, 2022: 7872500. DOI: 10.1155/2022/7872500.
[27]	Fripp J, Crozier S, WarfieldSK, et al. Automatic segmentation and quantitative analysis of the articular cartilages from magnetic resonance images of the knee[J]. IEEE Trans Med Imaging, 2010, 29(1): 55－64.
[28]	张银婷，彭鳒侨. 基于MRI图像的计算机膝关节建模新思路[J/CD]. 中华关节外科杂志(电子版), 2018, 12(6): 786－790.
[29]	Aprovitola A, Gallo L. Knee bone segmentation from MRI: a classification and literature review[J]. Biocybern Biomed Eng, 2016, 36(2): 437－449.
[30]	Du Y, Almajalid R, Shan J, et al. A novel method to predict knee osteoarthritis progression on MRI using machine learning methods[J]. IEEE Trans Nanobioscience, 2018, 17(3): 228－236.
[31]	Flannery SW, Kiapour AM, Edgar DJ, et al. Automated magnetic resonance image segmentation of the anterior cruciate ligament[J]. J Orthop Res, 2021, 39(4): 831－840.
[32]	Chang GH, Park LK, Le NA, et al. Subchondral bone length in knee osteoarthritis: adeep learning-derived imaging measure and its association with radiographic and clinical outcomes[J]. Arthritis Rheumatol, 2021, 73(12): 2240－2248.
[33]	Deng Y, You L, Wang Y, et al. A coarse-to-fine framework for automated knee bone and cartilage segmentation data from the osteoarthritis initiative[J]. J Digit Imaging, 2021, 34(4): 833－840.
[34]	Felfeliyan B, Hareendranathan A, Kuntze G, et al. Improved-Mask R-CNN: towards an accurate generic MSK MRI instance segmentation platform (data from the Osteoarthritis Initiative)[J/OL]. Comput Med Imaging Graph, 2022, 97: 102056. DOI: 10.1016/j.compmedimag.2022.102056.
[35]	Lipton ZC. The mythos of model interpretability[J]. Commun ACM, 2018, 61(10): 36－43.
[36]	Jeon Y, Yoshino K, Hagiwara S, et al. Interpretable and lightweight 3-D deep learning model for automated ACL diagnosis[J]. IEEE J Biomed Health Inform, 2021, 25(7): 2388－2397.
[37]	Ölmez E, Akdoǧan V, Korkmaz M, et al. Automatic segmentation of Meniscus in multispectral MRI using regions with convolutional neural network (R-CNN)[J]. J Digit Imaging, 2020, 33(4): 916－929.
[38]	Manna S, Bhattacharya S, Pal U. Self-supervised representation learning for detection of ACL tear injury in knee MR videos[J]. Pattern Recognit Lett, 2022, 154: 37－43.
[39]	Wahid A, Ali Shah J, KhanAU, et al. Multi-layered basis pursuit algorithms for classification of MR images of knee ACL tear[J/OL]. IEEE Access, 2020, 8: 205424-205435. DOI: 10.1109/ACCESS.2020.3037745.
[40]	Awan MJ, Rahim MSM, Salim N, et al. Efficient detection of knee anterior cruciate ligament from magnetic resonance imaging using deep learning approach[J/OL]. Diagnostics, 2021, 11(1): 105. DOI: 10.3390/diagnostics11010105.
[41]	Awan MJ, Rahim MSM, Salim N, et al. Automated knee MR images segmentation of anterior cruciate ligament tears[J/OL]. Sensors, 2022, 22(4): 1552. DOI: 10.3390/s22041552.
[42]	Calivá F, Kamat S, Morales Martinez A, et al. Surface spherical encoding and contrastive learning for virtual bone shape aging[J/OL]. Med Image Anal, 2022, 77: 102388. DOI: 10.1016/j.media.2022.102388.
[43]	Kanthavel R, Dhaya R. Prediction model using reinforcement deep learning technique for osteoarthritis disease diagnosis[J]. Comput Syst Sci Eng, 2022, 42(1): 257－269.
[44]	Moustakidis S, Christodoulou E, Papageorgiou E, et al. Application of machine intelligence for osteoarthritis classification: a classical implementation and a quantum perspective[J]. Quantum MachIntell, 2019, 1(3): 73－86.
[45]	Tan JS, Tippaya S, Binnie T, et al. Predicting knee joint kinematics from wearable sensor data in people with knee osteoarthritis and clinical considerations for future machine learning models[J/OL]. Sensors, 2022, 22(2): 446. DOI: 10.3390/s22020446.

Please choose a citation manager

Content to export