Share：
Share this content in WeChat
X
[Chinese][PDF]821
• Review •
Research progress of convolutional neural networks based on MRI in the diagnosis of meniscus injury
YUAN Dian  DU Yuzheng  WEI Dejian  ZHANG Junzhong  CAO Hui 

Cite this article as: YUAN D, DU Y Z, WEI D J, et al. Research progress of convolutional neural networks based on MRI in the diagnosis of meniscus injury[J]. Chin J Magn Reson Imaging, 2024, 15(3): 223-229. DOI:10.12015/issn.1674-8034.2024.03.037.


[Abstract] The meniscus plays a crucial role in maintaining knee joint stability, and meniscus injury is a common injury in the field of sports medicine, which is the main cause of knee osteoarthritis. MRI has high specificity and sensitivity, which can detect the morphological structure of the meniscus and internal signals of the knee joint. It is one of the best medical imaging techniques for diagnosing meniscus injuries. Convolutional neural networks, as a classic neural network in deep learning, have superior capabilities in the field of medical image assisted diagnosis. Research on the use of convolutional neural networks for MRI image assisted diagnosis of meniscus injury has also been proposed. This article provides a comprehensive overview of the application of convolutional neural networks in meniscus MRI image segmentation, detection, and classification. It can help readers understand the research progress of MRI based convolutional neural networks in meniscus injury diagnosis, and provide new directions for early diagnosis and personalized treatment of meniscus injury.
[Keywords] meniscal injury；magnetic resonance imaging；convolutional neural networks；deep learning；image segmentation；image classification

YUAN Dian1   DU Yuzheng1   WEI Dejian1   ZHANG Junzhong2   CAO Hui1*  

1 College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, China

2 The First Clinical Medical School, Shandong University of Traditional Chinese Medicine, Jinan 250355, China

Corresponding author: CAO H, E-mail: caohui63@163.com

Conflicts of interest   None.

Received  2023-12-05
Accepted  2024-02-26
DOI: 10.12015/issn.1674-8034.2024.03.037
Cite this article as: YUAN D, DU Y Z, WEI D J, et al. Research progress of convolutional neural networks based on MRI in the diagnosis of meniscus injury[J]. Chin J Magn Reson Imaging, 2024, 15(3): 223-229. DOI:10.12015/issn.1674-8034.2024.03.037.

[1]
DAI T Y, PAN Z Y, YIN F. In vivo studies of mesenchymal stem cells in the treatment of Meniscus injury[J]. Orthop Surg, 2021, 13(8): 2185-2195. DOI: 10.1111/os.13002.
[2]
TOMASZEWSKI R, ROST-ROSZKOWSKA M, WILCZEK G, et al. Changes in the avascular area of the meniscus using mesenchymal stem cells and growth plate chondrocytes in a pig model[J]. J Anat, 2021, 239(6): 1409-1418. DOI: 10.1111/joa.13508.
[3]
WU W G, WU H B. Platelet rich plasma combined with surgery for treatment of knee osteoarthritis with meniscus injury[J]. Chin J Jt Surg Electron Ed, 2021, 15(3): 369-372. DOI: 10.3877/cma.j.issn.1674-134X.2021.03.019.
[4]
DEVIANDRI R, DAULAY M C, ISKANDAR D, et al. Health-economic evaluation of meniscus tear treatments: a systematic review[J]. Knee Surg Sports Traumatol Arthrosc, 2023, 31(9): 3582-3593. DOI: 10.1007/s00167-022-07278-8.
[5]
TANG C, ZHANG W, LI H, et al. CNN-based qualitative detection of bone mineral density via diagnostic CT slices for osteoporosis screening[J]. Osteoporos Int, 2021, 32(5): 971-979. DOI: 10.1007/s00198-020-05673-w.
[6]
FANG Y J, LI W, CHEN X J, et al. Opportunistic osteoporosis screening in multi-detector CT images using deep convolutional neural networks[J]. Eur Radiol, 2021, 31(4): 1831-1842. DOI: 10.1007/s00330-020-07312-8.
[7]
LIM H K, HA H I, PARK S Y, et al. Prediction of femoral osteoporosis using machine-learning analysis with radiomics features and abdomen-pelvic CT: A retrospective single center preliminary study[J/OL]. PLoS One, 2021, 16(3): e0247330 [2023-09-12]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0247330. DOI: 10.1371/journal.pone.0247330.
[8]
DU X H, WEI H, LI P, et al. Artificial intelligence (AI) assisted CT/MRI image fusion technique in preoperative evaluation of a pelvic bone osteosarcoma[J/OL]. Front Oncol, 2020, 10: 1209 [2023-09-15]. https://pubmed.ncbi.nlm.nih.gov/32850355/. DOI: 10.3389/fonc.2020.01209.
[9]
DO N T, JUNG S T, YANG H J, et al. Multi-level seg-unet model with global and patch-based X-ray images for knee bone tumor detection[J/OL]. Diagnostics, 2021, 11(4): 691 [2023-09-15]. https://www.mdpi.com/2075-4418/11/4/691. DOI: 10.3390/diagnostics11040691.
[10]
PARK H S, JEON K, CHO Y J, et al. Diagnostic performance of a new convolutional neural network algorithm for detecting developmental dysplasia of the hip on anteroposterior radiographs[J]. Korean J Radiol, 2021, 22(4): 612-623. DOI: 10.3348/kjr.2020.0051.
[11]
SWIECICKI A, LI N Y, O'DONNELL J, et al. Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists[J/OL]. Comput Biol Med, 2021, 133: 104334 [2023-09-16]. https://pubmed.ncbi.nlm.nih.gov/33823398/. DOI: 10.1016/j.compbiomed.2021.104334.
[12]
SANTOMARTINO S M, KUNG J, YI P H. Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears[J]. Skeletal Radiol, 2024, 53(3): 445-454. DOI: 10.1007/s00256-023-04416-2.
[13]
ZHU X P, XU H, WANG L, et al. Impact of lateral meniscus injury detected by preoperative magnetic resonance imaging on midterm results after unicompartmental knee arthroplasty[J]. Knee, 2023, 44: 227-235. DOI: 10.1016/j.knee.2023.08.014.
[14]
CHEN L, LIANG X P, DAI H, et al. Evaluation of Diagnostic Effect and Accuracy of Standard CT and MRI for Knee Meniscus and Articular Cartilage Injury[J]. China Standardization, 2023(16): 222-225. DOI: 10.3969/j.issn.1002-5944.2023.16.050.
[15]
SIOURAS A, MOUSTAKIDIS S, GIANNAKIDIS A, et al. Knee injury detection using deep learning on MRI studies: a systematic review[J/OL]. Diagnostics, 2022, 12(2): 537 [2023-09-16]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8871256/. DOI: 10.3390/diagnostics12020537.
[16]
WILLIAMS C, DANESHVAR M, PINTO P. Emerging role of multiparametric magnetic resonance imaging in identifying clinically relevant localized prostate cancer[J]. Curr Opin Oncol, 2021, 33(3): 244-251. DOI: 10.1097/CCO.0000000000000717.
[17]
WANG X, LI J, LI T R. Research and application of bone and joint medical imaging in AI[J]. Image Technol, 2022, 34(4): 76-80. DOI: 10.3969/j.issn.1001-0270.2022.04.15.
[18]
SAJED S, SANATI A, GARCIA J E, et al. The effectiveness of deep learning vs. traditional methods for lung disease diagnosis using chest X-ray images: a systematic review[J/OL]. Appl Soft Comput, 2023, 147: 110817 [2023-09-17]. https://dl.acm.org/doi/abs/10.1016/j.asoc.2023.110817. DOI: 10.1016/j.asoc.2023.110817.
[19]
WANG L, WANG H R, HUANG Y N, et al. Trends in the application of deep learning networks in medical image analysis: evolution between 2012 and 2020[J/OL]. Eur J Radiol, 2022, 146: 110069 [2023-09-17]. https://pubmed.ncbi.nlm.nih.gov/34847395/. DOI: 10.1016/j.ejrad.2021.110069.
[20]
APOSTOLOPOULOS I D, PINTELAS E G, LIVIERIS I E, et al. Automatic classification of solitary pulmonary nodules in PET/CT imaging employing transfer learning techniques[J]. Med Biol Eng Comput, 2021, 59(6): 1299-1310. DOI: 10.1007/s11517-021-02378-y.
[21]
BOUDEGGA H, ELLOUMI Y, AKIL M, et al. Fast and efficient retinal blood vessel segmentation method based on deep learning network[J/OL]. Comput Med Imaging Graph, 2021, 90: 101902 [2023-09-20]. https://pubmed.ncbi.nlm.nih.gov/33892389/. DOI: 10.1016/j.compmedimag.2021.101902.
[22]
SARATXAGA C L, MOYA I, PICÓN A, et al. MRI deep learning-based solution for Alzheimer's disease prediction[J/OL]. J Pers Med, 2021, 11(9): 902 [2023-9-20]. https://pubmed.ncbi.nlm.nih.gov/34575679/. DOI: 10.3390/jpm11090902.
[23]
JENA B, NAYAK G K, SAXENA S. Convolutional neural network and its pretrained models for image classification and object detection: A survey[J/OL]. Concurrency And Computation, 2022, 34(6): e6767 [2023-09-23]. https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.6767. DOI: 10.1002/cpe.6767.
[24]
SAVITHADEVI M. Convolutional Neural Network based Retinal Vessel Segmentation[J]. Comput Sci Eng, 2022, 12(6): 135-144. DOI: 10.5121/cseij.2022.12613.
[25]
FENG J, YU S R, ZHANG Y P, et al. A system based on deep convolutional neural network improves the detection of early gastric cancer[J/OL]. Front Oncol, 2022, 12: 1021625 [2023-09-24]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.1021625/full. DOI: 10.3389/fonc.2022.1021625.
[26]
ULAGAMUTHALVI V, KULANTHAIVEL G, BALASUNDARAM A, et al. Breast mammogram analysis and classification using deep convolution neural network[J]. Comput Syst Sci Eng, 2022, 43(1): 275-289. DOI: 10.32604/csse.2022.023737.
[27]
TAYE M M. Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions[J/OL]. Computation, 2023, 11(3): 52[2023-09-24]. https://www.proquest.com/openview/0253dda1d60f3107c79bea87d4f43813/1?pq-origsite=gscholar&cbl=2032414. DOI: 10.3390/computation11030052.
[28]
RAUSCHER I, STAHL R, CHENG J, et al. Meniscal measurements of T1rho and T2 at MR imaging in healthy subjects and patients with osteoarthritis[J]. Radiology, 2008, 249(2): 591-600. DOI: 10.1148/radiol.2492071870.
[29]
TACK A, MUKHOPADHYAY A, ZACHOW S. Knee menisci segmentation using convolutional neural networks: data from the Osteoarthritis Initiative[J]. Osteoarthritis Cartilage, 2018, 26(5): 680-688. DOI: 10.1016/j.joca.2018.02.907.
[30]
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[J]. Radiology, 2018, 288(1): 177-185. DOI: 10.1148/radiol.2018172322.
[31]
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.
[32]
ÖLMEZ E, AKDOĞAN 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. DOI: 10.1007/s10278-020-00329-x.
[33]
BYRA M, WU M, ZHANG X D, et al. Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-Net with transfer learning[J]. Magn Reson Med, 2020, 83(3): 1109-1122. DOI: 10.1002/mrm.27969.
[34]
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.
[35]
JEON U, KIM H, HONG H, et al. Automatic Meniscus segmentation using adversarial learning-based segmentation network with object-aware map in knee MR images[J/OL]. Diagnostics, 2021, 11(9): 1612 [2023-09-25]. https://pubmed.ncbi.nlm.nih.gov/34573953/. DOI: 10.3390/diagnostics11091612.
[36]
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 Imag, 2023, 14(6): 192-197. DOI: 10.12015/issn.1674-8034.2023.06.035.
[37]
BIEN N, RAJPURKAR P, BALL R L, et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet[J/OL]. PLoS Med, 2018, 15(11): e1002699 [2023-10-02]. https://pubmed.ncbi.nlm.nih.gov/30481176/. DOI: 10.1371/journal.pmed.1002699.
[38]
TSAI C H, KIRYATI N, KONEN E, et al. Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet)[EB/OL]. 2020: arXiv: 2005.02706. http://arxiv.org/abs/2005.02706.pdf
[39]
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.
[40]
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.
[41]
QIU X B, LIU Z W, 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/OL]. Comput Methods Programs Biomed, 2021, 211: 106297 [2023-10-02]. https://pubmed.ncbi.nlm.nih.gov/34536633/. DOI: 10.1016/j.cmpb.2021.106297.
[42]
LI W, CAO P, ZHAO D Z, et al. Pulmonary nodule classification with deep convolutional neural networks on computed tomography images[J/OL]. Comput Math Methods Med, 2016, 2016: 6215085 [2023-10-03]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5192289/. DOI: 10.1155/2016/6215085.
[43]
LIU Y, XIE Y Q, LI Z B, et al. Research progress of deep learning target detection algorithm in security field[J]. Commun Technol, 2021, 54(9): 2063-2073. DOI: 10.3969/j.issn.1002-0802.2021.09.001.
[44]
ROBLOT V, GIRET Y, ANTOUN M BOU, 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.
[45]
HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2020, 42(2): 386-397. DOI: 10.1109/TPAMI.2018.2844175.
[46]
LU W, LIU D, SHAO M, et al. Application of improved mask R-CNN network in medical image recognition and segmentation[J]. Comput Eng Appl, 2021, 57(24): 234-241. DOI: 10.3778/j.issn.1002-8331.2105-0092.
[47]
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.
[48]
LI Y Z, WANG Y, FANG K B, et al. Automated meniscus segmentation and tear detection of knee MRI with a 3D mask-RCNN[J]. Eur J Med Res, 2022, 27(1): 247 [2023-10-03]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9661774/. DOI: 10.1186/s40001-022-00883-w.
[49]
ASTUTO B, FLAMENT I, NAMIRI N K, et al. Automatic deep learning-assisted detection and grading of abnormalities in knee MRI studies[J/OL]. Radiol Artif Intell, 2021, 3(3): e200165 [2023-10-16]. https://pubmed.ncbi.nlm.nih.gov/34142088/. DOI: 10.1148/ryai.2021200165.
[50]
ZHANG Q Y. Computer Aided Diagnosis of Knee Joint meniscus tear Based on Convolutional Neural Network[D]. Tianjin: Tianjin University of Technology, 2022.
[51]
LI J, QIAN K, LIU J Y, et al. Identification and diagnosis of meniscus tear by magnetic resonance imaging using a deep learning model[J]. J Orthop Translat, 2022, 34: 91-101. DOI: 10.1016/j.jot.2022.05.006.

PREV Progress in deep learning based on magnetic resonance imaging for rectal cancer research
NEXT Advance of peritumoral radiomics research
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn