Knee meniscus segmentation and tear detection based on magnitic resonacis images: A review of literature

Document Type : Review articles

Authors

Department of Computer Science, College of Science, University of Baghdad, Iraq

Abstract

The meniscus has a crucial function in human anatomy, and Magnetic Resonance Imaging (M.R.I.) plays an essential role in meniscus assessment. It is difficult to identify cartilage lesions using typical image processing approaches because the M.R.I. data is so diverse. An M.R.I. data sequence comprises numerous images, and the attributes area we are searching for may differ from each image in the series. Therefore, feature extraction gets more complicated, hence specifically, traditional image processing becomes very complex. In traditional image processing, a human tells a computer what should be there, but a deep learning (D.L.) algorithm extracts the features of what is already there automatically. The surface changes become valuable when diagnosing a tissue sample. Small, unnoticeable changes in pixel density may indicate the beginning of cancer or tear tissue in the early stages. These details even expert pathologists might miss. Artificial intelligence (A.I.) and D.L. revolutionized radiology by enhancing efficiency and accuracy of both interpretative and non-interpretive jobs. When you look at AI applications, you should think about how they might work. Convolutional Neural Network (C.N.N.) is a part of D.L. that can be used to diagnose knee problems. There are existing algorithms that can detect and categorize cartilage lesions, meniscus tears on M.R.I., offer an automated quantitative evaluation of healing, and forecast who is most likely to have recurring meniscus tears based on radiographs.

Keywords

[1] D. Azcona, K. McGuinness and A.F. Smeaton, A comparative study of existing and new deep learning methods for detecting knee injuries using the MRNet dataset, Int. Conf. Intell. Data Sci. Technol. Appl. IDSTA 2020, pp. 149–155.
[2] M. Bardis, R. Houshyar, C. Chantaduly, A. Ushinsky, J. Glavis-Bloom, M. Shaver, D. Chow, E. Uchio and P. Chang, Deep learning with limited data: Organ segmentation performance by U-Net, Electron. 9 (2020), no. 8.
[3] Y. Bengio, Learning deep architectures for AI, Found., Trends Mach. Learn. 2 (2009), no. 1.
[4] N. Bien P. Rajpurkar, R.L. Ball, J. Irvin, A. Park, E. Jones, M. Bereket, B.N. Patel, K.W. Yeom, K. Shpanskaya and S. Halabi, Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet, PLoS Medicine 15 (2018), no. 11, 1–19.
[5] C.M. Bishop and N.M. Nasrabadi, Pattern recognition and machine learning, New York, Springer, 2006.
[6] Boehringer-Ingelheim, Radiology rounds; A closer look at interstitial lung disease, Boehringer-Ingelheim Website, https://www.ipfradiologyrounds.com/hrct-primer/image-reconstruction/.
[7] I. Boniatis, G. Panayiotakis and E. Panagiotopoulos, A computer-based system for the discrimination between normal and degenerated menisci from magnetic resonance images, IEEE Int. Workshop Imag. Syst. Tech. IEEE, 2008, pp. 335–339.
[8] T. Brosch, Y. Yoo, D.K.B. Li, A. Traboulsee and R. Tam, Modeling the variability in brain morphology and lesion distribution in multiple sclerosis by deep learning, Int. Conf. Medical Image Comput. Computer-Assisted Intervention, 2014, pp. 462–469.
[9] G. Carneiro and J.C. Nascimento, Combining multiple dynamic models and deep learning architectures for tracking the left ventricle endocardium in ultrasound data, IEEE Trans. Pattern Anal. Mach. Intell. 35 (2013), no. 11, 2592–2607.
[10] P.D. Chang, T.T. Wong and M.J. Rasiej, Deep learning for detection of complete anterior cruciate ligament tear, J. Digital Imag. 32 (2019), no. 6, 980–986.
[11] C.-T. Cheng, T.-Y. Ho, T.-Y. Lee, C.-C. Chang, C.-C. Chou and C.-C. Chen, Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs, Eur. Radiol. 29 (2019), no. 10, 5469–5477.
[12] D.C. Cire¸san, A. Giusti, L.M. Gambardella and J. Schmidhuber, Mitosis detection in breast cancer histology images with deep neural networks, Int. Conf. Medical Image Computing and Computer-Assisted Intervention, Springer, Berlin, Heidelberg, 2013, pp. 411–418.
[13] V. Couteaux, S. Si-Mohamed, O. Nempont, T. Lefevre, A. Popoff, G. Pizaine, N. Villain, I. Bloch, A. Cotten and L. Boussel, Automatic knee meniscus tear detection and orientation classification with Mask-RCNN, Diagn. Intervent. Imag. 100 (2019), no. 4, 235–242.
[14] A.A. Cruz-Roa, J.E.A. Ovalle, A. Madabhushi and F.A.G. Osorio, A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013, Springer, 2013, pp. 403–410.

[15] J. Dai, K. He and J. Sun, Instance-aware semantic segmentation via multi-task network cascades, Proc. IEEE Conf. Comput. Vis. Pattern Recogn. 2016, pp. 3150–3158.
[16] E.B. Dam, M. Lillholm, J. Marques and M. Nielsen, Automatic segmentation of high- and low-field knee MRIs using knee image quantification with data from the osteoarthritis initiative, J. Med. Imag. (Bellingham) 2 (2015), no. 2, 024001.
[17] R. Fakoor, F. Ladhak, A. Nazi and M. Huber, Using deep learning to enhance cancer diagnosis and classification, In Proceedings of the Int. Conf. on machine learning, ACM, New York, USA 28 (2013), 3937–3949.
[18] J. Fripp, P. Bourgeat, C. Engstrom, S. Ourselin, S. Crozier and O. Salvado, Automated segmentation of the menisci from MR images, IEEE Int. Symp. Biomed. Imag. From nano to macro, IEEE, 2009, pp. 510–513.
[19] J.-C. Fu, C.-C. Lin, C.-N. Wang and Y.-K. Ou, Computer-aided diagnosis for knee meniscus tears in magnetic resonance imaging, JIPE 30 (2013), no. 2, 67–77.
[20] B.E. Gage, N.M. McIlvain, C.L. Collins, S.K. Fields and R.D. Comstock, Epidemiology of 6.6 million knee injuries presenting to United States emergency departments from 1999 through 2008, Acad. Emerg. Med. 19 (2012), no. 4, 378–385.
[21] E.R. Garwood, R. Tai and G. Joshi, The use of artificial intelligence in the evaluation of knee pathology, Seminars in Musculoskeletal Radiology, 24 (2020), no. 1, 21–29.
[22] M.L. Giger, N. Karssemeijer and J.A. Schnabel, Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer, Annual Rev. Biomed. Eng. 15 (2013), 327–357.
[23] Y. Guo, G. Wu, L.A. Commander, S. Szary, V. Jewells, W. Lin and D. Shen, Segmenting hippocampus from infant brains by sparse patch matching with deep-learned features, Int. Conf. Med. Image Comput. Comput.-Ass. Interven. 2014, pp. 308–315.
[24] S. Gyftopoulos, P. Harkey, J. Hemingway, D.R. Hughes, A.B. Rosenkrantz and R.D. Jr, Changing musculoskeletal extremity imaging utilization from 1994 through 2013: A medicare beneficiary perspective, Amer. J. Roentg. 209 (2017), no. 05, 1103–1109.
[25] S. Gyftopoulos, D. Lin, F. Knoll, A.M. Doshi, T.C. Rodrigues and M.P. Recht, Artificial intelligence in musculoskeletal imaging: Current status and future directions, Amer. J. Roentg. 213 (2019), no. 3, 506.
[26] D.J. Hand and R.J. Till, A simple generalization of the area under the ROC curve for multiple class classification problems, Mach. Learn. 45 (2001), no. 2, 171–186.
[27] Y. Hata, S. Kobashi, Y. Tokimoto, M. Ishikawa and H. Ishikawa, Computer-aided diagnosis system of meniscal tears with T1 and T2 weighted MR images based on fuzzy inference computational intelligence theory and applications, Int. Conf. Computat.Intell. 2001, pp. 55–58.
[28] A. Hosny, C. Parmar, J. Quackenbush, L.H. Schwartz and H.J.W.L. Aerts, Artificial intelligence in radiology, Nat. Rev. Cancer 18 (2018), no. 8, 500–510.
[29] I. Irmakci, S.M. Anwar, D.A. Torigian and U. Bagci, Deep learning for musculoskeletal image analysis, 53rd Asilomar Conf. Signals, Syst. Comput. IEEE, 2019, pp. 1481–1485.
[30] C. K¨ose, O. Gen¸calio˘glu and U. S¸evik, An automatic diagnosis method for the knee meniscus tears in MR images, Expert Syst. Appl. 36 (2009), no. 2, 1208–1216.
[31] N. Lassau, T. Estienne, P. de Vomecourt, M. Azoulay, J. Cagnol, G. Garcia, M. Majer, E. Jehanno, R. RenardPenna, C. Balleyguier and F. Bidault, Five simultaneous artificial intelligence data challenges on ultrasound, CT, and MRI, Diagn. Interv. Imag. 100 (2019), no. 4, 199–209.
[32] E.A. Levin, R.M. Morgan, L.D. Griffin and V.J. Jones, A comparison of thresholding methods for forensic reconstruction studies using fluorescent powder proxies for trace materials, J. Forensic Sci. 64 (2019), no. 2, 431–442.
[33] R. Li, W. Zhang, H.I. Suk, L. Wang, J. Li, D. Shen and S. Ji, Deep learning based imaging data completion for improved brain disease diagnosis, Int. Conf. Medical Image Comput. Comput.-Ass. Interven. 2014, pp. 305–312.
[34] J.-T. Lu, S. Pedemonte, B. Bizzo, S. Doyle, K.P. Andriole and M.H. Michalski, DeepSPINE: Automated lumbar vertebral segmentation, disc-level designation, and spinal stenosis grading using deep learning, Machine Learn. Healthcare Conf. PMLR, 2018, pp. 403–419.
[35] N.C. Nacey, M.G. Geeslin, G.W. Miller and J.L. Pierce, Magnetic resonance imaging of the knee: An overview and update of conventional and state of the art imaging, Magnetic Resonance Imag. 45 (2017), no. 5, 1257–1275.
[36] J.C. Nguyen, A.A. De Smet, B.K. Graf and H.G. Rosas, MR imaging-based diagnosis and classification of meniscal tears, Radiograph. 34 (2014), no. 04, 981–999.
[37] A. Paproki, C. Engstrom, S.S. Chandra, A. Neubert, J. Fripp and S. Crozier, Automated segmentation and analysis of normal and osteoarthritic knee menisci from magnetic resonance images–data from the osteoarthritis initiative, Osteoarthritis Cartilage 22 (2014), no. 9, 1259–1270.
[38] A. Paproki, C. Engstrom and M. Strudwick, Automated T2- mapping of the menisci from magnetic resonance images in patients with acute knee injury, Acad. Radiol. 24 (2017), no. 10, 1295–1304.
[39] V. Pedoia, J. Lee, B. Norman, T.M. Link and S. Majumdar, Diagnosing osteoarthritis from T2 maps using deep learning: An analysis of the entire osteoarthritis initiative baseline cohort, Osteoarthritis Cartilage 27 (2019), no. 7, 1002–1010.
[40] V. Pedoia, B. Norman, S.N. Mehany, M.D. Bucknor, T.M. Link and S. Majumdar, 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. Magnetic Resonance Imag. 49 (2019), no. 2, 400–410.
[41] Y.D. Pranata, K.C. Wang, J.C. Wang, I. Idram, J.Y. Lai, J.W. Liu and I.H. Hsieh, Deep learning and SURF for automated classification and detection of calcaneus fractures in CT images, Comput.Meth. Prog. Biomed. 171 (2019), 27–37.
[42] M.M. Rahman, L. D¨urselen and A.M. Seitz, Automatic segmentation of knee menisci - A systematic review, Artif. Intell. Med. 105 (2020), p. 101849.
[43] A. Raj, S. Vishwanathan, B. Ajani, K. Krishnan and H. Agarwal, Automatic knee cartilage segmentation using fully volumetric convolutional neural networks for evaluation of osteoarthritis, IEEE 15th Int. Symp. Biomed. Imag. (ISBI 2018), IEEE, 2018, pp. 851–854.
[44] B. Ramakrishna, W. Liu, G. Saiprasad, N. Safdar, C.I. Chang, K. Siddiqui, W. Kim, E. Siegel, J.W. Chai, C.C.C. Chen and S.K. Lee, An automatic computer-aided detection system for meniscal tears on magnetic resonance images, IEEE Trans. Med. Imag. 28 (2009), no. 8, 1308–1316.
[45] M.P. Recht and J. Kramer, MR imaging of the postoperative knee: A pictorial essay, Radiograph. 22 (2002), no. 4, 765–774.
[46] V. Roblot, Y. Giret and M.B. Antoun, Artificial intelligence to diagnose meniscus tears on MRI, Diagn. Interv. Imag. 100 (2019), no. 4, 243–249.
[47] H.R. Roth, L. Lu, A. Seff, K.M. Cherry, J. Hoffman, S. Wang, J. Liu, E. Turkbey and R.M. Summers, A new 2.5
D representation for lymph node detection using random sets of deep convolutional neural network observations,
Int. Conf. Med. Image Comput. Comput.-Ass. Interv. 2014, pp. 520–527.
[48] T. Sasaki, Y. Hata, Y. Ando, M. Ishikawa and H. Ishikawa, Fuzzy rule-based approach to segment the menisci region from MR images, In Medical Imaging 1999: Image Processing, Int. Soc. Opt. Photon. 3661 (1999), 258–265.
[49] A. Saygılı and S. Albayrak, A new computer-based approach for fully automated segmentation of knee meniscus from magnetic resonance images, Biocybern. Biomed. Eng. 37 (2017), no. 3, 432–425.
[50] A. Saygılı and S. Albayrak, An efficient and fast computer-aided method for fully automated diagnosis of meniscal tears from magnetic resonance images, Artif. Intell. Med. 97 (2019), no. 13, 118–130.
[51] A. Saygili, H. Kaya and S. Albayrak, Automatic detection of meniscal area in the knee MR images, Signal Process. Commun. Appl. Conf. (SIU), 2016, pp. 1337–1340.
[52] A. Saygılı and S. Varlı, Automated diagnosis of meniscus tears from MRI of the knee, Int.Sci. Vocat. Stud. J. 3 (2019), no. 2, 92–104.
[53] B. Schmauch, P. Herent, P. Jehanno, O. Dehaene, C. Saillard, C. Aub´e, A. Luciani, N. Lassau and S. J´egou, Diagnosis of focal liver lesions from ultrasound using deep learning, Diagn. Intervent. Imag. 100 (2019), no. 4, 227–233.
[54] H. Seim, D. Kainmueller, H. Lamecker, M. Bindernagel, J. Malinowski and S. Zachow, Model-based autosegmentation of knee bones and cartilage in MRI data, Proc. MICCAI Workshop Med. Image Anal. Clinic, 2010, pp. 215–223.
[55] M.S.M. Swamy and M.S. Holi, Knee joint menisci visualization and detection of tears by image processing, Int. Conf. Comput. Commun. Appl. ICCCA 2012, 2012, pp. 1–5.
[56] M.S. Swanson, J.W. Prescott and T.M. Best, Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees, Osteoarthritis Cartilage 18 (2010), no. 3, 344–353.
[57] J.G. Tamez-Pe˜na, S. Totterman and K.J. Parker, Unsupervised statistical segmentation of multispectral volumetric MRI images, Proc. SPIE 3661 (1999), 300–311.
[58] C.-H. Tsai, N. Kiryati, E. Konen, I. Eshed and A. Mayer, Knee injury detection using MRI with efficiently-layered network (ELNet), Med. Imag. Deep Learn. PMLR, 2020 (2020), 784–794.
[59] T. Urakawa, Y. Tanaka, S. Goto, H. Matsuzawa, K. Watanabe and N. Endo, Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network, Skelet. Radiol. 48 (2019), no. 2, 239–244.
[60] M.H.F. Zarandi, A. Khadangi, F. Karimi and I.B. Turksen, A computer-aided type-II fuzzy image processing for diagnosis of meniscus tear, J. Digit. Imag. 29 (2016), no. 6, 677–695.
[61] J. Zbontar, F. Knoll, A. Sriram, T. Murrell, Z. Huang, M.J. Muckley, A. Defazio, R. Stern, P. Johnson, M. Bruno, M. Parente, K.J. Geras, J. Katsnelson, H. Chandarana, Z. Zhang, M. Drozdzal, A. Romero, M. Rabbat, P. Vincent, N. Yakubova, J. Pinkerton, D. Wang, E. Owens, C.L. Zitnick, M.P. Recht, D.K. Sodickson and Y.W. Lui, fastMRI: An open dataset and benchmarks for accelerated MRI, arXiv:1811.08839, (2019).
[62] K. Zhang, W. Lu and P. Marziliano, The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images, Mach. Vis. Appl. 24 (2013), no. 7, 1459–1472.
[63] R. Zhao, Y. Zhang, B. Yaman, M.P. Lungren and M.S. Hansen, End-to-end AI-based MRI reconstruction and lesion detection pipeline for evaluation of deep learning image reconstruction, arXiv preprint arXiv:2109.11524, (2021).
[64] B. Zikria, N. Hafezi-Nejad, F.W. Roemer, A. Guermazi and S. Demehri, Meniscal surgery: Risk of radiographic joint space narrowing progression and subsequent knee replacement-data from the osteoarthritis initiative, Radiol. 282 (2017), no. 3, 807–816.
Volume 13, Issue 2
July 2022
Pages 691-708
  • Receive Date: 04 February 2022
  • Revise Date: 18 March 2022
  • Accept Date: 10 April 2022