Automated Diagnosis of Meniscus Tears from MRI of the Knee

Year 2019, Volume: 3 Issue: 2, 92 - 104, 31.12.2019

Ahmet Saygılı Songül Varlı

Abstract

Meniscus tears are serious knee abnormalities that can cause knee
osteoarthritis disorder. Therefore, early detection and treatment of meniscus
tears that may occur in the knee with computer-aided systems will prevent the
progression of these disorders. In this study, an approach which can detect the
meniscus tears automatically by using and comparing two different feature
extraction methods have been presented. With these methods, features of the
knee MR images were obtained and automatic meniscus tear classification was
performed by such features. Four different classifiers have been used to model
the features in the classification phase. The most successful classification
results were obtained from the support vector machines (SVM) with a success
rate of 90.13% and the extreme learning machines (ELM) with a success rate of
87.85% via the LBP feature extraction method. It is observed that better
results are obtained than the ones in similar studies in the literature. It is
aimed to improve the existing success with the use of deep feature extraction
methods in the future.

Keywords

Diagnosis; knee joint; HOG, LBP, meniscus tear, medical image processing

Supporting Institution

TÜBİTAK

Project Number

116E151

Thanks

The OAI is a public-private partnership comprised of five contracts (N01-AR-2-2258; N01-AR-2-2259; N01-AR-2-2260; N01-AR-2- 2261; N01-AR-2-2262) funded by the National Institutes of Health, a branch of the Department of Health and Human Services, and conducted by the OAI Study Investigators. Private funding partners include Merck Research Laboratories; Novartis Pharmaceuticals Corporation, GlaxoSmithKline; and Pfizer, Inc. Private sector funding for the OAI is managed by the Foundation for the National Institutes of Health. This manuscript was prepared using an OAI public use data set and does not necessarily reflect the opinions or views of the OAI investigators, the NIH, or the private funding partners. This study was supported by Turkish Scientific and Technical Research Council-TÜBİTAK (Project Number: 116E151).

References

• [1] Dalal N, Triggs B. "Histograms of oriented gradients for human detection". IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, USA, 881, 886-893, 25 June 2005.[2] Ojala T, Pietikäinen M, Harwood D. "A comparative study of texture measures with classification based on featured distributions". Pattern recognition, 29(1), 51-59, 1996.[3] Ojala T, Pietikainen M, Harwood D. "Performance evaluation of texture measures with classification based on Kullback discrimination of distributions". Pattern Recognition, Computer Vision & Image Processing, Proceedings of the 12th IAPR International Conference, Jerusalem, Israel, 582-585, 9-13 October 1994.[4] Carcagnì P, Coco M, Leo M, Distante C. "Facial expression recognition and histograms of oriented gradients: a comprehensive study". SpringerPlus, 4(1), 645, 2015.[5] Déniz O, Bueno G, Salido J, De la Torre F. "Face recognition using Histograms of Oriented Gradients". Pattern Recognition Letters, 32(12), 1598-1603, 2011.[6] Moore S, Bowden R. "Local binary patterns for multi-view facial expression recognition". Computer Vision and Image Understanding, 115(4), 541-558, 2011.[7] Gabor D, "Theory of communication. Part 1: The analysis of information". Journal of the Institution of Electrical Engineers-Part III: Radio and Communication Engineering, 93(26), 429-441, 1946.[8] Zhang F, Song Y, Cai W, Lee MZ, Zhou Y, Huang H, Shan S, Fulham MJ, Feng DD. "Lung nodule classification with multilevel patch-based context analysis". IEEE Transactions on Biomedical Engineering, 61(4), 1155-1166, 2014.[9] Bay H, Tuytelaars T, Van Gool L. "Surf: Speeded up robust features". Computer vision–ECCV, 404-417, 2006.[10] Tan X, Triggs B. "Fusing Gabor and LBP feature sets for kernel-based face recognition". International Workshop on Analysis and Modeling of Faces and Gestures, Rio de Janeiro, Brasil, 235-249, 20 October 2007.[11] Conde C, Moctezuma D, De Diego IM, Cabello E. "HoGG: Gabor and HoG-based human detection for surveillance in non-controlled environments". Neurocomputing, 100:19-30, 2013.[12] Ghosh P, Taylor TK. "The Knee Joint Meniscus: A Fibrocartilage of Some Distinction". Clinical orthopaedics and related research, 224, 52-63, 1987.[13] Seedhom B, Dowson D, Wright V. "Functions of the menisci. A preliminary study". Annals of the rheumatic diseases, 33(1), 111, 1974.[14] De Smet AA, Norris M, Yandow D, Quintana F, Graf B, Keene J. "MR diagnosis of meniscal tears of the knee: importance of high signal in the meniscus that extends to the surface". AJR American journal of roentgenology, 161(1), 101-107, 1993.[15] Dam EB, Lillholm M, Marques J, Nielsen M. "Automatic segmentation of high-and low-field knee MRIs using knee image quantification with data from the osteoarthritis initiative". Journal of Medical imaging, 2(2), 024001-024001, 2015.[16] Fripp J, Bourgeat P, Engstrom C, Ourselin S, Crozier S, Salvado O. "Automated segmentation of the menisci from MR images". Biomedical Imaging: From Nano to Macro, ISBI'09 IEEE International Symposium, Boston, USA, 510-513, 28 June-1 July 2009.[17] Kim MJ, Yoo JH, Hong H. "Automatic Segmentation of the meniscus based on Active Shape Model in MR Images through Interpolated Shape Information". Journal of KIISE: Computing Practices and Letters, 16(11), 1096-1100, 2010.[18] Paproki A, Engstrom C, Chandra SS, Neubert A, Fripp J, Crozier S. "Automated segmentation and analysis of normal and osteoarthritic knee menisci from magnetic resonance images–data from the Osteoarthritis Initiative". Osteoarthritis and Cartilage, 22(9), 1259-1270, 2014.[19] Swanson M, Prescott J, Best T, Powell K, Jackson R, Haq F, Gurcan M. "Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees". Osteoarthritis and cartilage, 18(3), 344-353, 2010.[20] Zhang K, Lu W, Marziliano P. "The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images. Machine vision and applications, 24(7), 1459-1472, 2013.[21] Hata Y, Kobashi S, Tokimoto Y, Ishikawa M, Ishikawa H. "Computer aided diagnosis system of meniscal tears with T1 and T2 weighted MR images based on fuzzy inference". Lecture notes in computer science, 55-58, 2001.[22] Boniatis I, Panayiotakis G, Panagiotopoulos E. "A computer-based system for the discrimination between normal and degenerated menisci from magnetic resonance images". Imaging Systems and Techniques, IST 2008 IEEE International Workshop, Chania, Island of Crete, Greece, 335-339, 10-11 September 2008.[23] Köse C, Gençalioğlu O, Şevik U. "An automatic diagnosis method for the knee meniscus tears in MR images". Expert Systems with Applications, 36(2, Part 1), 1208-1216, 2009.[24] Ramakrishna B, Liu W, Saiprasad G, Safdar N, Chang CI, Siddiqui K, Kim W, Siegel E, Chai JW, Chen CC. "An automatic computer-aided detection system for meniscal tears on magnetic resonance images". IEEE transactions on medical imaging, 28(8), 1308-1316, 2009.[25] Fu JC, Lin CC, Wang CN, Ou YK. "Computer-aided diagnosis for knee meniscus tears in magnetic resonance imaging". Journal of Industrial and Production Engineering, 30(2), 67-77, 2013.[26] Zarandi MF, Khadangi A, Karimi F, Turksen I. "A Computer-Aided Type-II Fuzzy Image Processing for Diagnosis of Meniscus Tear". Journal of digital imaging, 29(6), 677-695, 2016.[27] Saygili A, Albayrak S. "Meniscus segmentation and tear detection in the knee MR images by fuzzy c-means method". Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey, 1-4, 15-18 May 2017.[28] Hayashi D, Roemer FW, Jarraya M, Guermazi A. "Imaging of Osteoarthritis". Geriatric Imaging, 93-121, 2013.[29] Belo J, Berger M, Koes B, Bierma-Zeinstra S. "The prognostic value of the clinical ACR classification criteria of knee osteoarthritis for persisting knee complaints and increase of disability in general practice". Osteoarthritis and cartilage, 17(10), 1288-1292, 2009.[30] Arthritis Foundation. "What is Osteoarthritis?". [http://www.arthritis.org/about-arthritis/types/osteoarthritis/what-is-osteoarthritis.php] (01.05.2018).[31] Schiphof D, de Klerk BM, Koes BW, Bierma S. "Good reliability, questionable validity of 25 different classification criteria of knee osteoarthritis: a systematic appraisal". Journal of clinical epidemiology, 61(12), 1205-1215, 2008.[32] Iijima H, Aoyama T, Nishitani K, Ito H, Fukutani N, Isho T, Kaneda E, Kuroki H, Matsuda S. "Coexisting lateral tibiofemoral osteoarthritis is associated with worse knee pain in patients with mild medial osteoarthritis". Osteoarthritis and cartilage, 25(8), 1274-1281, 2017.[33] Elbaz A, Mor A, Segal G, Debi R, Shazar N, Herman A. "Novel classification of knee osteoarthritis severity based on spatiotemporal gait analysis". Osteoarthritis and cartilage, 22(3), 457-463, 2014.[34] Edwards M, Paccou J, Ward K, Jameson K, Moss C, Woolston J, Javaid M, Cooper C, Dennison E. "The relationship of bone properties using high resolution peripheral quantitative computed tomography to radiographic components of hip osteoarthritis". Osteoarthritis and cartilage, 25(9), 1478-1483, 2017.[35] Hardcastle S, Dieppe P, Gregson C, Arden N, Spector T, Hart D, Edwards M, Dennison E, Cooper C, Sayers A. "Individuals with high bone mass have an increased prevalence of radiographic knee osteoarthritis". Bone, 71, 171-179, 2015.[36] Boesen M, Ellegaard K, Henriksen M, Gudbergsen H, Hansen P, Bliddal H, Bartels E, Riis R. "Osteoarthritis year in review 2016: imaging". Osteoarthritis and cartilage, 25(2), 216-226, 2017.[37] Wang Y, Teichtahl A, Cicuttini FM. "Osteoarthritis year in review 2015: imaging". Osteoarthritis and cartilage, 24(1), 49-57, 2016.[38] WebMD Medical Team. "Knee Injury and Meniscus Tear". [http://www.webmd.com/fitness-exercise/tc/meniscus-tear-topic-overview#1] (02.06.2018).[39] WebMD Medical Team. "Meniscus Tears". [http://orthoinfo.aaos.org/topic.cfm?topic=a00358] (02.06.2018).[40] Rauscher I, Stahl R, Cheng J, Li X, Huber MB, Luke A, Majumdar S, Link TM. "Meniscal Measurements of T1ρ and T2 at MR Imaging in Healthy Subjects and Patients with Osteoarthritis". Radiology, 249(2), 591-600, 2008.[41] Bowers ME, Tung GA, Fleming BC, Crisco JJ, Rey J. "Quantification Of Meniscal Volume By Segmentation Of 3t Magnetic Resonance Images". Journal of biomechanics, 40(12), 2811-2815, 2007.[42] Gornale SS, Patravali PU, Marathe KS, Hiremath PS. "Determination of Osteoarthritis Using Histogram of Oriented Gradients and Multiclass SVM". International Journal of Image, Graphics & Signal Processing, 9(12), 2017.[43] Saygılı A, Albayrak S. "A new computer-based approach for fully automated segmentation of knee meniscus from magnetic resonance images". Biocybernetics and Biomedical Engineering, 37(3), 432-442, 2017.[44] Saygili A, Kaya H, Albayrak S. "Automatic detection of meniscal area in the knee MR images". Signal Processing and Communication Application Conference (SIU), Zonguldak, Turkey, 1337-1340, 16-19 May 2016.[45] Tiulpin A, Thevenot J, Rahtu E, Saarakkala S. "A novel method for automatic localization of joint area on knee plain radiographs". Scandinavian Conference on Image Analysis, Tromso, Norway, 290-301, 12-14 June 2017.[46] Huang D, Shan C, Ardabilian M, Wang Y, Chen L. "Local binary patterns and its application to facial image analysis: a survey". IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 41(6), 765-781, 2011.[47] Finnilä MA, Thevenot J, Aho OM, Tiitu V, Rautiainen J, Kauppinen S, Nieminen MT, Pritzker K, Valkealahti M, Lehenkari P, "Association between subchondral bone structure and osteoarthritis histopathological grade". Journal of Orthopaedic Research, 35(4), 785-792, 2017.[48] Thevenot J, Chen J, Finnilä M, Nieminen M, Lehenkari P, Saarakkala S, Pietikäinen M, "Local binary patterns to evaluate trabecular bone structure from micro-CT data: application to studies of human osteoarthritis". European Conference on Computer Vision, Zurich, Germany, 63-79, 6-12 September 2014.[49] Pietikäinen M, Hadid A, Zhao G, Ahonen T. "Local binary patterns for still images". Computer vision using local binary patterns, 13-47, 2011.[50] Ojala T, Pietikainen M, Maenpaa T. "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns". IEEE Transactions on pattern analysis and machine intelligence, 24(7), 971-987, 2002.[51] Liu Z-G, Yang Y, Ji XH. "Flame detection algorithm based on a saliency detection technique and the uniform local binary pattern in the YCbCr color space". Signal, Image and Video Processing, 10(2), 277-284, 2016.[52] Nevitt M, Felson D, Lester G. "The osteoarthritis initiative, Protocol for the Cohort Study". http://oai.epi-ucsf.org/datarelease/docs/StudyDesignProtocol.pdf. (02.05.2018)[53] Bloecker K, Guermazi A, Wirth W, Kwoh CK, Resch H, Hunter DJ, Eckstein F. "Correlation of semiquantitative vs quantitative MRI meniscus measures in osteoarthritic knees: results from the Osteoarthritis Initiative". Skeletal Radiology, 43(2), 227-232, 2014.