Abstract
As the most frequent cause of physical disability, musculoskeletal diseases such as arthritis and osteoporosis have a great social and economical impact. Quantitative magnetic resonance imaging (MRI) biomarkers are important tools that allow clinicians to better characterize, monitor, and even predict musculoskeletal disease progression. Post-processing pipelines often include image segmentation. Manually identifying the border of the region of interest (ROI) is a difficult and time-consuming task. Manual segmentation is also affected by inter- and intrauser variability, thus limiting standardization. Fully automatic or semi-automatic methods that minimize the user interaction are highly desirable. Unfortunately, an ultimate, highly reliable and extensively evaluated solution for joint and musculoskeletal tissue segmentation has not yet been proposed, and many clinical studies still adopt fully manual procedures. Moreover, the clinical translation of several promising quantitative MRI techniques is highly affected by the lack of an established, fast, and accurate segmentation method. The goal of this review is to present some of the techniques proposed in recent literature that have been adopted in clinical studies for joint and musculoskeletal tissue analyses in arthritis patients. The most widely used MRI sequences and image processing algorithms employed to accomplish segmentation challenges will be discussed in this paper.
Similar content being viewed by others
References
The burden of musculoskeletal diseases 2009 Rosemont, IL, USA: usbjd.org. 2008. http://www.boneandjointburden.org
Woolf AD, Pfleger B (2003) Burden of major musculoskeletal conditions. Bull World Health Organ 81(9):646–656
Barbour KE, Helmick CG, Theis KA, Murphy LB, Hootman JM, Brady TJ, Cheng YJ (2013) Prevalence of doctor-diagnosed arthritis and arthritis-attributable activity limitation—United States, 2010–2012. Morb Mortal Wkly Rep 62(44):869–873
Hawamdeh Ziad M, Al-Ajlouni Jihad M (2013) The clinical pattern of knee osteoarthritis in Jordan: a hospital based study. Int J Med Sci 10(6):790–795
Lohmander L, Englund P, Dahl L, Roos E (2007) The long term consequence of anterior cruciate ligament and meniscus injuries: Osteoarthritis. Am J Sports Med 35(10):1756–1769
Helmick CG, Felson DT, Lawrence RC, Gabriel S, Hirsch R, Kwoh CK, Liang MH, Kremers HM, Mayes MD, Merkel PA, Pillemer SR, Reveille JD, Stone JH, National Arthritis Data Workgroup (2008) Estimates of the prevalence of arthritis and other rheumatic conditions in the United States. Part I. Arthritis Rheum 58(1):15–25
Wright NC, Looker AC, Saag KG, Curtis JR, Delzell ES, Randall S, Dawson-Hughes B (2014) The recent prevalence of osteoporosis and low bone mass in the United States based on bone mineral density at the femoral neck or lumbar spine. J Bone Miner Res 29(11):2520–2526
Menashe L, Hirko K, Losina E, Kloppenburg M, Zhang W, Li L, Hunter DJ (2012) The diagnostic performance of MRI in osteoarthritis: A systematic review and meta-analysis. Osteoarthritis Cartilage 20(1):13–21
McQueen F, Stewart N, Crabbe J, Robinson E, Yeoman S, Tan P, McLean L (1999) Magnetic resonance imaging of the wrist in early rheumatoid arthritis reveals progression of erosions despite clinical improvement. Ann Rheum Dis 58(3):156–163
McQueen F, Benton N, Perry D, Crabbe J, Robinson E, Yeoman S, McLean L, Stewart N (2003) Bone edema scored on magnetic resonance imaging scans of the dominant carpus at presentation predicts radiographic joint damage of the hands and feet 6 years later in patients with rheumatoid arthritis. Arthritis Rheum 48(7):1814–1827
Hetland M, Ejbjerg B, Horslev-Petersen K, Jacobsen S, Vestergaard A, Jurik A, Stengaard-Pedersen K, Junker P, Lottenburger T, Hansen I, Andersen L, Tarp U, Skjødt H, Pedersen J, Majgaard O, Svendsen A, Ellingsen T, Lindegaard H, Christensen A, Vallø J, Torfing T, Narvestad E, Thomsen H, Ostergaard M (2008) MRI bone oedema is the strongest predictor of subsequent radiographic progression in early rheumatoid arthritis. Results from a 2 yeas randomized controlled trial (CIMESTRA). Ann Rheum Dis 67(7):998–1003
Link Thomas M (2012) Osteoporosis imaging: State of the art and advanced imaging. Radiology 263(1):3–17
Gonzalez RC, Woods RE (2001) Digital image processing, 2nd edn. Addison-Wesley, Boston
Weckbach S, Mendlik T, Horger W, Wagner S, Reiser MF, Glaser C (2006) Quantitative assessment of patellar cartilage volume and thickness at 3.0 tesla comparing a 3D-fast low angle shot versus a 3D-true fast imaging with steady-state precession sequence for reproducibility. Invest Radiol 41(2):189–197
Eckstein F, Kunz M, Schutzer M, Hudelmaier M, Jackson RD, Yu J, Eaton CB, Schneider E (2007) Two year longitudinal change and test-retest-precision of knee cartilage morphology in a pilot study for the osteoarthritis initiative. Osteoarthritis Cartilage 15(11):1326–1332
Schneider E, Nevitt M, McCulloch C, Cicuttini FM, Duryea J, Eckstein F, Tamez-Pena J (2012) Equivalence and precision of knee cartilage morphometry between different segmentation teams, cartilage regions, and MR acquisitions. Osteoarthritis Cartilage 20(8):869–879
Jordan CD, McWalter EJ, Monu UD, Watkins RD, Chen W, Bangerter NK, Hargreaves BA, Gold GE (2014) Variability of CubeQuant T1ρ, quantitative DESS T2, and cones sodium MRI in knee cartilage. Osteoarthritis Cartilage 22(10):1559–1567
Li X, Pedoia V, Kumar D, Rivoire J, Wyatt C, Lansdown D, Amano K, Okazaki N, Savic D, Koff MF, Felmlee J, Williams SL, Majumdar S (2015) Cartilage T1ρ and T2 relaxation times: Longitudinal reproducibility and variations using different coils, MR systems and sites. Osteoarthritis Cartilage 23(12):2214–2223
Pedoia V, Li X, Su F, Calixto N, Majumdar S (2015) Fully automatic analysis of the knee articular cartilage T1ρ relaxation time using voxel-based relaxometry. J Magn Reson Imaging (Epub ahead of print)
Eckstein F, Kwoh CK, Boudreau RM, Wang Z, Hannon MJ, Cotofana S, Hudelmaier MI, Wirth W, Guermazi A, Nevitt MC, John MR, Hunter DJ, OAI investigators (2013) Quantitative MRI measures of cartilage predict knee replacement: A case-control study from the Osteoarthritis Initiative. Ann Rheum Dis 72(5):707–714
Neogi Tuhina, Bowes Michael A, Niu Jingbo, De Souza Kevin M, Vincent Graham R, Goggins Joyce, Zhang Yuqing, Felson David T (2013) Magnetic resonance imaging-based three-dimensional bone shape of the knee predicts onset of knee osteoarthritis. Arthritis Rheum 68(8):2048–2058
Pedoia V, Lansdown DA, Zaid M, McCulloch CE, Souza R, Ma CB, Li X (2015) Three-dimensional MRI-based statistical shape model and application to a cohort of knees with acute ACL injury. Osteoarthritis Cartilage 23(10):1695–1703
Lansdown DA, Zaid M, Pedoia V, Subburaj K, Souza R, Benjamin C, Li X (2014) Reproducibility measurements of three methods for calculating in vivo MR-based knee kinematics. J Magn Reson Imaging 42(2):533–538
Zaid M, Lansdown D, Su F, Pedoia V, Tufts L, Rizzo S, Souza RB, Li X, Ma CB (2015) Abnormal tibial position is correlated to early degenerative changes 1 year following ACL reconstruction. J Orthop Res 33(7):1079–1086
Lohmander L, Ionescu M, Jugessur H, Poole A (1999) Changes in joint cartilage aggrecan after knee injury and in osteoarthritis. Arthritis Rheum 42:534–544
Price J, Till S, Bickerstaff D, Bayliss M, Hollander A (1999) Degradation of cartilage type II collagen precedes the onset of osteoarthritis following anterior cruciate ligament rupture. Arthritis Rheum 42:2390–2398
Dunn TC, Lu Y, Jin H, Ries MD, Majumdar S (2004) T2 relaxation time of cartilage at MR imaging: Comparison with severity of knee osteoarthritis. Radiology 232:592–598
Li X, Ma C, Link T et al (2007) In vivo T1ρ and T2 mapping of articular cartilage in osteoarthritis of the knee using 3 Tesla MRI. Osteoarthritis Cartilage 15(7):789–797
Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models-their training and application. Comput Vis Image Underst 1995(61):38–59
Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681–685
Solloway S, Hutchinson CE, Waterton JC, Taylor CJ (1997) The use of active shape models for making thickness measurements of articular cartilage from MR images. Magn Reson Med 37(6):943–952
Seim H, Kainmueller D, Lamecker H, Bindernagel M, Malinowski J, Zachow S (2010) Model-based Auto-Segmentation of Knee Bones and Cartilage in MRI Data MICCAI 2010 Workshop Medical Image Analysis for the Clinic—A Grand Challenge (SKI0) pp 215–223
Heimann T, Morrison BJ, Styner MA, Niethammer M, Warfield SK (2010) Segmentation of Knee Images: A Grand Challenge www.ski10.org
Vincent G, Wolstenholme C, Scott I, Bowes M (2011) Fully Automatic Segmentation of the Knee Joint using Active Appearance Models Data MICCAI 2010 Workshop Medical Image Analysis for the Clinic—A Grand Challenge (SKI0)
Williams TG, Vincent G, Bowes M, Cootes T, Balamoody S, Hutchinson C, Waterton JC, Taylor CJ (2010) Automatic segmentation of bones and inter-image anatomical correspondence by volumetric statistical modelling of knee MRI. Biomedical Imaging: From Nano to Macro, 2010 IEEE International Symposium on, pp 432–435
Williams TG, Holmes AP, Waterton JC, Maciewicz RA, Hutchinson CE, Moots Nash RJ, Taylor CJ (2010) Anatomically corresponded regional analysis of cartilage in asymptomatic and osteoarthritic knees by statistical shape modelling of the bone. IEEE Trans Med Imag 29(8):1541–1559
Tamez-Pena J, Gonzalez J, Farber J, Baum K, Schreyer E, Toterman S (2011) Atlas based method for the automated segmentation and quantification of knee features: Data from the osteoarthritis initiative, in Proceeding IEEE International Symposium Biomedical Imaging pp 1484–1487
Shan L, Charles C, Niethammer M (2012) Automatic multi-atlas-based cartilage segmentation from knee MR images, Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on, pp 1028–1031
Shan L, Zach C, Charles C, Niethammer M (2014) Automatic atlas-based three-label cartilage segmentation from MR knee images. Med Image Anal 18(7):1233–1246
Carballido-Gamio J, Majumdar S (2011) Atlas-based knee cartilage assessment. Magn Reson Med 66(2):574–583
Shamonin DP, Bron EE, Lelieveldt BPF, Smith M, Klain S, Starting M, Alzheimer’s Desease Neuroimeging Initiative (2014) Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer’s disease. Front Neuroinform. doi:10.3389/fninf.2013.00050
Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW (2010) Elastix: A toolbox for intensity-based medical image registration. IEEE Trans Med Imaging 29:196–205
Glocker B, Sotiras A, Komodakis N, Paragios N (2011) Deformable medical image registration: Setting the state of the art with discrete methods. Annu Rev Biomed Eng 15(13):219–244
Boykov Y, Veksler O (2001) Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell 23(11):1222–1239
Shim H, Chang S, Tao C, Wang JH, Kwoh CK, Bae KT (2009) Knee cartilage: Efficient and reproducible segmentation on high-spatial-resolution MR images with the semiautomated graph-cut algorithm method. Radiology 251(2):548–556
Ababneh SY, Prescott JW, Gurcan MN (2011) Automatic graph-cut based segmentation of bones from knee magnetic resonance images for osteoarthritis research. Med Image Anal 15(4):438–448
Jain V, Seung HS, Turaga SC (2010) Machines that learn to segment images: A crucial technology for connectomics. Curr Opin Neurobiol 20(5):653–666
Folkesson J, Dam E, Olsen OF, Pettersen P, Christiansen C (2005) Automatic segmentation of the articular cartilage in knee MRI using a hierarchical multi-class classification scheme. Med Image Comput Comput Assist Interv 8(Pt 1):327–334
Folkesson J, Dam EB, Olsen OF, Pettersen PC, Christiansen C (2007) Segmenting articular cartilage automatically using a voxel classification approach. IEEE Trans Med Imaging 26(1):106–115
Prasoon A, Igel C, Loog M, Lauze F, Dam EB, Nielsen M (2013) Femoral cartilage segmentation in Knee MRI scans using two stage voxel classification, Engineering in Medicine and Biology Society (EMBC), 35th Annual International Conference of the IEEE, pp 5469–5472
Zhang K, Lu W, Marziliano P (2013) Automatic knee cartilage segmentation from multi-contrast MR images using support vector machine classification with spatial dependencies. Magn Reson Imaging 31(10):1731–1743
Zhang K, Lu W (2011) Automatic human knee cartilage segmentation from multi-contrast MR images using extreme learning machines and discriminative random fields. In Proceedings of the Second international conference on Machine learning in medical imaging, pp 335–343
Pang J, Li P, Qiu M, Chen W, Qiao L (2015) Automatic articular cartilage segmentation based on pattern recognition from knee MRI images. J Digit Imaging (Epub ahead of print)
Prasoon A, Petersen K, Igel C, Lauze F, Dam E, Nielsen M (2013) Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. Med Image Comput Comput Assist Interv 16:246–253
Ciresan DC, Giusti A, Gambardella LM, Schmidhuber J (2013) Mitosis detection in breast cancer histology images with deep neural networks. Med Image Comput Comput Assist Interv 16:411–418
Cires C, Gambardella L, Schmidhuber J (2012) Deep neural networks segment neuronal membranes in electron microscopy images NIPS: Twenty-sixth Conference on Neural Information Processing Systems; Harrahs and Harveys, Lake Tahoe, pp 2852–2860
Yin Y, Williams R, Anderson DD, Sonka M (2010) Hierarchical Decision Framework with a Priori Shape Models for Knee Joint Cartilage Segmentation MICCAI 2010 Workshop Medical Image Analysis for the Clinic—A Grand Challenge (SKI0) pp 241–250
Lee S, Park SH, Shim H, Yun D, Lee S (2011) Optimization of local shape and appearance probabilities for segmentation of knee cartilage in 3-D MR images. Comput Vis Image Underst 115(12):1710–1720
Wang Z, Donoghue C, Rueckert D (2013) Patch-based segmentation without registration: Application to knee MRI lecture notes in computer science machine learning in medical. Imaging 8184(2013):98–105
Lee JG, Gumus S, Moon CH, Kwoh CK, Bae KT (2014) Fully automated segmentation of cartilage from the MR images of knee using a multi-atlas and local structural analysis method. Med Phys 41(9):092303
Wang Q, Wu D, Lu L, Liu M, Boyer KL, Zhou SK (2014) Semantic Context Forests for Learning-Based Knee Cartilage Segmentation in 3D MR Images. Medical Computer Vision. Large Data in Medical Imaging Lecture Notes in Computer Science, vol 8331. Springer, Newyork, pp 105–115
Xia Y, Chandra SS, Engstrom C, Strudwick MW, Crozier S, Fripp J (2014) Automatic hip cartilage segmentation from 3D MR images using arc-weighted graph searching. Phys Med Biol 59(23):7245–7266
Cheng Y, Guo C, Wang Y, Bai J, Tamura S (2013) Accuracy limits for the thickness measurement of the hip joint cartilage in 3D MR images: Simulation and validation. IEEE Trans Biomed Eng 60(2):517–533
Baniasadipour A, Zoroofi RA, Sato Y, Nishii T, Nakanishi K, Tanaka H, Sugano N, Yoshikawa H, Nakamura H, Tamura S (2007) A fully automated method for segmentation and thickness map estimation of femoral and acetabular cartilages in 3D CT images of the hip 5th International Symposium on Image and Signal Processing and Analysis, pp 92–97
Naish JH, Xanthopoulos E, Hutchinson CE, Waterton JC, Taylor CJ (2006) MR measurement of articular cartilage thickness distribution in the hip. Osteoarthritis Cartilage 14:967–973
Li W, Abram F, Beaudoin G, Berthiaume M-J, Pelletier J-P, Martel-Pelletier J (2008) Human hip joint cartilage: MRI quantitative thickness and volume measurements discriminating acetabulum and femoral head. IEEE Trans Biomed Eng 55(12):2731–2740
Carballido-Gamio J, Link TM, Li X, Han ET, Krug R, Ries MD, Majumdar S (2008) Feasibility and reproducibility of relaxometry, morphometric, and geometrical measurements of the hip joint with magnetic resonance imaging at 3T. J Magn Reson Imaging 28:227–235
Carballido-Gamio J, Bauer JS, Stahl R et al (2008) Inter-subject comparison of MRI knee cartilage thickness. Med Image Anal 12(2):120–135
Siversson C, Akhondi-Asl A, Bixby S, Kim YJ, Warfield SK (2014) Three-dimensional hip cartilage quality assessment of morphology and dGEMRIC by planar maps and automated segmentation. Osteoarthritis Cartilage 22(10):1511–1515
Ostergaard M, Peterfy C, Conaghan P, McQueen F, Bird P, Ejbjerg B, Shnier R, O’Connor P, Klarlund M, Emery P, Genant H, Lassere M, Edmonds J (2003) OMERACT rheumatoid arthritis magnetic resonance imaging studies. Core set of MRI acquisitions, joint pathology definitions, and the OMERACT RA-MRI scoring system. J Rheumatol 30(6):1385–1386
Koch M, Schwing AG, Comaniciu D, Pollefeys M (2011) Fully automatic segmentation of wrist bones for arthritis patients, Biomedical Imaging: From Nano to Macro, IEEE International Symposium on, pp 636–640
Włodarczyk J, Czaplicka K, Tabor Z, Wojciechowski W, Urbanik A (2015) Segmentation of bones in magnetic resonance images of the wrist. Int J Comput Assist Radiol 10(4):419–431
Hetland ML, Stengaard-Pedersen K, Junker P et al (2010) Radiographic progression and remission rates in early rheumatoid arthritis MRI bone oedema and anti-CCP predicted radiographic progressionin the 5-year extension of the double-blind randomized CIMESTRA trial. Ann Rheum Dis 69:1789–1795
Li X, Ma C, Bolbos R, Stahl R, Lozano J, Zuo J, Lin K, Link T, Safran M, Majumdar S (2008) Quantitative assessment of bone marrow edema pattern and overlying cartilage in knees with osteoarthritis and anterior cruciate ligament tear using MR imaging and spectroscopic imaging. J Magn Reson Imaging 28(2):453–461
Li X, Yu A, Virayavanich W, Noworolski SM, Link TM, Imboden J (2012) Quantitative characterization of bone marrow edema pattern in rheumatoid arthritis using 3 Tesla MRI. J Magn Reson Imaging 35(1):211–218
Teruel JR, Burghardt AJ, Rivoire J, Srikhum W, Noworolski SM, Link TM, Imboden JB, Li X (2014) Bone structure and perfusion quantification of bone marrow edema pattern in the wrist of patients with rheumatoid arthritis: A multimodality study. J Rheumatol 41(9):1766–1773
Neubert A, Fripp J, Engstrom C, Schwarz R, Lauer L, Salvado O, Crozier S (2012) Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models. Phys Med Biol 57(24):8357–8376
Haq R, Aras R, Besachio DA, Borgie RC, Audette MA (2015) 3D lumbar spine intervertebral disc segmentation and compression simulation from MRI using shape-aware models. Int J Comput Assist Radiol Surg 10(1):45–54
Yang Z, Fripp J, Chandra SS, Neubert A, Xia Y, Strudwick M, Paproki A, Engstrom C, Crozier S (2015) Automatic bone segmentation and bone-cartilage interface extraction for the shoulder joint from magnetic resonance images. Phys Med Biol 60(4):1441–1459
Engstrom CM, Fripp J, Jurcak V, Walker DG, Salvado O, Crozier S (2011) Segmentation of the quadratus lumborum muscle using statistical shape modeling. J Magn Reson Imaging 33(6):1422–1429
Karlsson A, Rosander J, Romu T, Tallberg J, Grönqvist A, Borga M, Dahlqvist Leinhard O (2015) Automatic and quantitative assessment of regional muscle volume by multi-atlas segmentation using whole-body water-fat MRI. J Magn Reson Imaging 41(6):1558–1569
Gordillo N, Montseney E, Sobervilla P et al (2013) State of the art survey on MRI brain tumor segmentation. Magn Reson Imaging 31(8):1426–1438
Li Z, Chen J (2015) Superpixel Segmentation Using Linear Spectral Clustering, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in press
Long J, Shelhamer E, Darrell T (2015) Fully Convolutional Networks for Semantic Segmentation The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in press
Acknowledgments
The authors would like to thank Colin Russell for proofreading the manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest.
Rights and permissions
About this article
Cite this article
Pedoia, V., Majumdar, S. & Link, T.M. Segmentation of joint and musculoskeletal tissue in the study of arthritis. Magn Reson Mater Phy 29, 207–221 (2016). https://doi.org/10.1007/s10334-016-0532-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10334-016-0532-9