Abstract
Diagnosing spinal problems is not an easy task. Doctors collect different types of information, including magnetic resonance imaging (MRI), to make a final diagnosis and decision on treatment modality. The localization of lumbar discs on MRI images is a challenging problem due to the wide range of variability in size, shape, number and appearance of discs and vertebrae. Current state-of-the art studies show that most of the implemented methods are semi-automatic and suffer from additional correction of the solution or are very sensitive to the changes in parameters. This chapter will use two different approaches—computational modelling using finite element method to investigate the displacements and stress distribution and machine learning (ML) algorithms to perform automatic segmentation of regions of interest (vertebrae, discs). The results for segmentation show high accuracy, with possibilities for improvement. Finite element analysis, performed on a 3-dimensional model automatically created from scans using ML, for a healthy and herniated disc, can provide an additional insight into the processes and different effect of the herniated disc onto the spine (i.e. back pain). A computer diagnostic system can be helpful in generating diagnostic results in short time and represent a help in final decision making.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Al-Kafri AS et al (2019) Boundary delineation of MRI images for lumbar spinal stenosis detection through semantic segmentation using deep neural networks. IEEE Access 7:43487–43501
Allison L et al (2015) Finite element analysis predicts experimental failure patterns in vertebral bodies loaded via intervertebral discs up to large deformation. Med Eng Phys 37:599–604
Alomari RS, Corso JJ, Chaudhary V, Dhillon G (2014) Lumbar spine disc herniation diagnosis with a joint shape model. Springer, Cham, pp 87–98
Ayed IB et al (2011) Graph cuts with invariant object-interaction priors: application to intervertebral disc segmentation. Springer, Berlin, Heidelberg, s.n., pp 221–232
Baroud G, Nemes J, Heini P, Steffen T (2003) Load shift of the intervertebral disc after a vertebroplasty: a finite element study. Eur Spine J 12(4):421–426
Bhole C, Kompalli S, Chaudhary V (2009) Context sensitive labeling of spinal structure in MR images. Medical imaging 2009: computer-aided diagnosis, vol 7260. International Society for Optics and Photonics, p 72603P
Bloice MD, Roth PM, Holzinger A (2019) Biomedical image augmentation using Augmentor. Bioinformatics 35(21):4522–4524
Bloice MD, Stocker C, Holzinger A (2017) Augmentor: an image augmentation library for machine learning, p 1708.04680
Bogduk N (2016) Functional anatomy of the spine. In: Handbook of clinical neurology, vol 136. Elsevier, pp 675–688
Cai Y et al (2016) Multi-modal vertebrae recognition using transformed deep convolution network. Comput Med Imaging Graph 51:11–19
Chen CS, Cheng CK, Liu CL, Lo WH (2001) Stress analysis of the disc adjacent to interbody fusion in lumbar spine. Med Eng Phys 23(7):483–491
Chen H et al (2018) VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images. Neuroimage 170:446–455
Chen S et al (2008) Biomechanical comparison of a new stand-alone anterior lumbar interbody fusion cage with established fixation techniques—A three-dimensional finite element analysis. BMC Muscoskeletal Disorders 9(88):1–10
Chevrefils C, Chériet F, Grimard G, Aubin CE (2007) Watershed segmentation of intervertebral disk and spinal canal from MRI images. Springer, Berlin, Heidelberg, pp 1017–1027
Clinical Centre of Kragujevac Website. Available at https://www.kc-kg.rs/. Accessed 21 Dec 2020
Corso JJ, Raja’SA, Chaudhary V (2008) Lumbar disc localization and labeling with a probabilistic model on both pixel and object features. Springer, Berlin, Heidelberg, s.n., pp 202–210
Cummins J et al (2006) Descriptive epidemiology and prior healthcare utilization of patients in the spine patient outcomes research trial’s (sport) three observational cohorts: disc herniation, spinal stenosis and degenerative spondylolisthesis. Spine 31(7):806
Dietrich M, Kedzior K, Wittek A, Zagrajek T (1992) Non-linear finite element analysis of formation and treatment of intervertebral disc Herniae, pp 225–231.
Dou Q et al (2017) 3D deeply supervised network for automated segmentation of volumetric medical images. Med Image Anal 41:10–54
Dreischarf M et al (2014) Comparison of eight published static finite element models of the intact lumbar spine: predictive power of models improves when combined together. J Biomech 47:1757–1766
Du HG et al (2016) Biomechanical analysis of press-extension technique on degenerative lumbar with disc herniation and staggered facet joint. Saudi Pharmaceut J 24(3):305–311
Eberlein R, Holzapfel G, Schulze-Bauer C (2002) Assessment of a spinal implant by means of advanced FE modeling of intact human intervertebral discs. Vienna, Austria
Ebrahimzadeh E, Fayaz F, Ahmadi F, Nikravan M (2018) A machine learning-based method in order to diagnose lumbar disc herniation disease by MR image processing. MedLife Open Access 1(1):1
Fagan M, Julian S, Siddall D, Mohsen A (2002) Patient specific spine models. Part 1: finite element analysis of the lumbar intervertebral disc—A material sensitivity study. Proc Inst Mech Eng Part H 216(5):299–314
Farda NA et al (2020) Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques. Injury.
Fardon DF et al (2014) Lumbar disc nomenclature: version 2.0: recommendations of the combined task forces of the North American Spine Society, the American Society of Spine Radiology and the American Society of Neuroradiology. Spine J 14(11):2525–2545
Ferguson S, Steffen T (2003) Biomechanics of the aging spine. Eur Spine J 2:S97–S103
Filipovic N (1999) Numerical solution of coupled problems of a deformable solid body and fluid flow (In Serbian). Faculty of Mechanical Enginireeing, University of Kragujevac, Kragujevac
Ghosh S, Chaudhary V (2014) Supervised methods for detection and segmentation of tissues in clinical lumbar MRI. Comput Med Imaging Graph 38(7):639–649
Ghosh S, Raja'S A, Chaudhary V, Dhillon G (2011) Composite features for automatic diagnosis of intervertebral disc herniation from lumbar MRI, pp 5068–5071
Glema A et al (2004) Modeling of intervertebral discs in the numerical analysis of spinal segment. ECCOMAS 2004
Goto K et al (2002) Mechanical analysis of the lumbar vertebrae in a three-dimensional finite element method model in which intradiscal pressure in the nucleus pulposus was used to establish the model. J Orthopaedic Sci 7(2):243–246
Greenberg MS (2016) Spine and spinal cord. In: Handbook of neurosurgery. 8th edn. New York Thieme, p 1102
Gulli A, Pal S (2017) Deep learning with Keras. Packt Publishing Ltd.
Haq R et al (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
Harun NF, Yusof KM, Jamaludin MZ, Hassan SAHS (2012) Motivation in problem-based learning implementation. Procedia Soc Behav Sci 56:233–242
Hassan CR, Lee W, Komatsu DE Qin YX (2020) Evaluation of nucleus pulposus fluid velocity and pressure alteration induced by cartilage endplate sclerosis using a poroelastic finite element analysis. In: Biomech Model Mechanobiol 1–11
He K, Zhang X, Ren S, Sun, J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Hoad CL, Martel AL (2002) Segmentation of MR images for computer-assisted surgery of the lumbar spine. Phys Med Biol 47(19):3503
Horsfield MA et al (2010) Rapid semi-automatic segmentation of the spinal cord from magnetic resonance images: application in multiple sclerosis. Neuroimage 50(2):446–455
Jackson RP et al (1989) The neuroradiographic diagnosis of lumbar herniated nucleus pulposus: II. A comparison of computed tomography (CT), myelography, CT-myelography, and magnetic resonance. Spine 14(2):1362–1367
Jarvik JG, Deyo RA (2002) Diagnostic evaluation of low back pain with emphasis on imaging. Ann Intern Med 137(7):586–597
Jordan J, Konstantinou K, O’Dowd J (2011) Herniated lumbar disc. BMJ Clin Evidence Arch 2009:1118
Kambin P (2005) Arthroscopic and endoscopic spinal surgery: text and Atlas. Humana Press, New Jersey
Koh J, Scott PD, Chaudhary V, Dhillon G (2011) An automatic segmentation method of the spinal canal from clinical MR images based on an attention model and an active contour model. In 2011 IEEE International symposium on biomedical imaging: from nano to macro. IEEE, pp 1467–1471
Kojić M, Filipović N, Stojanović B, Kojić N (2008) Computer modeling in bioengineering: theoretical background, examples and software. John Wiley & Sons
Kojic M, Filipovic N, Živkovic M & Slavkovic G (2001) PAK-FS finite element program for fluid-structure interaction. Kragujevac, Serbia
Kovačević V et al (2017) Standard lumbar discectomy versus microdiscectomy-differences in clinical outcome and reoperation rate. Acta Clin Croat 56(3):391–398
Kurutz M (2006) Age-sensitivity of time-related in vivo deformability of human lumbar motion segments and discs in pure centric tension. J Biomech 39(1):147–157
Kurutz M, Oroszváry L (2010) Finite element analysis of weightbath hydrotraction treatment of degenerated lumbar spine segments in elastic phase. J Biomech 43(3):433–441
Kurutz M, Oroszváry L (2012) Finite element modeling and simulation of healthy and degenerated human lumbar spine. In: Finite element analysis: from biomedical applications to industrial developments. p 193.
Lavecchia CE, Espino DM, Moerman KM, Tse KM et al (2018) Lumbar model generator: a tool for the automated generation of a parametric scalable model of the lumbar spine. J R Soc Interface 15(138):20170829
Li H, Wang H (2006) Intervertebral disc biomechanical analysis using the finite element modeling based on medical images. Comput Med Imaging Graph 30(6–7):363–370
Lin N, Yu W, Duncan J (2003) Combinative multi-scale level set framework for echocardiographic image segmentation. Med Image Anal 7:529–537
Little J, Pearcy M, Adam C (2008) Are coupled rotations in the lumbar spine largely due to the osseo-ligamentous anatomy?—A modeling study. Comput Methods Biomech Biomed Eng 11(1):95–103
Liu L et al (2020) A survey on U-shaped networks in medical image segmentations. Neurocomputing 409:244–258
Longo UG et al (2011) Symptomatic disc herniation and serum lipid levels. Eur Spine J 20(10):1658–1662
Malandrino A, Planell J, Lacroix D (2009) Statistical factorial analysis on the poroelastic material properties sensitivity of the lumbar intervertebral disc under compression, flexion and axial rotation. J Biomech 42(3):341–348
Marquardt G et al (2012) Ultra-long-term outcome of surgically treated far-lateral, extraforaminal lumbar disc herniations: a single-center series. Eur Spine J 21(4):660–665
Mbarki W et al (2020) Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI. Interdisc Neurosur 22:100837
Mengoni M et al (2017) Annulus fibrosus functional extrafibrillar and fibrous mechanical behaviour: experimental and computational characterisation. Roy Soc Open Sci 4:170807
Michopoulou SK et al (2009) Atlas-based segmentation of degenerated lumbar intervertebral discs from MR images of the spine. IEEE Trans Biomed Eng 56(9):2225–2231
Milasinovic D, Vukicevic A, Filipovic N (2020) dfemtoolz: An open-source C++ framework for efficient imposition of material and boundary conditions in finite element biomedical simulations. Comput Phys Commun 249:106996.
Mobbs RJ, Newcombe RL, Chandran KN (2001) Lumbar discectomy and the diabetic patient: incidence and outcome. J Clin Neurosci 8(1):10–13
Moradi S, Alizadehasl A, Dhooge J et al (2019) MFP-Unet: a novel deep learning based approach for left ventricle segmentation in echocardiography. Phys Medica 58–69
Moramarco V, Palomar A, Pappalettere C, Doblaré M (2010a) An accurate validation of a computational model of human lumbosacral segment. J Biomech 43(2):334–342
Neubert A et al (2013) Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images. J Am Med Inform Assoc 20(6):1082–1090
Oktay AB, Akgul YS (2011) Localization of the lumbar discs using machine learning and exact probabilistic inference. Springer, Berlin, Heidelberg, s.n., pp 158–165
Park WM, Kim K, Kim YH (2013) Effects of degenerated intervertebral discs on intersegmental rotations, intradiscal pressures, and facet joint forces of the whole lumbar spine. Comput Biol Med 43:1234–1240
Pekar V et al (2007) Automated planning of scan geometries in spine MRI scans. Springer, Berlin, Heidelberg, s.n., pp 601–608
Peng B et al (2006) Possible pathogenesis of painful intervertebral disc degeneration. Spine 31(5):560–566
Peulić A, Šušteršič T, Peulić M (2019) Non-invasive improved technique for lumbar discus hernia classification based on fuzzy logic. Biomed Eng/Biomedizinische Technik 64(4):421–428
Peulić M, Joković M, Šušteršič T & Peulić A (2020) A noninvasive assistant system in diagnosis of lumbar disc herniation. Comput Math Methods Med 6320126
Ranković V et al (2015) November. A fuzzy model for supporting the diagnosis of lumbar disc herniation. Belgrade, Serbia
Rasulić L et al (2020) Viable C5 and C6 proximal stump use in reconstructive surgery of the adult brachial plexus traction injuries. Neurosurgery 86(3):400–409
Rohlmann A et al (2006a) Determination of trunk muscle forces for flexion and extension by using a validated finite element model of the lumbar spine and measured in vivo data. J Biomech 39(6):981–989
Rohlmann A, Burra N, Zander T, Bergmann G (2007) Comparison of the effect of bilateral posterior dynamic and rigid fixation devices ont he loads in the lumbar spine: a finite element analysis. Eur Spine J 16(8):1223–1231
Rohlmann A, Zander T, Bergmann G (2006b) Spinal loads after osteoporotic vertebral fractures treatedby vertebroplasty or kyphoplasty. Eur Spine J 15(8):1255–1264
Rohlmann A et al (2006c) Analysis of the influence of disc degeneration on the mechanical behaviour of a lumbar motion segment using the finite element method. J Biomech 39(13):2484–2490
Ronneberger O, Fischer P, Brox T (2015) October. U-net: convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 234–241
Ruberté L, Natarajan R, Andersson G (2009) Influence of single-level lumbar degenerative disc disease on the behavior of the adjacent segments—A finite element model study. J Biomech 42(3):341–348
Schmidt H, Heuer F, Wilke H (2009) Which axial and bending stiffnesses of posterior implants are required to design a flexible lumbar stabilization system? J Biomech 42(1):48–54
Schmidt H et al (2007a) The risk of disc prolapses with complex loading in different degrees of disc degeneration—A finite element analysis. Clin Biomech 22:988–998
Schmidt S et al (2007b) Spine detection and labeling using a parts-based graphical model. Springer, Berlin, Heidelberg, s.n., pp 122–133
Schroeder Y, Wilson W, Huyghe J, Baaijens P (2006) Osmoviscoelastic finite element mdel of the intervertebral disc. Eur Spine J 15(Suppl 3):361–371
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, vol 1409, p 1556
Steffens D et al (2016) Do MRI findings identify patients with low back pain or sciatica who respond better to particular interventions? systematic review. Eur Spine J 25(4):1170–1187
Šušteršič T, Milovanović V, Ranković V, Filipović N (2020) A comparison of classifiers in biomedical signal processing as a decision support system in disc hernia diagnosis. Comput Biol Med 125:103978
Sustersic T, Rankovic V, Peulić M, Peulic A (2019) An early disc herniation identification system for advancement in the standard medical screening procedure based on Bayes theorem. IEEE J Biomed Health Inform 24(1):151–159
Suzani A et al (2015) Fast automatic vertebrae detection and localization in pathological CT scans-a deep learning approach. In International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 678–686
Tensorflow. Available at https://www.tensorflow.org/. Accessed 5 Oct 2019
Tsai R (1987) A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE J Robot Autom 3(4):323–344
Unal Y, Polat K, Kocer HE, Hariharan M (2015) Detection of abnormalities in lumbar discs from clinical lumbar MRI with hybrid models. Appl Soft Comput 33:65–76
Vitosevic F, Rasulic L, Medenica SM (2019) Morphological characteristics of the posterior cerebral circulation: an analysis based on non-invasive imaging. Turk Neurosurg 29(5):625–630
Wang G et al (2018) Interactive medical image segmentation using deep learning with image-specific fine tuning. IEEE Trans Med Imaging 37(7):1562–1573
Wang J, Parnianpour M, Shirazi-Adl A, Engin A (2000) Viscoelastic finite element analysis of a lumbar motion segment in combined compression and sagittal flexion. Spine 25(3):310–318
Wang T et al (2019) Development of a three-dimensional finite element model of thoracolumbar kyphotic deformity following vertebral column decancellation. Appl Bionics Biomech. Article ID 5109285
Williams J, Natarajan R, Andersson G (2007) Inclusion of regional poroelastic material properties better predicts biomechanical behaviour of lumbar discs subjected to dynamic loading. J Biomech 40(9):1981–1987
Winn H (2016) Youmans & Winn neurological surgery. 7th edn. Elsevier
Xie F, Zhou H, Zhao W, Huang L (2017) A comparative study on the mechanical behavior of intervertebral disc using hyperelastic finite element model. Technol Health Care 25(S1):177–187
Yang B, Lu Y, Um C, O’Connell G (2019) Relative nucleus pulposus area and position alter disk joint mechanics. J Biomech Eng 141:051004
Yang B, O’Connell G (2017) Effect of collagen fibre orientation on intervertebral disc torsion mechanics. Biomech Model Mechanobiol 16:2005–2015
Yang B, O’Connell G (2019) Intervertebral disc swelling maintains strain homeostasis throughout the annulus fibrosus: a finite element analysis of healthy and degenerated discs. Acta Biomater 100:61–74
Zander T, Rohlmann A, Burra N, Bergmann G (2006) Effect of a posterior dynamic implant adjacent to a rigid spinal fixator. Clin Biomech 21(8):767–774
Zhang H, Zhu W (2019) The path to deliver the most realistic follower load for a lumbar spine in standing posture: a finite element study. J Biomech Eng 141(3):1–10
Zhang Q, Zhou Y, Petit D, Teo E (2009) Evaluation of load transfer characteristics of a dynamic stabilization device on disc loading under compression. Med Eng Phys 31(5):533–538
Zhong Z et al (2006) Finite element analysis of the lumbar spine with a new cage using a topology optimization method. Med Eng Phys 28(1):90–98
Zhou Y et al (2019) Automatic lumbar MRI detection and identification based on deep learning. J Digit Imaging 32(3):513–520
Acknowledgements
This research is funded by Serbian Ministry of Education, Science, and Technological Development [451-03-68/2020-14/200107 (Faculty of Engineering, University of Kragujevac)]. This research is also supported by the projects that have received funding from the European Union’s Horizon 2020 research and innovation programmes under grant agreements No 952603 (SGABU project) and No 760921 (PANBioRA project). This article reflects only the author's view. The Commission is not responsible for any use that may be made of the information it contains.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Šušteršič, T., Kovačević, V., Ranković, V., Rasulić, L., Filipović, N. (2022). Computational Modelling and Machine Learning Based Image Processing in Spine Research. In: Canciglieri Junior, O., Trajanovic, M.D. (eds) Personalized Orthopedics. Springer, Cham. https://doi.org/10.1007/978-3-030-98279-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-98279-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98278-2
Online ISBN: 978-3-030-98279-9
eBook Packages: EngineeringEngineering (R0)