Semiautomatic computer-aided classification of degenerative lumbar spine disease in magnetic resonance imaging

BACKGROUND Computer-aided diagnosis (CAD) methods for detecting and classifying lumbar spine disease in Magnetic Resonance imaging (MRI) can assist radiologists to perform their decision-making tasks. In this paper, a CAD software has been developed able to classify and quantify spine disease (disc degeneration, herniation and spinal stenosis) in two-dimensional MRI. METHODS A set of 52 lumbar discs from 14 patients was used for training and 243 lumbar discs from 53 patients for testing in conventional two-dimensional MRI of the lumbar spine. To classify disc degeneration according to the gold standard, Pfirrmann classification, a method based on the measurement of disc signal intensity and structure was developed. A gradient Vector Flow algorithm was used to extract disc shape features and for detecting contour abnormalities. Also, a signal intensity method was used for segmenting and detecting spinal stenosis. Novel algorithms have also been developed to quantify the severity of these pathologies. Variability was evaluated by kappa (k) and intra-class correlation (ICC) statistics. RESULTS Segmentation inaccuracy was below 1%. Almost perfect agreement, as measured by the k and ICC statistics, was obtained for all the analyzed pathologies: disc degeneration (k=0.81 with 95% CI=[0.75..0.88]) with a sensitivity of 95.8% and a specificity of 92.6%, disc herniation (k=0.94 with 95% CI=[0.87..1]) with a sensitivity of 60% and a specificity of 87.1%, categorical stenosis (k=0.94 with 95% CI=[0.90..0.98]) and quantitative stenosis (ICC=0.98 with 95% CI=[0.97..0.98]) with a sensitivity of 70% and a specificity of 81.7%. DISCUSSION The proposed methods are reproducible and should be considered as a possible alternative when compared to reference standards.

[1]  Wenyu Liu,et al.  Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Vipin Chaudhary,et al.  Disc herniation diagnosis in MRI using a CAD framework and a two-level classifier , 2012, International Journal of Computer Assisted Radiology and Surgery.

[3]  D. Fardon,et al.  Nomenclature and classification of lumbar disc pathology. , 2001, Spine.

[4]  A. Todd-Pokropek,et al.  Texture-based quantification of lumbar intervertebral disc degeneration from conventional T2-weighted MRI , 2011, Acta radiologica.

[5]  Siegfried Trattnig,et al.  Quantitative analysis of lumbar intervertebral disc abnormalities at 3.0 Tesla: value of T2 texture features and geometric parameters , 2012, NMR in biomedicine.

[6]  Jason J. Corso,et al.  Computer-aided diagnosis of lumbar disc pathology from clinical lower spine MRI , 2010, International Journal of Computer Assisted Radiology and Surgery.

[7]  I Isherwood,et al.  MR imaging of the intervertebral disc: a quantitative study. , 1985, The British journal of radiology.

[8]  Jason J. Corso,et al.  Toward a clinical lumbar CAD: herniation diagnosis , 2010, International Journal of Computer Assisted Radiology and Surgery.

[9]  E Kanal,et al.  Application of a Semiautomated Contour Segmentation Tool to Identify the Intervertebral Nucleus Pulposus in MR Images , 2010, American Journal of Neuroradiology.

[10]  P. Hendrick,et al.  Neurological examination of the peripheral nervous system to diagnose lumbar spinal disc herniation with suspected radiculopathy: a systematic review and meta-analysis. , 2013, The spine journal : official journal of the North American Spine Society.

[11]  F. Kovacs,et al.  Vertebral Endplate Changes Are Not Associated with Chronic Low Back Pain among Southern European Subjects: A Case Control Study , 2012, American Journal of Neuroradiology.

[12]  S. Michopoulou,et al.  Image analysis for the diagnosis of MR images of the lumbar spine , 2011 .

[13]  G. Niu,et al.  MR Imaging Assessment of Lumbar Intervertebral Disk Degeneration and Age-Related Changes: Apparent Diffusion Coefficient versus T2 Quantitation , 2011, American Journal of Neuroradiology.

[14]  John A. Hipp,et al.  Assessment of Magnetic Resonance Imaging in the Diagnosis of Lumbar Spine Foraminal Stenosis—A Surgeon's Perspective , 2006, Journal of spinal disorders & techniques.

[15]  S. Trattnig,et al.  Parametric T2 and T2* mapping techniques to visualize intervertebral disc degeneration in patients with low back pain: initial results on the clinical use of 3.0 Tesla MRI , 2011, Skeletal Radiology.

[16]  Hans-Joachim Wilke,et al.  Review of existing grading systems for cervical or lumbar disc and facet joint degeneration , 2006, European Spine Journal.

[17]  Vipin Chaudhary,et al.  Lumbar spinal stenosis CAD from clinical MRM and MRI based on inter- and intra-context features with a two-level classifier , 2011, Medical Imaging.

[18]  R. Tibshirani,et al.  An introduction to the bootstrap , 1993 .

[19]  N Roberts,et al.  MRI analysis of lumbar intervertebral disc height in young and older populations , 1997, Journal of magnetic resonance imaging : JMRI.

[20]  B. Weiner,et al.  Toward the establishment of optimal computed tomographic parameters for the assessment of lumbar spinal fusion. , 2011, The spine journal : official journal of the North American Spine Society.

[21]  S. Halabi,et al.  Systematic Literature Review of Imaging Features of Spinal Degeneration in Asymptomatic Populations , 2015, American Journal of Neuroradiology.

[22]  James D. Kang,et al.  Introduction: disc degeneration: summary. , 2004, Spine.

[23]  R B Haynes,et al.  Evidence base of clinical diagnosis: The architecture of diagnostic research , 2002 .

[24]  T. Whitecloud,et al.  A comparison of computed tomography-myelography, magnetic resonance imaging, and myelography in the diagnosis of herniated nucleus pulposus and spinal stenosis. , 1993, Journal of spinal disorders.

[25]  R. Edelman,et al.  Magnetic resonance imaging (2) , 1993, The New England journal of medicine.

[26]  Punam K. Saha.  Novel theory and methods for tensor scale: a local morphometric parameter , 2003, SPIE Medical Imaging.

[27]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Fengyu Zheng,et al.  A Novel Method for the Quantitative Evaluation of Lumbar Spinal Stenosis , 2006, HSS Journal.

[29]  Jacob Cohen,et al.  The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability , 1973 .

[30]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[31]  D. Sackett,et al.  The architecture of diagnostic research , 2002, BMJ : British Medical Journal.

[32]  J. Hodler,et al.  Quantitative radiologic criteria for the diagnosis of lumbar spinal stenosis: a systematic literature review , 2011, BMC musculoskeletal disorders.

[33]  J. Katz,et al.  Diagnosis of lumbar spinal stenosis. , 1994, Rheumatic diseases clinics of North America.

[34]  Joachim Hornegger,et al.  Computer-Aided Assessment of Anomalies in the Scoliotic Spine in 3-D MRI Images , 2009, MICCAI.

[35]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[36]  C. Pfirrmann,et al.  Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration , 2001, Spine.

[37]  Jerry L. Prince,et al.  Snakes, shapes, and gradient vector flow , 1998, IEEE Trans. Image Process..

[38]  Michael Wood,et al.  Statistical inference using bootstrap confidence intervals , 2004 .

[39]  S. Lim,et al.  Prevalence of Disc Degeneration in Asymptomatic Korean Subjects. Part 1 : Lumbar Spine , 2013, Journal of Korean Neurosurgical Society.

[40]  Siegfried Trattnig,et al.  Quantitative T2 evaluation at 3.0T compared to morphological grading of the lumbar intervertebral disc: a standardized evaluation approach in patients with low back pain. , 2012, European journal of radiology.

[41]  Jason J. Corso,et al.  Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model , 2011, IEEE Transactions on Medical Imaging.

[42]  Ming Dar Tsai,et al.  A new method for lumbar herniated inter-vertebral disc diagnosis based on image analysis of transverse sections. , 2002, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[43]  Steven W. Hwang,et al.  A novel classification system of lumbar disc degeneration , 2015, Journal of Clinical Neuroscience.

[44]  H. Herkowitz.  The lumbar spine , 2004 .

[45]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[46]  S Crozier,et al.  Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models , 2012, Physics in medicine and biology.

[47]  Ayse Betül Oktay,et al.  Computer aided diagnosis of degenerative intervertebral disc diseases from lumbar MR images , 2014, Comput. Medical Imaging Graph..

[48]  Kien A. Hua,et al.  Computer-aided diagnosis of lumbar stenosis conditions , 2010, Medical Imaging.

[49]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[50]  Keita Ito,et al.  Advances in the diagnosis of degenerated lumbar discs and their possible clinical application , 2014, European Spine Journal.

[51]  J. Zamora,et al.  Lumbar spine: agreement in the interpretation of 1.5-T MR images by using the Nordic Modic Consensus Group classification form. , 2010, Radiology.

[52]  Paul A. Bottomley,et al.  19F magnetic resonance imaging , 1977 .