Intervertebral disc classification by its degree of degeneration from T2-weighted magnetic resonance images
- 606 Downloads
The primary goal of this article is to achieve an automatic and objective method to compute the Pfirrmann’s degeneration grade of intervertebral discs (IVD) from MRI. This grading system is used in the diagnosis and management of patients with low back pain (LBP). In addition, biomechanical models, which are employed to assess the treatment on patients with LBP, require this grading value to compute proper material properties.
Materials and methods
T2-weighted MR images of 48 patients were employed in this work. The 240 lumbar IVDs were divided into a training set (140) and a testing set (100). Three experts manually classified the whole set of IVDs using the Pfirrmann’s grading system and the ground truth was selected as the most voted value among them. The developed method employs active contour models to delineate the boundaries of the IVD. Subsequently, the classification is achieved using a trained Neural Network (NN) with eight designed features that contain shape and intensity information of the IVDs.
The classification method was evaluated using the testing set, resulting in a mean specificity (95.5 %) and sensitivity (87.3 %) comparable to those of every expert with respect to the ground truth.
Our results show that the automatic method and humans perform equally well in terms of the classification accuracy. However, human annotations have inherent inter- and intra-observer variabilities, which lead to inconsistent assessments. In contrast, the proposed automatic method is objective, being only dependent on the input MRI.
KeywordsClassification IVD Degeneration MR 2D Automatic Active contour model Neural network
The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under Grant agreement number 269909, MySpine project.
Compliance with ethical standards
Conflict of interest
None of the authors has any potential conflict of interest.
- 3.Malandrino A, Pozo JM, Castro-Mateos I, Frangi AF, van Rijsbergen MM, Ito K, Wilke HJ, Dao TT, Tho MCHB, Noailly J (2015) On the relative relevance of subjectspecific geometries and degeneration-specific mechanical properties for the study of cell death in human intervertebral disk models. Front Bioeng Biotechnol 3(5)Google Scholar
- 9.Jarman JP, Arpinar VE, Baruah D, Klein AP, Maiman DJ, Muftuler LT (2014) Intervertebral disc height loss demonstrates the threshold of major pathological changes during degeneration. Eur Spine J 1–7Google Scholar
- 11.Chwialkowski M, Shile P, Peshock R, Pfeifer D, Parkey R (1989) Automated detection and evaluation of lumbar discs in MR images. Eng Med Biol Soc 571–572Google Scholar
- 13.Ghosh S, Alomari R, Chaudhary V, Dhillon G (2011) Composite features for automatic diagnosis of intervertebral disc herniation from lumbar MRI. Eng Med Biol Soc EMBC 5068–5071Google Scholar
- 14.Una lY, Kocer H, Akkurt H (2011) A comparison of feature extraction techniques for diagnosis of lumbar intervertebral degenerative disc disease. In: International Symposium on Innovations in Intelligent Systems and Applications (INISTA), pp 490–494Google Scholar
- 15.Alomari RS, Corso JJ, Chaudhary V, Dhillon G (2010) Automatic diagnosis of lumbar disc herniation with shape and appearance features from MRI. SPIE Med Imaging 76241AGoogle Scholar
- 16.Neubert A, Fripp J, Engstrom C, Walker D, Weber M, Schwarz R, Crozier S (2013) Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images. J Am Med Inf Assoc 20(6):1082–1090Google Scholar
- 17.Lootus M, Kadir T, Zisserman (2015) A.: automated radiological grading of spinal MRI In: recent advances in computational methods and clinical applications for spine imaging, pp 119–130Google Scholar
- 19.Castro-Mateos I, Pozo JM, Lazary A, Frangi AF (2014) 2D segmentation of intervertebral discs and its degree of degeneration from T2-weighted magnetic resonance images. SPIE Med Imaging 903517Google Scholar
- 24.Malandrino A, Noailly J, Lacroix D, Beard DA (2011) The effect of sustained compression on oxygen metabolic transport in the intervertebral disc decreases with degenerative changes. PLOS Comput Biol 7(8)Google Scholar
- 25.Schmidt S, Bergtholdt M, Dries S, Schnorr C (2007) Spine detection and labeling using a parts-based graphical model. In: Lect Notes Comput Sc (IPMI), pp 122–133Google Scholar
- 26.Stern D, Vrtovec T, Pernus F, Likar B (2010) Automated determination of the centers of vertebral bodies and intervertebral discs in CT and MR lumbar spine images. In: Proceedings of SPIE, pp 762350Google Scholar
- 27.Peng Z, Zhong J, Wee W, Lee JH (2005) Automated vertebra detection and segmentation from the whole spine MR images. Eng Med Biol Soc Ann IEEE-EMBS, pp 2527–2530Google Scholar
- 28.Corso JJ, Alomari RS, Chaudhary V (2008) Lumbar disc localization and labeling with a probabilistic model on both pixel and object features. In: Lect Notes Comput Sc (MICCAI), pp 202–210Google Scholar
- 30.Hon JY, Bahri S, Gardner V, Muftuler LT (2014) In vivo quantification of lumbar disc degeneration: assessment of ADC value using a degenerative scoring system based on Pfirrmann framework. Eur Spine J 24(11):1–7Google Scholar