Classification of Intervertebral Disc on Lumbar MR Images using SVM

Computer aided diagnosis is the most predominant research in computer vision. While considering the lumbar Magnetic Resonance Images (MRIs), identification of pathologies is a complex task as the size of the soft tissues may vary. Before recognizing the injury in the soft tissue, it is necessary to identify in which soft tissue, the pathology occurs. In order to address this issue, the classification of lumbar Intervertebral Discs (IVDs) on lumbar MRI is performed. The classification is determined after feature extraction on the region of interest. Histogram of Oriented Gradients (HOG) is applied to extract the features and a model is built using Support Vector Machine (SVM) for classification. A multi-class classification is performed on 80 subjects, both T1-weighted and T2-weighted, with a total of 960 Intervertebral Discs. The result of the research work done in this paper gives 71.53% accuracy on the classification of Lumbar MR Images. Also, the classification accuracy is compared with the features extracted using Fourier Descriptors (FD), and it shows HOG gives a promising result.

[1]  Ronald M. Summers,et al.  Automated spinal column extraction and partitioning , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[2]  Mandy Eberhart,et al.  Decision Forests For Computer Vision And Medical Image Analysis , 2016 .

[3]  Demetri Terzopoulos,et al.  Deformable models in medical image analysis: a survey , 1996, Medical Image Anal..

[4]  Dorin Comaniciu,et al.  Marginal Space Learning for Efficient Detection of 2D/3D Anatomical Structures in Medical Images , 2009, IPMI.

[5]  S. Mahmoudi,et al.  Template Matching Approaches Applied to Vertebra Detection , 2012 .

[6]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Cristian Lorenz,et al.  Spine Segmentation Using Articulated Shape Models , 2008, MICCAI.

[8]  T. Sree Sharmila,et al.  Efficient quality analysis of MRI image using preprocessing techniques , 2013, 2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES.

[9]  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.

[10]  Yalin Zheng,et al.  Automated segmentation of lumbar vertebrae in digital videofluoroscopic images , 2004, IEEE Transactions on Medical Imaging.

[11]  Zheng Zhao,et al.  Knowledge-based active appearance model applied in medical image localization , 2005, IEEE International Conference Mechatronics and Automation, 2005.

[12]  T. S. R. Raja,et al.  Impact of applying pre-processing techniques for improving classification accuracy , 2014, Signal Image Video Process..

[13]  Alexander R. Vaccaro,et al.  Artificial disc replacement. , 2013, Clinical privilege white paper.

[14]  Sree Sharmila Thangaswamy,et al.  Developing an efficient technique for satellite image denoising and resolution enhancement for improving classification accuracy , 2013 .

[15]  Xu Tao,et al.  Localization of a linear structure object in medical images based on hidden Markov model , 2003, 16th IEEE Symposium Computer-Based Medical Systems, 2003. Proceedings..

[16]  Ayse Betül Oktay,et al.  Simultaneous Localization of Lumbar Vertebrae and Intervertebral Discs With SVM-Based MRF , 2013, IEEE Transactions on Biomedical Engineering.

[17]  W. Huda,et al.  Imaging strategies to reduce the risk of radiation in CT studies, including selective substitution with MRI , 2007, Journal of magnetic resonance imaging : JMRI.

[18]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[19]  Jerry L. Prince,et al.  A Survey of Current Methods in Medical Image Segmentation , 1999 .

[20]  Hamed Sari-Sarraf,et al.  Customized Hough transform for robust segmentation of cervical vertebrae from X-ray images , 2002, Proceedings Fifth IEEE Southwest Symposium on Image Analysis and Interpretation.

[21]  Dorin Comaniciu,et al.  Spine detection in CT and MR using iterated marginal space learning , 2013, Medical Image Anal..

[22]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[23]  Mythreyi Bhargavan,et al.  Too few radiologists? , 2002, AJR. American journal of roentgenology.

[24]  Shang-Hong Lai,et al.  Learning-Based Vertebra Detection and Iterative Normalized-Cut Segmentation for Spinal MRI , 2009, IEEE Transactions on Medical Imaging.

[25]  L Remonda,et al.  [Spinal stenosis: current aspects of imaging diagnosis and therapy]. , 1996, Schweizerische medizinische Wochenschrift.

[26]  Mohammed Benjelloun,et al.  Fully automatic vertebra detection in x-ray images based on multi-class SVM , 2012, Medical Imaging.