Research on MRI Disc Localization and Degeneration Classification Based on Gabor Feature
1 College of Information Science and Engineering, Huaqiao University, Xiamen 361021，Fujian, China
2Department of Orthopaedics, 113th Hospital of PLA, Ningbo 315040, Zhejiang, China
3 Fifth Laboratory, Research Institute of Field Surgery, Daping Hospital, Third Military Medical University of Chinese PLA, State Key Laboratory for Trauma, Burn and Combined Injury, Chongqing 400042, China
Abstract：An unsupervised method based on Gabor feature for localizing intervertebral discs (IVDs) automatically and classifying disc degeneration was proposed in this paper. At first, a series of Gaborfiltered spine images were obtained in order to extract the information of spine edges and disc edges based on which the areas of spines could be determined. After that, on the basis of the prior knowledge,the exact location of IVDs in the spines were calculated. Finally, associating localization results with Gabor coefficients, the classification of IVD degeneration was realized based on gray information of nucleus pulposus and annulus fibrosis which were obtained by ellipse fitting. Experiments were performed in a dataset of 37 patients, the results showed that our method was simpler than the existing methods while with a similar accuracy of 966%, and it increased the precision to 1.46 mm. Besides, the degeneration classification of level 1-5 could be realized by our classification algorithm.
［1］Ghosh S, Malgireddy MR, Chaudhary V, et al. A supervised approach towards segmentation of clinical MRI for automatic lumbar diagnosis ［M］ // Lecture Notes in Computational Vision and BiomeChanics 17. Berlin: SpringerVerlag, 2014: 185-195.
［2］Da Silva Barreiro M, NogueiraBarbosa MH, Rangayyan RM, et al. Semiautomatic classification of intervertebral disc degeneration in magnetic resonance images of the spine［C］// Proceedings of Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC), 5th ISSNIPIEEE. Salvador: IEEE Computer Society Press, 2014: 1-5.
［3］Shi Ruiqiong, Sun Dongmei, Qiu Zhengding, et al. An efficient method for segmentation of MRI spine images［C］//Proceedings of IEEE/ICME International Conference on Complex Medical Engineering. Beijing: IEEE Computer Society Press, 2007: 717-721.
［4］查艳丽. MRI脊柱图像的定位与分割［D］. 北京: 北京交通大学, 2009.
［5］Alomari RS, Corso JJ, Chaudhary V. Labeling of lumbar discs using both pixeland objectlevel features with a twolevel probabilistic model ［J］. IEEE Trans Med Imaging, 2011, 30(1): 1-10
［6］Ghosh S, Chaudhary V. Supervised methods for detection and segmentation of tissues in clinical lumbar MRI ［J］. Computerized Medical Imaging and Graphics, 2014, 38: 639-649.
［7］Oktay AB, Akgul YS. Simultaneous localization of lumbar vertebrae and intervertebral discs with SVMbased MRF ［J］. IEEE Trans Biomed Eng, 2013, 60(9): 2375-2383.
［8］Peng Zhigang, Zhong Jia, Wee W, et al. Automated vertebra detection and segmentation from the whole spine MR images［C］// Proceedings of 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS). Shanghai: IEEE Computer Society Press, 2005: 2527-2530.
［9］Ghosh S, Alomari RS, Chaudhary V, et al. Computeraided diagnosis for lumbar mri using heterogeneous classifiers［C］// Proceedings of IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Chicago: IEEE Computer Society Press, 2011:1179-1182
［10］Oktay AB, Albayrak NB, Akgul YS. Computer aided diagnosis of degenerative intervertebral disc diseases from lumbar MR images ［J］. Computerized Medical Imaging and Graphics, 2014, 38(7):613-619.
［11］谢元旦, 贾朱植, 董立文. Fourier 变换和 Gabor 变换与小波变换的比较研究［J］.鞍山科技大学学报, 2005, 28(1):12-16
［12］宗君斌. 基于Gabor小波系数融合的人脸识别［D］. 杭州: 浙江工业大学, 2009.
［13］薛涛, 刘潇潇, 张海兵. 基于 Gabor 特征融合和 LSSVM 的人脸识别算法［J］. 计算机应用与软件, 2014, 31(7):191-194.
［14］马大国, 马岩. 基于Gabor 特征的木材表面缺陷的分块检测［J］.东北林业大学学报, 2013, 41(10):118-121.
［15］李英, 田春娜, 颜建强. 一种图像中的文字区域检测新方法［J］. 西安电子科技大学学报, 2013, 40(6):187-192.
［16］Ji Peijin, Jin Lianwen, Li Xutao. Visionbased vehicle type classification using partial Gabor filter bank［C］ // Proceedings of IEEE International Conference on Automation and Logistics. Jinan: IEEE Computer Society Press, 2007:1037-1040.
［17］赵英男, 孟凡斌, 金忠. Gabor核函数窗的设置研究［J］. 计算机科学, 2009, 36(1): 111-113.
［18］Watanabe A, Benneker LM, Boesch C, et al. Classification of intervertebral disk degeneration with axial T2 mapping［J］. American Journal of Roentgenology, 2007,189(4): 936-942.
［19］Gander W, Golub GH, Strebel R. Leastsquares fitting of circles and ellipses ［J］. BIT Numerical Mathematics, 1994, 34(4): 558-578.
