Title :
Classification of cross-section area of spinal canal on kernel-based support vector machine
Author :
Wu, Chao-Cheng ; Li, Hsiao-Chi ; Chiang, Yung-Hsiao ; Lin, Jiannher
Author_Institution :
Dept. of Electr. Eng., Nat. Taipei Univ. of Technol., Taipei, Taiwan
Abstract :
The cross section area of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, this region can only be defined by doctors manually and calculated the amount of area by commercial software at present. The solution for reliable and robust classification and measurement remains open. This manuscript utilized kernel-based support vector machine to provide an automatically classification and measurement of the cross-section area of spinal canal. This kernel-based SVM classifier is compared with the linear SVM proposed in [1] and the present method. The experiments showed that the kernel based-SVM classifier could provide a better performance and robust classification result for the cross section area of spinal canal.
Keywords :
image classification; medical image processing; neurophysiology; patient diagnosis; support vector machines; LSS; adult preoperative diagnosis; commercial software; cross-section area classification; kernel-based SVM classifier; kernel-based support vector machine; lumbar spinal stenosis; reliable classification; robust classification; spinal canal; Fluids; Irrigation; Kernel; Magnetic resonance imaging; Medical services; Support vector machines; Training; Classification; Kernel function; Radial basis function (RBF); Spinal Canal; Support Vector Machine (SVM);
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4673-1713-9
Electronic_ISBN :
978-1-4673-1712-2
DOI :
10.1109/ICSMC.2012.6378142