Title :
3D Reconstruction of encephalic tissue in MRI image using immune Sphere-Shaped SVM
Author :
Guo, Lei ; Li, Ying ; Miao, Dongbo ; Yan, Weili ; Shen, Xueqin
Author_Institution :
Province-Minist. Joint Key Lab. of Electromagn. Field & Electr. Apparatus Reliability, Hebei Univ. of Technol., Tianjin, China
Abstract :
In MRI images, the boundary of each encephalic tissue is highly irregular. Sphere-Shaped Support Vector Machine (SSSVM) has the advantage of solving high non-linearity and irregularity problems. In this paper, SSSVM is applied in brain MRI image 3D reconstruction. Selecting parameters for SSSVM, however, is a complicated problem. Appropriate parameters can make the model more flexible and help to obtain more accurate data description. In this paper, Immune Algorithm (IA) is used in searching for optimal SSSVM parameters. Immune SSSVM (ISSSVM) is proposed to reconstruct 3D model of each encephalic tissue. As shown by the experiment of this study, encephalic tissues are reconstructed efficiently and satisfied accuracies and visual effects are obtained.
Keywords :
biological tissues; biomedical MRI; brain; image reconstruction; support vector machines; 3D image reconstruction; Immune Algorithm; SSSVM parameter; brain MRI image; encephalic tissue; immune sphere shaped SVM; sphere shaped support vector machine; visual effect; Brain modeling; Electromagnetic fields; Geology; Image reconstruction; Kernel; Magnetic resonance imaging; Neoplasms; Support vector machine classification; Support vector machines; Visual effects;
Conference_Titel :
Electromagnetic Field Computation (CEFC), 2010 14th Biennial IEEE Conference on
Conference_Location :
Chicago, IL
Print_ISBN :
978-1-4244-7059-4
DOI :
10.1109/CEFC.2010.5481513
