In head MRI image sequences, the boundary of each encephalic tissue is highly complicated and irregular. It is a real challenge to traditional 3D modeling algorithms. Support Vector Machine (SVM) based on statistical learning theory has solid theoretical foundation. Sphere-Shaped SVM (SSSVM) was originally developed for solving some special classification problems. In this paper, it is extended to image 3D modeling which tries to find the smallest hypersphere enclosing target data in high dimensional space by kernel function. However, selecting parameter is a complicated problem which directly affects modeling accuracy. Immune Algorithm (IA), mainly applied to optimization, is used to search optimal parameter for SSSVM. So, Immune SSSVM (ISSSVM) is proposed to construct the 3D models for encephalic tissues. As our experiment demonstrates, the models are constructed and reach satisfactory modeling accuracies. Theory and experiment indicate ISSSVM exhibits its great potential in image 3D modeling.