Affine based image registration applied to MRI brain

This paper presents a quantitative evaluation of state - of-the art intensity based image registration methods applied to medical images. These methods range from a global domain transformation using affine as transformation. The aim of this study is to access the stability of these methods for medical image analysis. Evaluation using temporal cases especially for MRI brain images based on quantitative analysis and a multiobserver study is presented which gives an indication of the accuracy and robustness of the algorithm. The affine transformation is tested with normal MR brain image and MR brain image with lesion. The detailed analysis of this affine transformation is also tested with MR brain images with various noise levels. The accuracy of the affine transformation is evaluated using observer study which varies according to the selection of control points.