Clinical Analysis of MR Brain Images using 2-D Rigid Registration Method

In this paper, clinical analysis of subjects diagnosed with malignant tumor/cyst is performed using a 2-D rigid multimodal registration techniquea principal axes method. Highly descriptive rigid control points are detected in reference image using area-based technique. The corresponding control points are initialized in target image. Inverse affine transformation is applied to get the registered image. After removing high geometric deformations such as scaling, translation and change in patient posture (rotation of head) by the area based technique, clinical information obtained after registration (CIAR) is ascertained. In CIAR, radiological and pathological information from the registered datasets is discussed. The method is tested on real multi-modal MR T1, T2, post contrast T1 unregistered image datasets of 10 patients obtained from PGIMER (Post Graduate Institute of Medical Education & Research, Chandigarh, India). The robustness achieved by the proposed method (proved by the cited examples) makes it a useful tool in routine clinical practice.