ROI extraction from motion affected MR images by suppression of blurring and motion artifacts in the image background

Abstract

An algorithm is presented for extraction of the region of interest (ROI) enclosed by the outer boundary of the imaged object. Although there are many algorithms presently available for solving segmentation tasks, they can be easily misled by the ghost artifacts and blurring in the background of the image. Therefore, a two step background-clearing algorithm is proposed in this paper. The first step involves selection of the least motion-affected views, using an entropy minimization criterion for suppression of motion induced blurs. The second step involves cancellation of the remaining ghost artifacts, using a fuzzy model. Both these steps tend to increase the number of dark pixels in the image. The contour extraction is performed using an improved active contour model (snake). The proposed method has been applied to spin echo MR images affected by rotational motion, producing good results.