Spleen segmentation in MRI sequence images using template matching and active contours

This paper proposes an approach for automatic segmentation of the human spleen in MRI-sequence images. It is based on the active contours without edges and uses a template matching method to define the initial contour at which the segmentation begins. The algorithm of the segmentation includes several steps. The sequence is divided in two parts (before and after the middle image). Using the first segmentation of the middle image of the sequence the mask for segmentation in the next image in the sequence is created. For each sequential image we use the segment from the previous as a mask. The proposed approach allows extracting the spleen in the different depth images, which has a variable form and unstable position. Some experimental results are presented, obtained by computer simulation in the MATLAB environment. Implementation results demonstrate the effectiveness of the approach for application in screening diagnostics.