Medical Image Segmentation Using a Geometric Active Contour Model Based on Level Set Method

We present a level set framework for medical image segmentation using a new defined speed function. This function combines the alignment term, which makes a level set as close as possible to a boundary of object, the minimal variance term, which best separates the interior and exterior in the contour and the smoothing term, which makes a segmented boundary become less sensitive to noise. The use of a proposed speed function can improve the segmentation accuracy while making the boundaries of each object much smoother. Finally, we have demonstrated that the design of the speed function plays an important part in segmenting the synthetic and CT images reliably.