Medical Image Segmentation Based on Watershed and Graph Theory

Abstract—Medical Image Segmentation Based on Watershed and Graph Theory. Strong noise, poor gray-scale contrast, blurred margins of tissue are characteristics of < Final Year Projects > medical images. Extracting object of interest in medical images is challenging. A segmentation approach that combines watershed algorithm with graph theory is proposed in this paper. This algorithm reconstructs gradient before watershed segmentation, based on the reconstruction, a floating-point active-image is introduced as the reference image of watershed transform. Finally, a graph theory based algorithm Grab Cut is used for fine segmentation. False contours of over-segmentation are effectively excluded and total segmentation quality significant improved as suitable for medical image segmentation. Nowadays, imaging technology such as computerized tomography (CT), ultrasonic (US) and magnetic resonance imaging (MRI) plays an irreplaceable role in medical diagnosis, pathology research, operation planning and post operation observation. Correctly extract the object of interest is an important step, which can pave the way to successful medical diagnosis and analysis. Medical Image Segmentation Based on Watershed and Graph Theory.