Local complex phase based level set and its application to DIC red blood cell segmentation

Cell segmentation in microscopy imagery is essential for many biomedical applications. In this paper, a novel level set based technique is proposed for segmenting the differential interference contrast (DIC) red blood cell microscopy images. Based on the framework of subjective surfaces, a local complex phase based edge indicator function is introduced to replace the traditional gradient-based edge detection method for the local image feature acquisition, which is the key for the evolution of the surface. In addition, to help improve the detection of cell edges, we propose a modified version of level set framework in subjective surfaces embedded with shape prior information. In experiments, we show that the proposed method is more accurate and reliable than several existing typical level set methods for DIC red blood cell image segmentation.