Using Fuzzy Inference system for detection the edges of Musculoskeletal Ultrasound Images

Edge detection in Musculoskeletal Ultrasound Imaging readily allows an ultrasound image to be rendered as a binary image. This facilitates automated measurement of geometric parameters, such as muscle thickness, circumference and cross-sectional area of the tendon. In this work, we introduced a new method of edge detection based on a fuzzy inference system and apply it to the ultrasound image. An anisotropic diffusion filter was used to reduce speckle noise before implementation of the edge detection method, which consists of three characteristic steps. The first step entailed fuzzification, for which three fuzzy membership functions were applied to the image. The parameters of these functions were selected based on an analysis of the standard deviation of grey level intensities in the image. Secondly, 12 fuzzy rules for identifying edges were constructed. Thirdly, defuzzification was carried out using the Takagi-Sugeno method. Furthermore, a reference-based edge measurement was quantitatively determined by comparing edge characteristics with a standard reference. We made two inferences from our observations. Firstly, the ability to automatically identify the important details of a musculoskeletal ultrasound image in a very short time is possible. Secondly, this method is effective compared with other methods.