A New Way to Process B-Scan Images

Image processing is an important phase in order to improve the accuracy both for diagnosis procedure and for surgical operation. Medical diagnosis is one of the most important areas in which image processing procedures are usefully applied. In this paper, we use the Cellular Neural Networks to research diagnostic images. We present a robustness design theorem for the optimal edge detector cellular neural network (OEDGE CNN). As applications, the CNN can detect successfully the embossment of B-scan image. Our findings show that CNN may provide a useful tool for medical image processing. To this point, a novel approach to image processing has been developed in the work.