Preliminary study of pneumonia symptoms detection method using Cellular Neural Network

Medical diagnosis is one of the most important procedure in which image processing are usefully applied. In this paper, a pneumonia symptoms detection method based on cellular neural networks (CNNs) is proposed. The CNN design is characterized by a virtual template expansion obtained through a multistep operation. It is based on linear space invariant 3 × 3 templates. The proposed design is capable of performing pneumonia symptoms detection within a short time. The main idea in Cellular Neural Network is that connection is allowed between adjacent units only. There are few rules in Cellular Neural Network that has to be implemented when designing the templates, such as state equation, output equation, boundary equation, and also the initial value. These templates are combined to create the most ideal algorithm to detect the pneumonia symptoms in an image. Candy software is used as a CNN simulator to detect the pneumonia symptoms area. It was tested on the 23 grayscale pneumonia symptoms CT image obtained from the diagnostic imaging department. The simulation results show good performance based on the difference grayscale color and segmentation between the normal area and lung region area.