A Novel Approach for Lung Pattern Analysis using Neural Networks and Fuzzy Interface System

Abstract

An important and crucial aspect of image processing is effective identification of lung cancer at an initial stage. One of the state of the art methods in lung cancer detection is machine learning, namely ANNs (Artificial Neural Networks) and Fuzzy Logic. These researches mainly focus upon image quality and accuracy. ANN has proved to be efficient due to their ability to learn and generalize from data. To detect lung cancer based on fuzzy logic to classify the normal and abnormal images, in the abnormal result, use other symptoms as input to fuzzy logic system to find case of the patient (cancerous or noncancerous) depending on the membership function of inputs. Expanding rough approximations into fuzzy environment which help to obtain solutions for various real time problems. Patterns are conferred to the network via the input layer which communicates to one or more hidden layers where the actual processing is done via a system of weighted connections. The hidden layers then bond to an output layer. The objective of the proposal is to materialize a means to fasten the process as well as the accuracy of detecting the cancer cells to a valuable extent it helps in saving human lives.