TEXTURE FEATURE ANALYSIS AND SOFT COMPUTING METHOD BASED LUNG CANCER CLASSIFICATION SYSTEM
Shobha Yelburgi, Premachand D R
Image preprocessing, Segmentation, Back Propagation Neural Network (BPNN), Classification.
Magnetic Resonance Imaging (MRI) might be a problematic assignment for tumor fluctuation and complexity because of lung image classification. This work presents the lung cancer classification system using Back Propagation Neural Network (BPNN) algorithm based on MRI Lung images. The proposed tumor recognition framework comprises of four stages, to be specific preprocessing, feature extraction, segmentation and classification. Extraction of identified tumor framework features was accomplished utilizing Gray Level Co-occurrence Matrix (GLCM) strategy. At long last, the Back Propagation Neural Network Classifier has been created to perceive various kinds of lung disease. The proposed framework can be effective in grouping these models and reacting to any variation from the abnormality. The entire framework is isolated into different types of phases: the Learning/Training Phase and the Recognition/Test Phase. A BPNN classifier under the scholarly ideal separation measurements is utilized to decide the chance of every pixel having a place with the foreground (tumor) and the background. The simulation of the proposed system is also developed using MATLAB software. The simulation result of the proposed method demonstrates the stability of lung cancer analysis. It shows that the proposed lung cancer classifications are superior to those from lung MRIs than existing lung cancer classifications. The overall accuracy of the proposed system is 98.45%