Efficient Classification of Lung Tumor using Neural Classifier
In this paper a new classification algorithm is proposed for the Efficient Classification of Lung Tumor. In order to develop algorithm 80 CT scan images of patients have been considered consisting of Benign Tumor, Malignant Tumor and Normal Lung Computed tomography (CT) Scan image. With a view to extract features from the CT scan images after image processing, an algorithm proposes (DCT) discrete cosine Transform domain coefficients. The Efficient classifiers based on Multilayer Perceptron (MLP) Neural Network. A separate Cross- Validation dataset is used for proper evaluation of the proposed classificat ion algorithm with respect to important performance measures, such as MSE and classification accuracy. The Average Classification Accuracy of MLP Neural Network comprising of one hidden layers with 7 PE’s organized in a typical topology is found to be superior (100 %) for Training . Finally, optimal algorithm has been developed on the basis of the best classifier performance. The algorithm will provide an effective alternative to traditional method of Lung Computed tomography (CT) scan image analysis for deciding the tumor in lung is Benign or Malignant.