A Computer-Aided Diagnosis System for Classification of Lung Tumors

摘要

Lung cancer is the leading cancer killer throughout the worid. Despite the boost in technology that has enhanced diagnostic and clinical developments in the medical field, the accuracy in lung tumor evaluation still remains a comprising issue. This article aims toward creating a diagnosis system using artificial neural network to classify the lung tumor either to malignant or benign tumor in computed tomography images. The diagnosing system comprises image processing and artificial neural network procedures. Image processing include procedures such as histogram equalization, image filtering, image segmentation. For the classification system, features were extracted from the segmented images and fed to MLP (multilayer Perceptron) neural network that uses backpropagation algorithm for the learning of the network. Results have rendered the proposed techniques promising with accurate levels of lung cancer detection. The system was able to achieve an accuracy of 95.2% sensitivity, 100% specificity, and an overall classification accuracy of 97.3%. A user-friendly MATLAB graphical user interface program has been constructed to test the proposed algorithm.