ANFIS Based Lung Tissue Classification on CT Scan Images

Abstract

Analysis of primary lung tumors and disease is important for lung cancer staging, and an automated system that can detect both types of abnormalities will be helpful for clinical routine. In this project, present a new method to automatically detect both normal and abnormal tumor, simultaneously in Computerized Tomography(CT) thoracic images and perform the detection in a multistage approach, by first detecting all potential abnormalities, then differentiate between normal and abnormal tumor. Then lung tumors are classified as benign and maligant using ANFIS and evaluate the parameters sensitivity, specificity, precision, recall and accuracy. The proposed method achieve results 98% for malignant tumor region in accordance with ground truth images.