Classification of lung image and nodule detection using fuzzy inference system

Abstract

The objective of this paper is to classify likely cancerous and noncancerous lung image and to detect the location of the nodule in the lung image provided by CT scan. The novelness of this paper is to provide better accuracy and assists radiologist to analyze CT scan images of lung accurately. This efficient proposed method consists of image enhancement, extracting region of interest using Active Contour Model, extracting spatial features from segmented image, train those feature vectors and classify the test image through Fuzzy Inference System. This proposed method performance is compared with one of the most efficient and popular existing method Support Vector Machine and shows better accuracy of 94.12%.