Lung cancer diagnosis from CT images using fuzzy inference system

Abstract

The Fuzzy Inference System (FIS) plays a vital role in the medicalfield to provide medical assistance to the radiologist to diagnose the abnormality in the medical images. This paper presents a scheme to improve the efficiency of the lung cancer diagnosis system by proposing the segmentation of the suspected lung nodules by region based segmentation and cancer identification by FIS. The proposed method is implemented in two phases. The first phase carries pre-processing for primary noise removal by wiener filter followed by region growing to segment the suspected lung nodules from CT lung images. The second phase carries the classification of the segmented nodules as either benign (normal) or malignant (cancerous) by extracting the features like diameter, shape and intensity values and given as the input to the FIS. The Fuzzy system finds the severity of the suspected lung nodules based on IF-THEN rules. The sensitivity of the proposed system is 92.3%, which show that the proposed work can help the radiologists to increase their diagnostic confidence. © 2011 Springer-Verlag.