Noninvasive Technique for Classification of Pulmonary Cancer Based on Computerized Tomography: Review and Analysis

Abstract

Lung cancer is one of the leading causes of death in the United States and Europe. Most cancers that start in the lung, known as primary lung cancers, are carcinomas that derive from epithelial cells. The most common symptoms are coughing (including coughing up blood), weight loss, shortness of breath, and chest pains. Different diagnostic procedures have been followed in an attempt to differentiate between the benign and malignant tumors such as computed tomography or magnetic resonance imaging scans, angiogram, chest x-ray, and biopsy, which is the most accurate procedure that determines the pulmonary tumor type. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterized abnormalities that are found. In the clinical interpretation of medical images, limitations in the human eye-brain visual system, reader fatigue, distraction, the presence of overlapping structures that camouflage disease in images, and the vast number of abnormal cases seen in screening programs provide cause for detection and interpretation errors. A comprehensive review on the subject has been done to give an overview of the recent studies, their methodology, and the result of those studies, along with the authors' analysis of these studies.