Identifying Lung Cancer Using CT Scan Images Based on Artificial Intelligence

Abstract

Lung cancer is among the leading cause of death among men and women. Early detection of lung cancers can increase the possibility of survival amongst patients. The preferred 5-years survival rate for lung most cancers sufferers will increase from 16% to 50% if the disease is detected on time. Computerized tomography (CT) is frequently used for diagnosis and is more efficient than X-ray. However, the images need to be reviewed by a qualified physician who specializes in interpreting the CT scan. This may lead to misinterpretation and conflicting reports among physicians. Therefore, a lung cancer detection system that uses image processing methods to categorize lung cancer in CT images will be more consistent and precise. This paper presents a lung cancer detection system using the Artificial Intelligence (AI) method. The study uses Median, Gaussian, and Watershed segments to reduce noisy and shredded CT images. Then, the Weight Optimization Neural Network method was used to improve accuracy and reduce the computational time. The results were compared with previous works and shows higher accuracy and shorter computational time.