Detection of Lung Cancer in CT image using Image Processing

Detection of Lung Cancer in CT image using Image Processing

Dr Anitha D , Koteswara reddy M , Thirumala reddy

Department of Computational Intelligence, School of computing,

SRM Institute of Science and Technology,

Kattankulathur, Tamilnadu, India.603203

Abstract— Lung diseases are conditions that specifically affect the lungs and disrupt the breathing process. Lung cancer is a major cause of death in humans globally. Timely identification can increase the likelihood of survival among individuals. Timely diagnosis of the problem leads to a significant increase in the average survival rates for individuals with lung cancer, from 14 to 49 percent. Although computed tomography (CT) is significantly more efficient than X-ray, a comprehensive diagnosis necessitates the use of numerous imaging techniques to mutually reinforce each other. A convolutional neural network (CNN) is designed and assessed for the purpose of identifying lung cancer in CT scans. A densely connected convolutional neural network (CNN) and adaptive boosting algorithm were employed to classify the lung picture as either normal or cancerous. A dataset consisting of 201 lung images is utilized, with a portion of the photos allocated for training and the remaining images used for testing and classification purposes. The experimental findings demonstrated that the proposed strategy attained a high level of accuracy.

Keyword: Medicinal, deep learning, Mobile net model, CNN, minutiae.