DefinePK

Abstract

Lung cancer is the leading cause of cancerous deaths in the world in men and women. It is the most difficult cancer to cure and the number of deaths that it causes is generally increasing. It is very difficult to detect in its early stage. In advanced stages, treating the disease includes surgery, chemotherapy, radiation therapy or combination. Normally, the radiologists and surgeons detect the locations of the cancerous tumor from the computed tomographic images. However, the computed tomographic images are two dimensional. The mapping of stacks of two dimensional images into original lung cavities in three dimensional involves lot of mental work and long time for the surgeons before they plan for surgery. This work aimed to develop a novel semi-automated three dimensional computer-aided diagnostic system to localize the cancerous lung tumor in isotropic chest computed tomographic images. In addition, it measures the volume and size of the cancerous tumor. Low dose helical computed tomographic scan images retrospectively obtained from 23 subjects who suffered from lung cancer (conformed through biopsy test) have been taken for this study. To validate the system performance, results were compared with the three independent radiologist’s results. The obtained results show that a computer-aided diagnostic system performance is satisfactory and may useful for surgical planning of lung cancer.