Main Article Content
Lung cancer is considered the deadliest disease all over the globe. Early diagnosis can reduce the mortality rate by 20%. Computed tomography (CT) is considered a precise imaging technique used for lung cancer diagnosis. Though CT slices have the features of high resolution, non-invasive, and painless, the availability of hundreds of two-dimensional lung CT slices makes the detection process difficult and might result in false alarms. Recently, 3D visualization diagnosis for lung cancer detection and segmentation becomes an interesting domain for physicians. The utilization of 3D visualization assists the doctors to observe the pulmonary nodules efficiently. Therefore, this paper develops an automated 3D lung cancer tumor visualization and volume measurement technique using Simpleware Synopsys software. The presented model uses Simpleware Synopsys software to visualize the tumor in 3D format and measure the tumor size. The presented model in Simpleware Synopsys software involves different processes such as preprocessing, segmentation, morphological operations, 3D tumor visualization, and tumor volume measurement. The presented model uses Median Filtering (MF) as a preprocessing technique to remove the noise. In addition, region growing based segmentation technique is used to detect the tumor regions accurately. Besides, a set of morphological operations such as erode, dilate, open, and close are utilized. To examine the effective performance of the presented method, extensive experimentation was carried out on LIDC dataset and our own dataset collected from JIPMER hospital, Puducherry, India. The simulation outcome ensured the superior performance of the presented model by obtaining a maximum 3D visualization accuracy of 98% which is nearly 3.80% more than the existing methods.