Hand Crafted Features for Efficient Lung Cancer Diagnosis Using Stacked Autoencoder.

The most critical steps to improve the clinical management of the lung cancer are the early detection and the accurate diagnosis. In this study, an automated system for lung cancer diagnosis from one computed tomography (CT) scan is developed to distinguish between malignant and benign nodules. This system utilizes two different kinds of features to describe the lung nodules. These features indicate the nodule's preceding growth rate, which is considered the major point in pulmonary nodule diagnosis. Analytical Local Binary Pattern is implemented to characterize the pulmonary nodule texture. Special functions called spherical harmonics are used to characterize the nodule surface. Finally, a stacked autoencoder is utilized to reduce the dimensionality of the modeled features values and to eliminate the noise in the data followed by a probability-based linear classifier to diagnose the nodule. The proposed system is tested using Lung Image Database Consortium (LIDC) database. The effectiveness of the presented framework is confirmed where the system accuracy, sensitivity, specificity, and area under the ROC curve of 93.79%, 94.36%, 92.80%, and 0.9764 respectively are achieved.