Chest X-ray features extraction for lung cancer classification

Abstract

This study presents a computer algorithm, which consists of four main steps (image acquisition, image pre-processing, nodule candidate detection, and feature extraction) for nodule detection in chest radiographs. Algorithm is applied on small-cell type of lung cancer (SCLC) and non-small-cell type of lung cancer (NSCLC) images. Total 50 images (25 from each category) were used to estimate geometrical and texture features. Active shape model (ASM) was used for lung field segmentation. Gray level co-occurrence matrix (GLCM) was used to estimate texture features.