Quantitative surface characterization of pulmonary nodules based on thin-section CT images

Characterization of pulmonary nodules plays a significant role in the differential diagnosis of lung cancer. This paper presents a method to quantify surface characteristics of small pulmonary nodules with well-defined surfaces based on thin-section CT images. The segmentation of the three-dimensional(3-D) nodule images are obtained by a 3-D deformable surfaces approach. The feature extraction algorithms are designed to quantify the surface characteristic parameters from 3-D nodule images by using surface curvatures and ridge lines. Experimental results of our method, applied to patients 3-D nodule images, demonstrate its performance.