Title :
Quantitative surface characterization of pulmonary nodules based on thin-section CT images
Author :
Kawata, Y. ; Niki, N. ; Ohmatsu, H. ; Kakinuma, R. ; Eguchi, K. ; Kaneko, M. ; Moriyama, N.
Author_Institution :
Fac. of Eng., Tokushima Univ., Japan
fDate :
8/1/1998 12:00:00 AM
Abstract :
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 the authors´ method, applied to patients 3-D nodule images, demonstrate its performance
Keywords :
computerised tomography; feature extraction; image segmentation; lung; medical image processing; 3-D deformable surfaces approach; feature extraction algorithms; lung diagnostic differential diagnosis; medical diagnostic imaging; pulmonary nodules; quantitative surface characterization; ridge lines; surface characteristic parameters; thin-section CT images; Biomedical optical imaging; Biopsy; Cancer; Computed tomography; Feature extraction; Hospitals; Image segmentation; Lesions; Lungs; Shape measurement;
Journal_Title :
Nuclear Science, IEEE Transactions on
