Abstract
This paper focuses on an approach for characterizing the internal structure which is one of important clues for differentiating between malignant and benign nodules in three-dimensional (3-D) thoracic images. In this approach, each voxel was described in terms of shape index derived from curvatures on the voxel. The voxels inside the nodule were aggregated via shape histogram to quantify how much shape category was present in the nodule. Topological features were introduced to characterize the morphology of the cluster constructed from a set of voxels with the same shape category. The properties such as curvedness and CT density were also built into the representation. In the classification step, a hybrid unsupervised/supervised structure was performed to improve the classifier performance. It combined the k-means clustering procedure and the linear discriminate (LD) classifier. The performance of the hybrid classifier was compared to that of LD classifier alone. Receiver operating characteristics (ROC) analysis was used to evaluate the accuracy of the classifiers. We also compared the performance of the hybrid classifier with those of physicians. The classification performance reached the performance of physicians. Our results demonstrate the feasibility of the hybrid classifier based on the topological and histogram features to assist physicians in making diagnostic decisions.
Chapter PDF
Similar content being viewed by others
References
Kaneko, M., Eguchi, K., Ohmatsu, H., Kakinuma, R., Naruke, T., Suemasu, K., Moriyama, N.: Peripheral lung cancer: Screening and detection with low-dose spiral CT versus radiography. Radiology 201, 798–802 (1996)
Mori, K., Saitou, Y., Tominaga, K., Yokoi, K., Miyazawa, N., Okuyama, A., Sasagawa, M.: Small nodular legions in the lung periphery: new approach to diagnosis with CT. Radiology 177, 843–849 (1990)
Zwirewich, C.V., Veda, S., Miller, R.R., Muller, N.L.: Solitary pulmonary nodule: high-resolution CT and radiological pathologic correlation. Radiology 179, 469–476 (1991)
Siegelman, S.S., Zerhouni, E.A., Leo, F.P., Khouri, N.F., Stitik, F.P.: CT of the solitary pulmonary nodule. AJR 135, 1–13 (1980)
Proto, A.V., Thomas, S.R.: Pulmonary nodules studied by computed tomography. Radiology 156, 149–153 (1985)
Cavouras, D., Prassopoulos, P., Pantelidis, N.: Image analysis methods for solitary pulmonary nodule characterization by computed tomography. European Journal of Radiology 14, 169–172 (1992)
McNitt-Gray, M.F., Hart, E.M., Goldin, J.G., Yao, C.-W., Aberle, D.R.: A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution computed tomography. In: Proc. SPIE, vol. 2710, pp. 1024–1034 (1996)
Kawata, Y., Niki, N., Ohmatsu, H., Kakinuma, R., Eguchi, K., Kaneko, M., Moriyama, N.: Shape analysis of pulmonary nodules based on thin-section CT images. In: Proc. SPIE, vol. 3034, pp. 967–974 (1997)
Kawata, Y., Niki, N., Ohmatsu, H., Kakinuma, R., Eguchi, K., Kaneko, M., Moriyama, N.: Quantitative surface characterization of pulmonary nodules based on thin-section CT images. IEEE Trans. Nuclear Science 45, 2132–2138 (1998)
Hirano, Y., Mekada, Y., Hasegawa, J., Toriwaki, J., Ohmatsu, H., Eguchi, K.: Quantification of vessels convergence in three-dimensional chest X-ray CT images with three-dimensional concentration index. Medical Imaging Technology 15, 228–236 (1997)
Tozaki, T., Kawata, Y., Niki, N., Ohmatsu, H., Kakinuma, R., Eguchi, K., Moriyama, N.: Pulmonary organs analysis for differential diagnosis based on thoracic thin-section CT images. IEEE Trans. Nuclear Science 45, 3075–3082 (1998)
Kitaoka, H., Takaki, R.: Simulations of bronchial displacement owing to solitary pulmonary nodules. Nippon Acta Radiologica 59, 318–324 (1999)
Kawata, Y., Niki, N., Ohmatsu, H., Kusumoto, M., Kakinuma, R., Mori, K., Eguchi, K., Kaneko, M., Moriyama, N.: Classification of pulmonary nodules in thin-section CT images by using multi-scale curvature indexes. In: IEEE Int. Conf. on Image Processing, vol. 2, pp. 197–201 (1999)
Kawata, Y., Niki, N., Ohmatsu, H.: Curvature based internal structure analysis of pulmonary nodules using thoracic 3-D CT images. IEICE Trans. J-83-D-II, 209–218 (2000)
Caselles, V., Kimmel, R., Sapiro, G., Sbert, C.: Minimal surfaces based object segmentation. IEEE Trans. Pattern Analysis Machine Intelligence 19, 394–398 (1997)
Thirion, J.-P., Gourdon, A.: Computing the differential characteristics of isointensity surfaces. Computer Vision and Image Understanding 61, 190–202 (1995)
Koenderink, J.J., Doom, A.J.V.: Surface shape and curvature scales. Image and Vision Computing 10, 557–565 (1992)
Dorai, C., Jain, A.K.: COSMOS-A representation scheme for 3D free-form objects. IEEE Trans. Pattern Analysis Machine Intelligence 19, 1115–1130 (1997)
Yonekura, T., Yokoi, S., Toriwaki, J., Fukumura, T.: Connectivity and Euler number of figures in the digitized three-dimensional space. Trans. IECE J65-D, 80–87 (1982)
Saito, T., Toriwaki, J.: Euclidean distance transformation for three-dimensional digital images. Trans. IEICE J76-D-II, 445–453 (1993)
Duda, R.O., Hart, P.E.: Pattern classification and scene analysis. John Wiley, Sons, Chichester (1973)
Costanza, M.C., Afifi, A.A.: Comparison of stopping rules in forward stepwise discriminate analysis. J. of the American Statistical Association 74, 77–785 (1979)
Metz, C.E.: ROC methodology in radiologic imaging. Investigative Radiology 21, 720–733 (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kawata, Y. et al. (2000). Hybrid Classification Approach of Malignant and Benign Pulmonary Nodules Based on Topological and Histogram Features. In: Delp, S.L., DiGoia, A.M., Jaramaz, B. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2000. MICCAI 2000. Lecture Notes in Computer Science, vol 1935. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-40899-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-40899-4_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41189-5
Online ISBN: 978-3-540-40899-4
eBook Packages: Springer Book Archive