Mixed Kernel Function SVM for Pulmonary Nodule Recognition
Automatic pulmonary nodule detection in computed tomography (CT) images has been a challenging problem in computer aided diagnosis (CAD). Most recent recognition methods based on support vector machines (SVMs) have shown difficulty in achieving balanced sensitivity and accuracy. To improve overall performance of SVM based pulmonary nodule detection, a mixed kernel SVM method is proposed for recognizing pulmonary nodules in CT images by combining both Gaussian and polynomial kernel functions. The proposed mixed kernel SVM, together with a grid search for parameters optimization, can be tuned to seek a balance between sensitivity and accuracy so as to meet the CADs need, and eventually to improve learning and generalization ability of the SVM at the same time. In our experiments, thirteen features were extracted from the candidate regions of interest (ROIs) preprocessed from a set of real CT samples, and the mixed kernel SVM was trained to recognize the nodules in the ROIs. The results show that the proposed method takes into account both the sensitivity and accuracy compared to single kernel SVMs. The sensitivity and accuracy of the proposed method achieve 92.59% and 92% respectively.
Keywordsimage recognition mixed kernel function support vector machine pulmonary nodule
Unable to display preview. Download preview PDF.
- 1.Cascio, D., Magro, R., Fauci, F., Iacomi, M., Raso, G.: Automatic detection of lung nodules in CT datasets based on stable 3D massspring models. Computers in Biology and Medicine, 1098–1109 (2012)Google Scholar
- 4.Zhang, J., Li, B., Tian, L.-F., et al.: Lung Nodule Recognition Combining Rule-Based Method and SVM. Journal of South China University of Technology (Natural Science Edition) 39, 125–129 (2011)Google Scholar
- 5.Liu, Y., Zhao, D., Liu, J.: Recognition of 3-D Lung Nodules Based on K-L Transform and Support Vector Machine. Journal of Northeastern University (Natural Science) 30, 1249–1252 (2009)Google Scholar
- 7.Liu, L., Liu, W.: A Method of Pulmonary Nodules Detection with Support Vector Machines. In: Proceedings of 8th International Conference on Intelligent Systems Design and Applications, ISDA, pp. 32–35 (2008)Google Scholar
- 8.Liu, L., Liu, W., Chu, C., et al.: Fast Classification of Benign and Malignant Solitary Pulmonary Nodules in CT image. Optics and Precision Engineering 17, 2060–2067 (2009)Google Scholar
- 9.Xie, J.: Optimal Control of Chaotic System Based on LS-SVM with Mixed Kernel. In: Proceedings of 3rd International Symposium on Intelligent Information Technology Application, pp. 622–625 (2009)Google Scholar
- 10.Lu, Y.-L., Li, L., Zhou, M., Tian, G.: A New Fuzzy Support Vector Machine Based on Mixed Kernel Function. In: Proceedings of 2009 International Conference on Machine Learning and Cybernetics, pp. 526–531 (2009)Google Scholar
- 11.Wang, H., Sun, F., et al.: On Multiple Kernel Learning Methods. Acta Automatica Sinica 36, 1037–1047 (2010) (in Chinese)Google Scholar
- 12.Gönen, M., Alpaydin, E.: Multiple Kernel Learning Algorithms. Journal of Machine Learning Research, 2211–2268 (2011)Google Scholar
- 13.Wang, Q.: Detection of Lung Nodules in CT Images Based on 3D SVMs. PhD Dissertation, Changchun: Jilin University (2011)Google Scholar
- 15.Jia, T., Zhao, D., Wei, Y., et al.: Computer-Aided Lung Nodule Detection Based on CT images. In: Proceedings of IEEE/ICME International Conference on Complex Medical Engineering, pp. 816–819. IEEE, Beijing (2007)Google Scholar