Multimodal Classification of Breast Masses in Mammography and MRI Using Unimodal Feature Selection and Decision Fusion
In this work, a classifier combination approach for computer aided diagnosis (CADx) of breast mass lesions in mammography (MG) and magnetic resonance imaging (MRI) is investigated, using a database with 278 and 243 findings in MG resp. MRI including 98 multimodal (MM) lesion annotations. For each modality, feature selection was performed separately with linear Support Vector Machines (SVM). Using nonlinear SVMs, calibrated unimodal malignancy estimates were obtained and fused to a multimodal (MM) estimate by averaging. Evaluating the area under the receiver operating characteristic curve (AUC), feature selection raised AUC from 0.68, 0.69 and 0.72 for MG, MRI and MM to 0.76, 0.73 and 0.81 with a significant improvement for MM (P=0.018). Multimodal classification offered increased performance compared to MG and MRI (P=0.181 and P=0.087). In conclusion, unimodal feature selection significantly increased multimodal classification performance and can provide a useful tool for generating joint CADx scores in the multimodal setting.
KeywordsSupport Vector Machine Feature Selection Breast Masse Decision Fusion Decision Score
Unable to display preview. Download preview PDF.
- 4.Constantinos, S.P., Pattichis, M.S., Micheli-Tzanakou, E.: Medical imaging fusion applications: An overview. In: Conference Record of the Thirty-Fifth Asilomar Conference on Signals, Systems and Computers 2001, vol. 2, pp. 1263–1267. IEEE (2001)Google Scholar
- 6.Bhooshan, N., Giger, M.L., Drukker, K., Yuan, Y., Li, H., McCann, S., Newstead, G., Sennett, C.: Performance of Triple-Modality CADx on Breast Cancer Diagnostic Classification. In: Martí, J., Oliver, A., Freixenet, J., Martí, R. (eds.) IWDM 2010. LNCS, vol. 6136, pp. 9–14. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 7.Ng, A.Y.: Feature selection, l 1 vs. l 2 regularization, and rotational invariance. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 78. ACM (2004)Google Scholar
- 8.Weston, J., Mukherjee, S., Chapelle, O., Pontil, M., Poggio, T., Vapnik, V.: Feature selection for svms. Advances in Neural Information Processing Systems, 668–674 (2001)Google Scholar
- 11.Platel, B., Huisman, H., Laue, H., Mus, R., Mann, R., Hahn, H., Karssemeijer, N.: Computerized characterization of breast lesions using dual-temporal resolution dynamic contrast-enhanced mr images. In: Workshop on Breast Image Analysi in conjunction with the 14th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2011 (2011)Google Scholar
- 12.Veltman, J., Stoutjesdijk, M., Mann, R., Huisman, H.J., Barentsz, J.O., Blickman, J.G., Boetes, C.: Contrast-enhanced magnetic resonance imaging of the breast: the value of pharmacokinetic parameters derived from fast dynamic imaging during initial enhancement in classifying lesions. European Radiology 18(6), 1123–1133 (2008)CrossRefGoogle Scholar
- 14.Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST) 2(3), 27 (2011)Google Scholar