A Vector Machine Formulation with Application to the Computer-Aided Diagnosis of Breast Cancer from DCE-MRI Screening Examinations
- 237 Downloads
This study investigates the use of a proposed vector machine formulation with application to dynamic contrast-enhanced magnetic resonance imaging examinations in the context of the computer-aided diagnosis of breast cancer. This paper describes a method for generating feature measurements that characterize a lesion’s vascular heterogeneity as well as a supervised learning formulation that represents an improvement over the conventional support vector machine in this application. Spatially varying signal-intensity measures were extracted from the examinations using principal components analysis and the machine learning technique known as the support vector machine (SVM) was used to classify the results. An alternative vector machine formulation was found to improve on the results produced by the established SVM in randomized bootstrap validation trials, yielding a receiver-operating characteristic curve area of 0.82 which represents a statistically significant improvement over the SVM technique in this application.
KeywordsBreast Cancer Detection Computer-Aided Diagnosis Machine Learning Support Vector Machine Receiver-Operating Characteristic Curve Analysis Magnetic Resonance Imaging
We would like to thank Elizabeth Ramsay for her assistance in image acquisition. The MRI data was acquired using funding from the Canadian Breast Cancer Research Alliance. The authors would like to thank the Canadian Breast Cancer Foundation and the Canadian Institute for Health Research for contributing to the funding of this study.
- 2.Curry SJ: Fulfilling the potential of cancer prevention and early detection. National Academies Press, Washington DC, USA, 2003Google Scholar
- 8.Levman J, Martel AL: Computer-aided diagnosis of breast cancer from magnetic resonance imaging examinations by custom radial basis function vector machine. IEEE Proceedings of the Engineering in Medicine and Biology Society, Buenos Aires, Argentina, 2010Google Scholar
- 9.Efron B, et al: An introduction to the bootstrap. Chapman & Hall, New York, 1994Google Scholar
- 15.Karahaliou A, et al: Quantifying heterogeneity of lesion uptake in dynamic contrast enhanced MRI for breast cancer diagnosis. 4th International Conference on Imaging Technologies in Biomedical Sciences, Milos, Greece, 2007Google Scholar
- 17.Song C, Smith M, Huang Y, Jeraj R, Fain S: Heterogeneity of vascular permeability in breast lesions with dynamic contrast enhanced MRI. Proceedings of the 17th International Symposium for Magnetic Resonance in Medicine, 2009.Google Scholar
- 23.LIBSVM. Available at http://www.csie.ntu.edu.tw/∼cjlin/libsvm/. Accessed Jan. 25, 2009.