Exploitation of Correspondence Between CC and MLO Views in Computer Aided Mass Detection
In this paper we investigate the effect of reclassification of CAD findings using correspondences in MLO and CC views, with the aim of reducing false positives and inconsistencies. We use a method to link regions identified as suspicious in both projections and add a two-view classifier to an existing CAD scheme. The input of this two-view classifier was a feature vector containing the likelihood of malignancy of the region, the likelihood of malignancy of the corresponding region in the other view, and a number of features that describe the resemblance between the both regions. Using FROC analysis we show that detection results improve when using two-view information.
KeywordsLinear Discriminant Analysis Single View Abnormal Case Forward Feature Selection Correspondence Score
Unable to display preview. Download preview PDF.
- 1.Nishikawa, R.M., Edwards, A., Schmidt, R.A., Papaioannou, J., Linver, M.N.: Can radiologists recognize that a computer has identified cancers that they have overlooked? In: SPIE Medical Imaging, vol. 6146 (2006)Google Scholar
- 2.Zheng, B., Chough, D., Ronald, P., Cohen, C., Hakim, C.M., Abrams, G., Ganott, M.A., Wallace, L., Shah, R., Sumkin, J.H., Gur, D.: Actual versus intended use of CAD systems in the clinical environment. In: SPIE Medical Imaging, vol. 6146 (2006)Google Scholar
- 7.van Engeland, S., Karssemeijer, N.: Matching breast lesions in multiple mammographic views. In: Agha, G.A., De Cindio, F., Rozenberg, G. (eds.) APN 2001. LNCS, vol. 2208, pp. 1172–1173. Springer, Heidelberg (2001)Google Scholar
- 10.Good, W.F., Zheng, B., Chang, Y.-H., Wang, X.H., Maitz, G., Gur, D.: Multi-image cad employing features derived from ipsilateral mammographic views. In: SPIE 1999 Image processing, vol. 3661, pp. 474–485 (1999)Google Scholar