Validation of Graph Theoretic Segmentation of the Pectoral Muscle
Two graph theoretic methods are used in conjunction with active contours to segment the pectoral muscle in 82 screening mammograms. To validate the method, the boundaries are also marked by four radiologists with different levels of experience in mammography. The simultaneous truth and performance level estimation (STAPLE) method is used to estimate the true boundary and to estimate the sensitivity and specificity of the segmentation schemes. The performance of one of the two algorithms is found not differ significantly from radiologists.
Unable to display preview. Download preview PDF.
- 4.Ma, F., Bajger, M., Bottema, M.J.: Extracting the pectoral muscle in screening mammograms using a graph pyramid. In: Lovel, B.C., Meader, A.J. (eds.) Workshop Proceedings, APRS Workshop on Digital Image Computing (WDIC 2005), pp. 39–42. University of Queensland (2005)Google Scholar
- 5.Bajger, M., Ma, F., Bottema, M.J.: Minimum spanning trees and active contours for identification of the pectoral muscle in screening mammograms. In: Lovel, B.C., Meader, A.J., Ourselin, S., Caelli, T. (eds.) Proceedings of Digital Image Computing: Techniques and Technology (DICTA 2005). IEEE, Los Alamitos (2005)Google Scholar