Detection of masses in digitised mammograms using dendronic image analysis

Abstract

If detected early, breast cancer can be treated with better patient outcomes and significantly lower costs. Using the spatial dendronic structure and hierarchical repartment operator, difficult cases of spiculated and stellate tumours can be identified early. The techniques are robust to noise and can reveal various layers of biophysical and biomedical differences in a suspect tumour. In particular, the hierarchical repartment parameter of a mass in a digital mammogram can be obtained using compactness ratios of successive information peeling in this mass. This parameter alone was applied to distinguish all biopsied masses from normal parenchymal tissues in eight separate cases.