Faster Image Dendrogram Creation: An Efficient Algorithm for the Detection of Tumours in Digital Mammography

Abstract

Dendronic image analysis has been shown to provide a robust technique in the detection of tumours within digital mammograms. It provides the capability of fully automated image analysis through hierarchical segmentation. However, its general acceptance in image analysis has not been realised due to computational intensity in creating the image dendrogram. We have developed an efficient technique that can create image dendrograms a great deal faster than traditional repetitive segmentation algorithms, making dendronic analysis of digital mammograms a viable tool in the detection of breast cancer.