Normal mammogram classification based on regional analysis
Author
Yajie Sun, CF Babbs, EJ Delp
Abstract
The majority of screening mammograms are normal. It will be beneficial if a detection system is designed to help radiologists readily identify normal regions of mammograms. In this paper, we will present a binary tree classifier based on the use of global features extracted from different levels of a 2-D Quincunx wavelet decomposition of normal and abnormal regional images. This classifier is then used to classify whether an entire whole-field mammogram is normal. This approach is fundamentally different from other approaches that identify a particular abnormality in that is independent of the particular type of abnormality.
Journal
Circuits and Systems, 2002. MWSCAS-2002. The 2002 45th Midwest Symposium on
Publication Date
2002-08-01
