doi: 10.4304//jsw.4.9.1014-1021
A New Ensemble Learning Approach for Microcalcification Clusters Detection
- School of Management, Xi'AN University of Architecture and Technology, Xi’AN, China
Abstract
A new microcalcification clusters (MCs) detectionmethod in mammograms is proposed, which is based on anew ensemble learning method. In this paper, we propose abagging with adaptive cost adjustment ensemble algorithm;and a new ensemble strategy, called boosting with relevancefeedback, by embedding the relevance feedback techniqueinto the heterogenous base learner training, and meanwhilecarefully design an effectively systematical feedback scheme,which promise the preventing of overfitting. The groundtruth of MCs is assumed to be known as a priori. In ouralgorithm, each MCs is enhanced by a well designed highpassfilter. Then the 116 dimentional image features areextracted by the feature extractor and fed to the ensembledecision model. In image feature domain, the MCs detectionprocedure is formulated as a supervised learning andclassification problem, and the trained ensemble model isused as a classifier to decide the presence of MCs or not.Case study on microcalcification clusters detection forbreast cancer diagnosis illustrates that the proposedalgorithm is not only effective but also efficiency.
Keywords
- feature
- microcalcification clusters
- ba
How to Cite
Xinsheng Zhang, "A New Ensemble Learning Approach for Microcalcification Clusters Detection," Journal of Software, vol. 4, no. 9, pp. 1014-1021, 2009. https://doi.org/ 10.4304//jsw.4.9.1014-1021
Copyright & License
Copyright © 2009 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
