Addressing image variability while learning classifiers for detecting clusters of micro-calcifications

Authors:
Glenn Fung;Balaji Krishnapuram;Nicolas Merlet;Eli Ratner;Philippe Bamberger;Jonathan Stoeckel;R. Bharat Rao
Affiliations:
Computer Aided Diagnosis & Therapy group, Siemens Medical Solutions USA, Inc., Malvern;Computer Aided Diagnosis & Therapy group, Siemens Medical Solutions USA, Inc., Malvern;Beck building, Siemens Computer Aided Diagnosis, Jerusalem, Israel;Beck building, Siemens Computer Aided Diagnosis, Jerusalem, Israel;Beck building, Siemens Computer Aided Diagnosis, Jerusalem, Israel;Siemens Information Systems Ltd, Bangalore, India;Computer Aided Diagnosis & Therapy group, Siemens Medical Solutions USA, Inc., Malvern
Venue:
IWDM'06 Proceedings of the 8th international conference on Digital Mammography
Year:
2006

Citing 4
Cited 0

Bagging predictors

Machine Learning
SSVM: A Smooth Support Vector Machine for Classification

Computational Optimization and Applications
Sparse bayesian learning and the relevance vector machine

The Journal of Machine Learning Research
Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Computer aided detection systems for mammography typically use standard classification algorithms from machine learning for detecting lesions. However, these general purpose learning algorithms make implicit assumptions that are commonly violated in CAD problems. We propose a new ensemble algorithm that explicitly accounts for the small fraction of outlier images which tend to produce a large number of false positives. A bootstrapping procedure is used to ensure that the candidates from these outlier images do not skew the statistical properties of the training samples. Experimental studies on the detection of clusters of micro-calcifications indicate that the proposed method significantly outperforms a state-of-the-art general purpose method for designing classifiers (SVM), in terms of FROC curves on a hold out test set.