Format

Send to

Choose Destination
Med Image Anal. 2014 Feb;18(2):241-52. doi: 10.1016/j.media.2013.10.014. Epub 2013 Nov 12.

Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications.

Author information

1
Department of Electrical and Information Engineering, University of Cassino and L.M., Via Di Biasio 43, 03043 Cassino (FR), Italy. Electronic address: a.bria@unicas.it.
2
Diagnostic Image Analysis Group, Radboud University Nijmegen Medical Centre, P.O. Box 9102, 6500 HC Nijmegen, The Netherlands. Electronic address: n.karssemeijer@rad.umcn.nl.
3
Department of Electrical and Information Engineering, University of Cassino and L.M., Via Di Biasio 43, 03043 Cassino (FR), Italy. Electronic address: tortorella@unicas.it.

Abstract

Finding abnormalities in diagnostic images is a difficult task even for expert radiologists because the normal tissue locations largely outnumber those with suspicious signs which may thus be missed or incorrectly interpreted. For the same reason the design of a Computer-Aided Detection (CADe) system is very complex because the large predominance of normal samples in the training data may hamper the ability of the classifier to recognize the abnormalities on the images. In this paper we present a novel approach for computer-aided detection which faces the class imbalance with a cascade of boosting classifiers where each node is trained by a learning algorithm based on ranking instead of classification error. Such approach is used to design a system (CasCADe) for the automated detection of clustered microcalcifications (μCs), which is a severely unbalanced classification problem because of the vast majority of image locations where no μC is present. The proposed approach was evaluated with a dataset of 1599 full-field digital mammograms from 560 cases and compared favorably with the Hologic R2CAD ImageChecker, one of the most widespread commercial CADe systems. In particular, at the same lesion sensitivity of R2CAD (90%) on biopsy proven malignant cases, CasCADe and R2CAD detected 0.13 and 0.21 false positives per image (FPpi), respectively (p-value=0.09), whereas at the same FPpi of R2CAD (0.21), CasCADe and R2CAD detected 93% and 90% of true lesions respectively (p-value=0.11) thus showing that CasCADe can compete with high-end CADe commercial systems.

KEYWORDS:

Clustered microcalcifications; Computer aided detection; Mammography; Unbalanced data

PMID:
24292553
DOI:
10.1016/j.media.2013.10.014
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center