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

• Published in: Medical image analysis 2014-02, Vol.18 (2), p.241-252
• Main Authors: Bria, A., Karssemeijer, N., Tortorella, F.
• Format: Article
• Language: English
• Subjects: Algorithms; Breast Neoplasms - diagnostic imaging; Calcinosis - diagnostic imaging; Clustered microcalcifications; Computer aided detection; Female; Humans; Mammography; Mammography - methods; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Unbalanced data
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2013.10.014

[Display omitted] •Finding abnormalities in diagnostic images involves a skewed classification problem.•Our approach faces the class imbalance with a cascade of boosted ranking classifiers.•On this basis we designed a CADe system (CasCADe) for clustered microcalcifications.•We show that CasCADe can compete with high-end CADe commercial systems such as R2CAD.•The time necessary to completely process a mammogram was about 3s. 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.