Multi-view probabilistic classification of breast microcalcifications

Alan Joseph Bekker, Moran Shalhon, Hayit Greenspan, Jacob Goldberger*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. In this paper we apply a multi-view-classifier for the task. We describe a two-step classification method that is based on a view-level decision, implemented by a logistic regression classifier, followed by a stochastic combination of the two view-level indications into a single benign or malignant decision. The proposed method was evaluated on a large number of cases from a standardized digital database for screening mammography (DDSM). Experimental results demonstrate the advantage of the proposed multi-view classification algorithm that automatically learns the best way to combine the views.

Original languageEnglish
Article number2488019
Pages (from-to)645-6536
Number of pages5892
JournalIEEE Transactions on Medical Imaging
Issue number2
StatePublished - 1 Feb 2016


  • Computer-aided diagnosis (CADx)
  • Curvelet transform
  • Mammography
  • Microcalcifications
  • Multi-view analysis


Dive into the research topics of 'Multi-view probabilistic classification of breast microcalcifications'. Together they form a unique fingerprint.

Cite this