Detecting and classifying linear structures in mammograms using random forests.

Michael Berks, Zezhi Chen, Sue Astley, Chris Taylor

Research output: Contribution to journalArticlepeer-review

Abstract

Detecting and classifying curvilinear structure is important in many image interpretation tasks. We focus on the challenging problem of detecting such structure in mammograms and deciding whether it is normal or abnormal. We adopt a discriminative learning approach based on a Dual-Tree Complex Wavelet representation and random forest classification. We present results of a quantitative comparison of our approach with three leading methods from the literature and with learning-based variants of those methods. We show that our new approach gives significantly better results than any of the other methods, achieving an area under the ROC curve A(z) = 0.923 for curvilinear structure detection, and A(z) = 0.761 for distinguishing between normal and abnormal structure (spicules). A detailed analysis suggests that some of the improvement is due to discriminative learning, and some due to the DT-CWT representation, which provides local phase information and good angular resolution.
Original languageEnglish
Pages (from-to)510-24
Number of pages485
JournalInformation Processing in Medical Imaging
Volume22
Publication statusPublished - 2011

Fingerprint

Dive into the research topics of 'Detecting and classifying linear structures in mammograms using random forests.'. Together they form a unique fingerprint.

Cite this