Circle-like foreign element detection in chest x-rays using normalized cross-correlation and unsupervised clustering

Fatema Tuz Zohora, Sameer K. Antani, KC Santosh

Abstract: Presence of foreign objects (buttons, medical devices) adversely impact the performance of the automated chest X-ray (CXR) screening. We present a novel image processing and machine learning technique to detect circle-like foreign elements in CXR images that helps avoid confusions in automated detection of abnormalities, such as nodules and other calcifications. In our technique, we apply <strong>normalized cross-correlation</strong> using a few templates to collect potential circle-like elements and <strong>unsupervised clustering</strong> to make a decision. We validated our fully automatic technique on a set of 400 publicly available images hosted by LHNCBC, U.S. National Library of Medicine (NLM), National Institutes of Health (NIH). Our method achieved an accuracy greater than 90&percnt; and outperforms existing techniques that are reported in the literature.