You are here

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

Printer-friendly versionPrinter-friendly version
Zohora FT, Antani SK, Santosh KC
Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105741V (2 March 2018); doi: 10.1117/12.2293739; doi.org/10.1117/12.2293739.
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 normalized cross-correlation using a few templates to collect potential circle-like elements and unsupervised clustering 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% and outperforms existing techniques that are reported in the literature.

© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Zohora FT, Antani SK, Santosh KC. Circle-like foreign element detection in chest x-rays using normalized cross-correlation and unsupervised clustering. Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105741V (2 March 2018); doi: 10.1117/12.2293739; doi.org/10.1117/12.2293739.