#156:
S. Candemir,
S. Jaeger,
K. Palaniappan,
S. Antani, and
G. Thoma
IEEE Healthcare Innovation Conference,
2012
Abstract,
Bibtex,
PlainText,
PDF,
Google Scholar
The National Library of Medicine (NLM) is de- veloping a digital chest x-ray (CXR) screening system for deployment in resource constrained communities. An important first step in the analysis of digital CXRs is the automatic detection of the lung regions. In this paper, we present a graph cut based robust lung segmentation method that detects the lungs with high accuracy. The method consists of two stages: (i) average lung shape model calculation, and (ii) lung boundary detection based on graph cut. Preliminary results on public chest x-rays demonstrate the robustness of the method.
@inproceedings{Sema:HIC-2012-lung-seg,
author = "S. Candemir and S. Jaeger and K. Palaniappan and S. Antani and G. Thoma",
title = "Graph cut based automatic lung boundary detection in chest radiographs",
year = 2012,
booktitle = "IEEE Healthcare Innovation Conference",
keywords = "registration, segmentation, graph methods, anatomical, biomedical"
}
S. Candemir, S. Jaeger, K. Palaniappan, S. Antani, and G. Thoma. Graph cut based automatic lung boundary detection in chest radiographs. IEEE Healthcare Innovation Conference, 2012.