K C Santosh
University of South Dakota, USA
Title: Automated chest X-ray screening for the evidence of pulmonary abnormalities
Biography
Biography: K C Santosh
Abstract
The talk is aimed at presenting an automatic chest X-rays screening system to detect pulmonary abnormalities using chest X-rays (CXR) in non-hospital settings. In particular, the primary motivator of the project is the need for screening HIV+ populations in resource-constrained regions for the evidence of Tuberculosis (TB). The system analyzes thoracic edge map, shapes as well as symmetry that exists between the lung sections of the posteroanterior CXRs. In this study, we have used two CXR benchmark collections made available by the U.S. National Library of Medicine and have achieved a maximum abnormality detection accuracy of 88.67% and the corresponding area under the ROC curve of 0.95, which outperforms the reported state-of-the-art.