Electrical & Computer Engineering: Faculty Publications

Automated Diagnosis of Pneumothorax X-ray Images Utilizing Deep Convolutional Neural Network

Document Type

Conference Proceeding

Publication Date

3-28-2020

Publication Title

SoutheastCon 2020 Proceedings

DOI

10.1109/SoutheastCon44009.2020.9249683

Abstract

Pneumothorax is a severe respiratory disease. In this study, an algorithm using a Deep Convolutional Neural Network (DCNN) is proposed to detect visual signs for Pneumothorax within X-ray images and conduct a diagnosis. Detecting and diagnosing Pneumothorax remains challenging despite of its prevalence. The deep residual network ResNet-101 was adapted through transfer learning. A database of 5,302 Pneumothorax radiographs was utilized for training, and a preliminary diagnosis accuracy of 86.26% was obtained. The area under the receiver operating characteristic curve (AUC) was 92.13%.

Comments

Georgia Southern University faculty member, Rami J. Haddad co-authored, "Automated Diagnosis of Pneumothorax X-ray Images Utilizing Deep Convolutional Neural Network."

Copyright

See the publisher's copyright and reuse policies.

Share

COinS