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

Ziqi Wang, Rami J. Haddad

Research output: Contribution to book or proceedingConference articlepeer-review

2 Scopus citations

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%.

Original languageEnglish
Title of host publicationIEEE SoutheastCon 2020, SoutheastCon 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728168616
DOIs
StatePublished - Mar 28 2020
Event2020 IEEE SoutheastCon, SoutheastCon 2020 - Virtual, Raleigh, United States
Duration: Mar 28 2020Mar 29 2020

Publication series

NameConference Proceedings - IEEE SOUTHEASTCON
Volume2020-March
ISSN (Print)1091-0050
ISSN (Electronic)1558-058X

Conference

Conference2020 IEEE SoutheastCon, SoutheastCon 2020
Country/TerritoryUnited States
CityVirtual, Raleigh
Period03/28/2003/29/20

Keywords

  • Convolutional Neural Networks
  • Deep Learning
  • Medical Imaging
  • Pneumothorax
  • Radiograph Processing

Fingerprint

Dive into the research topics of 'Automated Diagnosis of Pneumothorax X-ray Images Utilizing Deep Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this