Automatic detection of pneumonia analyzing ultrasound digital images

Ronald Barrientos, Avid Roman-Gonzalez, Franklin Barrientos, Leonardo Solis, Malena Correa, Monica Pajuelo, Cynthia Anticona, Roberto Lavarello, Benjamin Castaneda, Richard Oberhelman, William Checkley, Robert H Gilman, Mirko Zimic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Pneumonia is one of the major causes of child mortality. Unfortunately, in developing countries there is a lack of infrastructure and medical experts in rural areas to provide the required diagnostics opportunely. Lung ultrasound echography has proved to be an important tool to detect lung consolidates as evidence of pneumonia. This paper presents a method for automatic diagnostics of pneumonia using ultrasound imaging of the lungs. The approach presented here is based on the analysis of patterns present in rectangular segments from the ultrasound digital images. Specific features from the characteristic vectors were obtained and classified with standard neural networks. A training and testing set of positive and negative vectors were compiled. Vectors obtained from a single patient were included only in the testing or in the training set, but never in both. Our approach was able to correctly classify vectors with evidence of pneumonia, with 91.5% sensitivity and 100% specificity.

Original languageEnglish (US)
Title of host publication2016 IEEE 36th Central American and Panama Convention, CONCAPAN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467395786
DOIs
StatePublished - Jun 7 2017
Event36th IEEE Central American and Panama Convention, CONCAPAN 2016 - San Jose, Costa Rica
Duration: Nov 9 2016Nov 11 2016

Other

Other36th IEEE Central American and Panama Convention, CONCAPAN 2016
CountryCosta Rica
CitySan Jose
Period11/9/1611/11/16

Keywords

  • echography
  • image processing
  • Pneumonia
  • remote diagnostics
  • ultrasound

ASJC Scopus subject areas

  • Modeling and Simulation
  • Health Informatics
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems and Management
  • Energy Engineering and Power Technology

Fingerprint Dive into the research topics of 'Automatic detection of pneumonia analyzing ultrasound digital images'. Together they form a unique fingerprint.

  • Cite this

    Barrientos, R., Roman-Gonzalez, A., Barrientos, F., Solis, L., Correa, M., Pajuelo, M., Anticona, C., Lavarello, R., Castaneda, B., Oberhelman, R., Checkley, W., Gilman, R. H., & Zimic, M. (2017). Automatic detection of pneumonia analyzing ultrasound digital images. In 2016 IEEE 36th Central American and Panama Convention, CONCAPAN 2016 [7942375] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CONCAPAN.2016.7942375