Skip to main content

Research Repository

Advanced Search

Improving Uncertainty Estimation With Semi-supervised Deep Learning for COVID-19 Detection Using Chest X-ray Images

Calderon-Ramirez, Saul; Yang, Shengxiang; Moemeni, Armaghan; Colreavy-Donnelly, Simon; Elizondo, David A.; Oala, Luis; Rodríguez-Capitán, Jorge; Jiménez-Navarro, Manuel; López-Rubio, Ezequiel; Molina-Cabello, Miguel A.

Improving Uncertainty Estimation With Semi-supervised Deep Learning for COVID-19 Detection Using Chest X-ray Images Thumbnail


Authors

Saul Calderon-Ramirez

Shengxiang Yang

Simon Colreavy-Donnelly

David A. Elizondo

Luis Oala

Jorge Rodríguez-Capitán

Manuel Jiménez-Navarro

Ezequiel López-Rubio

Miguel A. Molina-Cabello



Contributors

Abstract

In this work we implement a COVID-19 infection detection system based on chest Xray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.

Citation

Calderon-Ramirez, S., Yang, S., Moemeni, A., Colreavy-Donnelly, S., Elizondo, D. A., Oala, L., …Molina-Cabello, M. A. (2021). Improving Uncertainty Estimation With Semi-supervised Deep Learning for COVID-19 Detection Using Chest X-ray Images. IEEE Access, 9, 85442 - 85454. https://doi.org/10.1109/ACCESS.2021.3085418

Journal Article Type Article
Acceptance Date May 22, 2021
Online Publication Date Jun 2, 2021
Publication Date 2021
Deposit Date Jun 4, 2021
Publicly Available Date Mar 29, 2024
Journal IEEE Access
Electronic ISSN 2169-3536
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Peer Reviewed Peer Reviewed
Volume 9
Pages 85442 - 85454
DOI https://doi.org/10.1109/ACCESS.2021.3085418
Keywords Uncertainty estimation , Coronavirus , Covid-19 , Chest X-Ray , Computer Aided Diagnosis , Semi-Supervised Deep Learning , MixMatch
Public URL https://nottingham-repository.worktribe.com/output/5625937
Publisher URL https://ieeexplore.ieee.org/document/9445026

Files





You might also like



Downloadable Citations