Skip to main content

ORIGINAL RESEARCH article

Front. Artif. Intell.
Sec. Machine Learning and Artificial Intelligence
Volume 7 - 2024 | doi: 10.3389/frai.2024.1410841

Uncertainty Quantification in Multi-class Image Classification using Chest X-ray images of Covid-19 and Pneumonia

Provisionally accepted
Albert Whata Albert Whata *Katlego Dibeco Katlego Dibeco Kudakwashe Madzima Kudakwashe Madzima Ibidun OBAGBUWA Ibidun OBAGBUWA
  • Sol Plaatje University, Kimberley, South Africa

The final, formatted version of the article will be published soon.

    This paper investigates uncertainty quantification (UQ) techniques in multi-class classification of chest X-ray images Pneumonia, and Normal). We evaluate Bayesian Neural Networks (BNN) and various Deep Neural Networks with UQ (DNN with UQ) techniques, including Monte Carlo dropout, Ensemble Bayesian Neural Network (EBNN), Ensemble Monte Carlo (EMC) dropout, across different evaluation metrics. Our analysis reveals that DNNs with UQ, especially EBNN and EMC dropout, consistently outperform BNNs. For example, in Class 0 vs. All, EBNN achieved a U Acc of 92.6%, U AUC-ROC of 95.0%, and a Brier Score of 0.157, significantly surpassing BNN's performance. Similarly, EMC Dropout excelled in Class 1 vs. All with a U Acc of 83.5%, U AUC-ROC of 95.8%, and a Brier Score of 0.165. These advanced models demonstrated higher accuracy, better discriaminative capability, and more accurate probabilistic predictions. Our findings highlight the efficacy of DNNs with UQ in enhancing model reliability and interpretability, making them highly suitable for critical healthcare applications like chest X-ray image classification.

    Keywords: Uncertainty quantification deep neural networks, Bayesian neural networks, Monte Carlo dropout, Ensemble Monte Carlo, chest-x-ray, classificationn metrics, multi-class classification

    Received: 01 Apr 2024; Accepted: 29 Aug 2024.

    Copyright: © 2024 Whata, Dibeco, Madzima and OBAGBUWA. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Albert Whata, Sol Plaatje University, Kimberley, South Africa

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.