UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection

Authors

Moloud Abdar, The Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia
Soorena Salari, The Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran
Sina Qahremani, The Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran
Hak-Keung Lam, The Centre for Robotics Research, Department of Engineering, King’s College London, London, United Kingdom
Fakhreddine (Fakhri) Karray, The Centre for Pattern Analysis and Machine Intelligence, Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada & Mohamed bin Zayed University of Artificial IntelligenceFollow
Sadiq Hussain, The System Administrator, Dibrugarh University, Dibrugarh, India
Abbas Khosravi, The Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia
U. Rajendra Acharya, The Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Clementi, Singapore
Vladimir Makarenkov, The Department of Computer Science, University of Quebec in Montreal, Montreal, QC, Canada
Saeid Nahavandi, The Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia & The Harvard Paulson School of Engineering and Applied Sciences, Harvard University, Allston, 02134, MA, United States

Document Type

Article

Publication Title

Information Fusion

Abstract

The COVID-19 (Coronavirus disease 2019) pandemic has become a major global threat to human health and well-being Thus, the development of computer-aided detection (CAD) systems that are capable to accurately distinguish COVID-19 from other diseases using chest computed tomography (CT) and X-ray data is of immediate priority Such automatic systems are usually based on traditional machine learning or deep learning methods Differently from most of existing studies, which used either CT scan or X-ray images in COVID-19-case classification, we present a simple but efficient deep learning feature fusion model, called UncertaintyFuseNet, which is able to classify accurately large datasets of both of these types of images We argue that the uncertainty of the model’s predictions should be taken into account in the learning process, even though most of existing studies have overlooked it We quantify the prediction uncertainty in our feature fusion model using effective Ensemble MC Dropout (EMCD) technique A comprehensive simulation study has been conducted to compare the results of our new model to the existing approaches, evaluating the performance of competing models in terms of Precision, Recall, F-Measure, Accuracy and ROC curves The obtained results prove the efficiency of our model which provided the prediction accuracy of 99.08% and 96.35% for the considered CT scan and X-ray datasets, respectively Moreover, our UncertaintyFuseNet model was generally robust to noise and performed well with previously unseen data The source code of our implementation is freely available at: https://github.com/moloud1987/UncertaintyFuseNet-for-COVID-19-Classification. Copyright © 2021, The Authors. All rights reserved.

First Page

364

Last Page

381

DOI

10.1016/j.inffus.2022.09.023

Publication Date

2-2023

Keywords

COVID-19, Deep learning, Early fusion, Feature fusion, Uncertainty quantification, Classification (of information), Computer aided diagnosis, Computerized tomography, Deep learning, Forecasting, Health risks, Large dataset, Risk assessment

Comments

Open Access version from King's Research Portal

Uploaded on June 21, 2024

Recommended Citation

M. Abdar et al., "UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection," Information Fusion, vol. 90, pp. 364 - 381, Feb 2023. doi: 10.1016/j.inffus.2022.09.023