RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection

TL;DR

This paper introduces RCoNet, a robust deep learning model for COVID-19 detection from chest X-ray images that maximizes mutual information, leverages high-order statistics, and incorporates uncertainty estimation to improve accuracy and reliability.

Contribution

The paper proposes RCoNet, a novel framework combining deformable mutual information maximization, high-order feature extraction, and multi-expert uncertainty-aware learning for enhanced COVID-19 detection.

Findings

Improved detection accuracy on COVID-19 CXR datasets.

Effective uncertainty estimation reduces misclassification.

Enhanced feature representation through high-order statistics.

Abstract

The novel 2019 Coronavirus (COVID-19) infection has spread world widely and is currently a major healthcare challenge around the world. Chest Computed Tomography (CT) and X-ray images have been well recognized to be two effective techniques for clinical COVID-19 disease diagnoses. Due to faster imaging time and considerably lower cost than CT, detecting COVID-19 in chest X-ray (CXR) images is preferred for efficient diagnosis, assessment and treatment. However, considering the similarity between COVID-19 and pneumonia, CXR samples with deep features distributed near category boundaries are easily misclassified by the hyper-planes learned from limited training data. Moreover, most existing approaches for COVID-19 detection focus on the accuracy of prediction and overlook the uncertainty estimation, which is particularly important when dealing with noisy datasets. To alleviate these concerns, we propose a novel deep network named {\em RCoNet$^k_s$} for robust COVID-19 detection which employs {\em Deformable Mutual Information Maximization} (DeIM), {\em Mixed High-order Moment Feature} (MHMF) and {\em Multi-expert Uncertainty-aware Learning} (MUL). With DeIM, the mutual information (MI) between input data and the corresponding latent representations can be well estimated and maximized to capture compact and disentangled representational characteristics. Meanwhile, MHMF can fully explore the benefits of using high-order statistics and extract discriminative features of complex distributions in medical imaging. Finally, MUL creates multiple parallel dropout networks for each CXR image to evaluate uncertainty and thus prevent performance degradation caused by the noise in the data.