Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification

TL;DR

This paper introduces a novel joint learning framework with a redesigned COVID-Net backbone and contrastive training to improve COVID-19 CT classification across heterogeneous datasets, addressing domain shifts and enhancing accuracy.

Contribution

It proposes a new multi-site learning method with a redesigned network and contrastive loss to handle cross-site domain discrepancies in COVID-19 CT classification.

Findings

Achieved over 12% improvement in AUC on two datasets.

Outperformed original COVID-Net and existing multi-site methods.

Enhanced domain invariance and classification accuracy.

Abstract

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performances on both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.