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

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.

Published as a journal paper at IEEE J-BHI; code and dataset are available at https://github.com/med-air/Contrastive-COVIDNet

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
• Extracting possibly representative COVID-19 Biomarkers from X-Ray images with Deep Learning approach and image data related to Pulmonary Diseases
• MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data
• Radiologist-Level COVID-19 Detection Using CT Scans with Detail-Oriented Capsule Networks
• Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects
• CovidCTNet: An Open-Source Deep Learning Approach to Identify Covid-19 Using CT Image
• Unpaired Multi-modal Segmentation via Knowledge Distillation

Cited by in corpus (6)

• Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
• Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation
• Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images
• Clinically Labeled Contrastive Learning for OCT Biomarker Classification
• Classification of COVID-19 via Homology of CT-SCAN
• Explainability Guided Multi-Site COVID-19 CT Classification