Boosting COVID-19 Severity Detection with Infection-aware Contrastive Mixup Classification

2022/11/26 by Junlin Hou, Hou, Junlin, Jilan Xu +9 · 2 citations
Computer Science · Engineering · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Radiomics and Machine Learning in Medical Imaging #cs.CV #eess.IV

paper · pdf · doi:10.48550/arxiv.2211.14559

ECCV AIMIA Workshop 2022

arxiv created 2022/12/01 · arxiv updated 2022/12/02

Abstract

This paper presents our solution for the 2nd COVID-19 Severity Detection Competition. This task aims to distinguish the Mild, Moderate, Severe, and Critical grades in COVID-19 chest CT images. In our approach, we devise a novel infection-aware 3D Contrastive Mixup Classification network for severity grading. Specifcally, we train two segmentation networks to first extract the lung region and then the inner lesion region. The lesion segmentation mask serves as complementary information for the original CT slices. To relieve the issue of imbalanced data distribution, we further improve the advanced Contrastive Mixup Classification network by weighted cross-entropy loss. On the COVID-19 severity detection leaderboard, our approach won the first place with a Macro F1 Score of 51.76%. It significantly outperforms the baseline method by over 11.46%.

Cited by

• Advancing Lung Disease Diagnosis in 3D CT Scans
• Multi-Source COVID-19 Detection via Variance Risk Extrapolation

Related

• FDVTS's Solution for 2nd COV19D Competition on COVID-19 Detection and Severity Analysis
• Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images
• Enhancing COVID-19 Severity Analysis through Ensemble Methods
• COVID-Net CT-S: 3D Convolutional Neural Network Architectures for COVID-19 Severity Assessment using Chest CT Images
• CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors