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

TL;DR

This paper introduces an infection-aware 3D contrastive mixup classification network that leverages lesion segmentation masks and weighted loss to improve COVID-19 severity detection from chest CT images, achieving first place in a competition.

Contribution

The novel infection-aware 3D contrastive mixup classification network effectively integrates lesion segmentation and weighted loss to enhance severity grading accuracy.

Findings

Achieved first place with a Macro F1 Score of 51.76%.

Outperformed baseline by over 11.46%.

Effectively handled data imbalance issues.

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%.