Boosting COVID-19 Severity Detection with Infection-aware Contrastive Mixup Classification
This work addresses the problem of automated severity grading for COVID-19 patients, which is incremental as it builds on existing methods with specific enhancements for data imbalance and infection awareness.
The paper tackled COVID-19 severity detection from chest CT images by developing an infection-aware 3D Contrastive Mixup Classification network, achieving first place in a competition with a Macro F1 Score of 51.76% and outperforming the baseline by over 11.46%.
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%.