COVID Detection in Chest CTs: Improving the Baseline on COV19-CT-DB

TL;DR

This paper compares three deep learning methods for COVID-19 detection in chest CT scans, achieving significant performance improvements over the baseline on the COV19-CT-DB dataset.

Contribution

It introduces and evaluates three distinct deep learning approaches, including a volumetric 3D method, for COVID-19 detection in chest CTs, surpassing existing baseline performance.

Findings

Best model achieves macro-F1 score of 0.92

Significant improvement over baseline score of 0.70

Demonstrates effectiveness of volumetric and slice-wise approaches

Abstract

The paper presents a comparative analysis of three distinct approaches based on deep learning for COVID-19 detection in chest CTs. The first approach is a volumetric one, involving 3D convolutions, while the other two approaches perform at first slice-wise classification and then aggregate the results at the volume level. The experiments are carried on the COV19-CT-DB dataset, with the aim of addressing the challenge raised by the MIA-COV19D Competition within ICCV 2021. Our best results on the validation subset reach a macro-F1 score of 0.92, which improves considerably the baseline score of 0.70 set by the organizers.