Advancing COVID-19 Detection in 3D CT Scans
This is an incremental improvement for medical professionals needing more accurate COVID-19 diagnosis from CT scans.
The paper tackled COVID-19 detection in 3D CT scans by proposing a model that removes non-lung parts and uses a pretrained feature extractor, achieving a Macro F1 Score of 0.94 and surpassing the baseline by 16%.
To make a more accurate diagnosis of COVID-19, we propose a straightforward yet effective model. Firstly, we analyse the characteristics of 3D CT scans and remove the non-lung parts, facilitating the model to focus on lesion-related areas and reducing computational cost. We use ResNeSt50 as the strong feature extractor, initializing it with pretrained weights which have COVID-19-specific prior knowledge. Our model achieves a Macro F1 Score of 0.94 on the validation set of the 4th COV19D Competition Challenge $\mathrm{I}$, surpassing the baseline by 16%. This indicates its effectiveness in distinguishing between COVID-19 and non-COVID-19 cases, making it a robust method for COVID-19 detection.