Lung infection and normal region segmentation from CT volumes of COVID-19 cases

TL;DR

This paper introduces an automated segmentation method using a fully convolutional network to distinguish infection and normal lung regions in COVID-19 CT scans, aiding diagnosis with high accuracy.

Contribution

It presents a novel FCN architecture with dense pooling and dilated convolutions for effective COVID-19 lung region segmentation.

Findings

Dice score for normal regions: 0.911

Dice score for infection regions: 0.753

Effective across mild to severe COVID-19 cases

Abstract

This paper proposes an automated segmentation method of infection and normal regions in the lung from CT volumes of COVID-19 patients. From December 2019, novel coronavirus disease 2019 (COVID-19) spreads over the world and giving significant impacts to our economic activities and daily lives. To diagnose the large number of infected patients, diagnosis assistance by computers is needed. Chest CT is effective for diagnosis of viral pneumonia including COVID-19. A quantitative analysis method of condition of the lung from CT volumes by computers is required for diagnosis assistance of COVID-19. This paper proposes an automated segmentation method of infection and normal regions in the lung from CT volumes using a COVID-19 segmentation fully convolutional network (FCN). In diagnosis of lung diseases including COVID-19, analysis of conditions of normal and infection regions in the lung is important. Our method recognizes and segments lung normal and infection regions in CT volumes. To segment infection regions that have various shapes and sizes, we introduced dense pooling connections and dilated convolutions in our FCN. We applied the proposed method to CT volumes of COVID-19 cases. From mild to severe cases of COVID-19, the proposed method correctly segmented normal and infection regions in the lung. Dice scores of normal and infection regions were 0.911 and 0.753, respectively.