Linguistics

Philosophy

Contrast (vision)

Government (linguistics)

Computer science

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)

Coronavirus disease 2019 (COVID-19)

Segmentation

Economic shortage

Pattern recognition (psychology)

Infectious disease (medical specialty)

Artificial intelligence

Medicine

Deep learning

Disease

Machine learning

Pathology

IEEE Transactions on Medical Imaging

Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Inf-Net</i> ) is proposed to automatically identify infected regions from chest CT slices. In our <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Inf-Net</i> , a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on our <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COVID-SemiSeg</i> and real CT volumes demonstrate that the proposed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Inf-Net</i> outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.

Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images