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

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 (Inf-Net) is proposed to automatically identify infected regions from chest CT slices. In our Inf-Net, 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 COVID-SemiSeg and real CT volumes demonstrate that the proposed Inf-Net outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.

Structure of RNA-dependent RNA polymerase from 2019-nCoV, a major antiviral drug target (preprint)

A novel coronavirus (2019-nCoV) outbreak has caused a global pandemic resulting in tens of thousands of infections and thousands of deaths worldwide. The RNA-dependent RNA polymerase (RdRp, also named nsp12), which catalyzes the synthesis of viral RNA, is a key component of coronaviral replication/transcription machinery and appears to be a primary target for the antiviral drug, remdesivir. Here we report the cryo-EM structure of 2019-nCoV full-length nsp12 in complex with cofactors nsp7 and nsp8 at a resolution of 2.9-[A]. Additional to the conserved architecture of the polymerase core of the viral polymerase family and a nidovirus RdRp-associated nucleotidyltransferase (NiRAN) domain featured in coronaviral RdRp, nsp12 possesses a newly identified {beta}-hairpin domain at its N-terminal. Key residues for viral replication and transcription are observed. A comparative analysis to show how remdesivir binds to this polymerase is also provided. This structure provides insight into the central component of coronaviral replication/transcription machinery and sheds light on the design of new antiviral therapeutics targeting viral RdRp. One Sentence SummaryStructure of 2019-nCov RNA polymerase.