HD2A-Net: A novel dual gated attention network using comprehensive hybrid dilated convolutions for medical image segmentation.

The convolutional neural networks (CNNs) have been widely proposed in the medical image analysis tasks, especially in the image segmentations. In recent years, the encoder-decoder structures, such as the U-Net, were rendered. However, the multi-scale information transmission and effective modeling for long-range feature dependencies in these structures were not sufficiently considered. To improve the performance of the existing methods, we propose a novel hybrid dual dilated attention network (HD2A-Net) to conduct the lesion region segmentations. In the proposed network, we innovatively present the comprehensive hybrid dilated convolution (CHDC) module, which facilitates the transmission of the multi-scale information. Based on the CHDC module and the attention mechanisms, we design a novel dual dilated gated attention (DDGA) block to enhance the saliency of related regions from the multi-scale aspect. Besides, a dilated dense (DD) block is designed to expand the receptive fields. The ablation studies were performed to verify our proposed blocks. Besides, the interpretability of the HD2A-Net was analyzed through the visualization of the attention weight maps from the key blocks. Compared to the state-of-the-art methods including CA-Net, DeepLabV3+, and Attention U-Net, the HD2A-Net outperforms significantly, with the metrics of Dice, Average Symmetric Surface Distance (ASSD), and mean Intersection-over-Union (mIoU) reaching 93.16%, 93.63%, and 94.72%, 0.36 pix, 0.69 pix, and 0.52 pix, and 88.03%, 88.67%, and 90.33% on three publicly available medical image datasets: MAEDE-MAFTOUNI (COVID-19 CT), ISIC-2018 (Melanoma Dermoscopy), and Kvasir-SEG (Gastrointestinal Disease Polyp), respectively.

SARS-CoV-2 ORF8 Forms Intracellular Aggregates and Inhibits IFNγ-Induced Antiviral Gene Expression in Human Lung Epithelial Cells.

Infection with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes COVID-19, a disease that involves significant lung tissue damage. How SARS-CoV-2 infection leads to lung injury remains elusive. The open reading frame 8 (ORF8) protein of SARS-CoV-2 (ORF8SARS-CoV-2) is a unique accessory protein, yet little is known about its cellular function. We examined the cellular distribution of ORF8SARS-CoV-2 and its role in the regulation of human lung epithelial cell proliferation and antiviral immunity. Using live imaging and immunofluorescent staining analyses, we found that ectopically expressed ORF8SARS-CoV-2 forms aggregates in the cytosol and nuclear compartments of lung epithelial cells. Using in silico bioinformatic analysis, we found that ORF8SARS-CoV-2 possesses an intrinsic aggregation characteristic at its N-terminal residues 1-18. Cell culture did not reveal any effects of ORF8SARS-CoV-2 expression on lung epithelial cell proliferation and cell cycle progression, suggesting that ORF8SARS-CoV-2 aggregates do not affect these cellular processes. Interestingly, ectopic expression of ORF8SARS-CoV-2 in lung epithelial cells suppressed basal expression of several antiviral molecules, including DHX58, ZBP1, MX1, and MX2. In addition, expression of ORF8SARS-CoV-2 attenuated the induction of antiviral molecules by IFNγ but not by IFNß in lung epithelial cells. Taken together, ORF8SARS-CoV-2 is a unique viral accessory protein that forms aggregates when expressing in lung epithelial cells. It potently inhibits the expression of lung cellular anti-viral proteins at baseline and in response to IFNγ in lung epithelial cells, which may facilitate SARS-CoV-2 escape from the host antiviral innate immune response during early viral infection. In addition, it seems that formation of ORF8SARS-CoV-2 aggregate is independent from the viral infection. Thus, it would be interesting to examine whether any COVID-19 patients exhibit persistent ORF8 SARS-CoV-2 expression after recovering from SARS-CoV-2 infection. If so, the pathogenic effect of prolonged ORF8SARS-CoV-2 expression and its association with post-COVID symptoms warrant investigation in the future.