D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanism (preprint)

Coronavirus Disease 2019 (COVID-19) has caused great casualties and becomes almost the most urgent public health events worldwide. Computed tomography (CT) is a significant screening tool for COVID-19 infection, and automated segmentation of lung infection in COVID-19 CT images will greatly assist diagnosis and health care of patients. However, accurate and automatic segmentation of COVID-19 lung infections remains to be challenging. In this paper we propose a dilated dual attention U-Net (D2A U-Net) for COVID-19 lesion segmentation in CT slices based on dilated convolution and a novel dual attention mechanism to address the issues above. We introduce a dilated convolution module in model decoder to achieve large receptive field, which refines decoding process and contributes to segmentation accuracy. Also, we present a dual attention mechanism composed of two attention modules which are inserted to skip connection and model decoder respectively. The dual attention mechanism is utilized to refine feature maps and reduce semantic gap between different levels of the model. The proposed method has been evaluated on open-source dataset and outperforms cutting edges methods in semantic segmentation. Our proposed D2A U-Net with pretrained encoder achieves a Dice score of 0.7298 and recall score of 0.7071. Besides, we also build a simplified D2A U-Net without pretrained encoder to provide a fair comparison with other models trained from scratch, which still outperforms popular U-Net family models with a Dice score of 0.7047 and recall score of 0.6626. Our experiment results have shown that by introducing dilated convolution and dual attention mechanism, the number of false positives is significantly reduced, which improves sensitivity to COVID-19 lesions and subsequently brings significant increase to Dice score.

A CRISPR-Cas12a-based specific enhancer for more sensitive detection of SARS-CoV-2 infection (preprint)

High Ct-values falling in the grey zone are frequently encountered in SARS-CoV-2 detection by real-time reverse transcription PCR (rRT-PCR) and have brought urgent challenges in diagnosis of samples with low viral load. Based on the single-stranded DNA reporter trans-cleavage activity by Cas12a upon target DNA recognition, we create a Specific Enhancer for detection of PCR-amplified Nucleic Acids (SENA) to confirm SARS-CoV-2 detection through specifically targeting its rRT-PCR amplicons. SENA is highly sensitive, with its limit of detection being at least 2 copies/reaction lower than that of the corresponding rRT-PCR, and highly specific, which identifies both false-negative and false-positive cases in clinic applications. SENA provides effective confirmation for nucleic acid amplification-based molecular diagnosis, and may immediately eliminate the uncertainty problems of rRT-PCR in SARS-CoV-2 clinic detection. One Sentence SummaryCRISPR-Cas12a-based COVID-19 diagnosis.

A preliminary study on the reproductive toxicity of GS-5734 on male mice (preprint)

Background GS-5734 as a novel and promising medicine for COVID-2019, its biological impact on the mammalian reproductive system has not been systematically studied. The aim of this study was to evaluate the effects of GS-5734 on sperm parameters and spermatogenesis in mice. Materials and Methods In this study, GS-5734 was synthesized according to the report. 28 adult male mice were randomly segregated into four groups (n=7 for each group). The group 1 was set as the control group, the group 1, 2, 3 and 4 were administered with GS-5734 at a daily dose of 0, 10, 50, 150 μg/mouse respectively, by intraperitoneal injection for 10 days. On the 7th day after the last injection, the testes and cauda epididymides were collected for HE staining and sperm concentration, motility, morphology analysis. Results The results indicated that after treated with GS-5734, the total sperm count and motile sperm rate showed downward trends, the abnormal sperm rate showed an increasing trend. As compared with the control group, GS-5734 at a daily dose of 150 μg/mouse caused a significant decrease in sperm concentration and motility, and a significant increased of abnormal sperm rate; the 50 μg/mouse drug treatment lead to a significant decrease in sperm motility and an increase in abnormal sperm rate. The HE staining of testicular and epididymal tissues showed that the spermatogenesis of mice was significantly deteriorated with the increasing dosage of GS-5734, especially in the 150 μg/mouse group. Conclusion Our findings suggest that a high dosage of GS-5734 may induce testicular toxicity and result in deterioration of sperm parameters in mice. More investigation on the reproductive toxicity of GS-5734 is required.