Prior Attention Network for Multi-Lesion Segmentation in Medical Images.

The accurate segmentation of multiple types of lesions from adjacent tissues in medical images is significant in clinical practice. Convolutional neural networks (CNNs) based on the coarse-to-fine strategy have been widely used in this field. However, multi-lesion segmentation remains to be challenging due to the uncertainty in size, contrast, and high interclass similarity of tissues. In addition, the commonly adopted cascaded strategy is rather demanding in terms of hardware, which limits the potential of clinical deployment. To address the problems above, we propose a novel Prior Attention Network (PANet) that follows the coarse-to-fine strategy to perform multi-lesion segmentation in medical images. The proposed network achieves the two steps of segmentation in a single network by inserting a lesion-related spatial attention mechanism in the network. Further, we also propose the intermediate supervision strategy for generating lesion-related attention to acquire the regions of interest (ROIs), which accelerates the convergence and obviously improves the segmentation performance. We have investigated the proposed segmentation framework in two applications: 2D segmentation of multiple lung infections in lung CT slices and 3D segmentation of multiple lesions in brain MRIs. Experimental results show that in both 2D and 3D segmentation tasks our proposed network achieves better performance with less computational cost compared with cascaded networks. The proposed network can be regarded as a universal solution to multi-lesion segmentation in both 2D and 3D tasks. The source code is available at https://github.com/hsiangyuzhao/PANet.

Exploration of molecular targets and mechanisms of Chinese medicinal formula Acacia Catechu -Scutellariae Radix in the treatment of COVID-19 by a systems pharmacology strategy.

Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In China, the Acacia catechu (AC)-Scutellariae Radix (SR) formula has been widely used for pulmonary infection in clinical practice for several centuries. However, the potential role and mechanisms of this formula against COVID-19 remains unclear. The present study was designed to dissect the active ingredients, molecular targets, and the therapeutic mechanisms of AC-SR formula in the treatment of COVID-19 based on a systems pharmacology strategy integrated by ADME screening, target prediction, network analysis, GO and KEGG enrichment analysis, molecular docking, and molecular dynamic (MD) simulations. Finally, Quercetin, Fisetin(1-), kaempferol, Wogonin, Beta-sitosterol, Baicalein, Skullcapflavone II, Stigmasterol were primarily screened to be the potentially effective active ingredients against COVID-19. The hub-proteins were TP53, JUN, ESR1, MAPK1, Akt1, HSP90AA1, TNF, IL-6, SRC, and RELA. The potential mechanisms of AC-SR formula in the treatment of COVID-19 were the TNF signaling pathway, PI3K-Akt signaling pathway and IL-17 signaling pathway, etc. Furthermore, virtual docking revealed that baicalein, (+)-catechin and fisetin(1-) exhibited high affinity to SARS-CoV-2 3CLpro, which has validated by the FRET-based enzymatic inhibitory assays with the IC50 of 11.3, 23.8, and 44.1 µM, respectively. And also, a concentration-dependent inhibition of baicalein, quercetin and (+)-catechin against SARS-CoV-2 ACE2 was observed with the IC50 of 138.2, 141.3, and 348.4 µM, respectively. These findings suggested AC-SR formula exerted therapeutic effects involving "multi-compounds and multi-targets." It might be working through directly inhibiting the virus, improving immune function, and reducing the inflammatory in response to anti-COVID-19. Ultimately, this study would provide new perspective for discovering potential drugs and mechanisms against COVID-19.

D2A U-Net: Automatic segmentation of COVID-19 CT slices based on dual attention and hybrid dilated convolution.

Coronavirus Disease 2019 (COVID-19) has become one of the most urgent public health events worldwide due to its high infectivity and mortality. Computed tomography (CT) is a significant screening tool for COVID-19 infection, and automatic segmentation of lung infection in COVID-19 CT images can assist diagnosis and health care of patients. However, accurate and automatic segmentation of COVID-19 lung infections is faced with a few challenges, including blurred edges of infection and relatively low sensitivity. To address the issues above, a novel dilated dual attention U-Net based on the dual attention strategy and hybrid dilated convolutions, namely D2A U-Net, is proposed for COVID-19 lesion segmentation in CT slices. In our D2A U-Net, the dual attention strategy composed of two attention modules is utilized to refine feature maps and reduce the semantic gap between different levels of feature maps. Moreover, the hybrid dilated convolutions are introduced to the model decoder to achieve larger receptive fields, which refines the decoding process. The proposed method is evaluated on an open-source dataset and achieves a Dice score of 0.7298 and recall score of 0.7071, which outperforms the popular cutting-edge methods in the semantic segmentation. The proposed network is expected to be a potential AI-based approach used for the diagnosis and prognosis of COVID-19 patients.

Serum Cystatin C and Coronavirus Disease 2019: A Potential Inflammatory Biomarker in Predicting Critical Illness and Mortality for Adult Patients.

This study aimed at determining the relationship between baseline cystatin C levels and coronavirus disease 2019 (COVID-19) and investigating the potential prognostic value of serum cystatin C in adult patients with COVID-19. 481 patients with COVID-19 were consecutively included in this study from January 2, 2020, and followed up to April 15, 2020. All clinical and laboratory data of COVID-19 patients with definite outcomes were reviewed. For every measure, COVID-19 patients were grouped into quartiles according to the baseline levels of serum cystatin C. The highest cystatin C level was significantly related to more severe inflammatory conditions, worse organ dysfunction, and worse outcomes among patients with COVID-19 (P values < 0.05). In the adjusted logistic regression analyses, the highest cystatin C level and ln-transformed cystatin C levels were independently associated with the risks of developing critically ill COVID-19 and all-cause death either in overall patients or in patients without chronic kidney disease (P values < 0.05). As a potential inflammatory marker, increasing baseline levels of serum cystatin C might independently predict adverse outcomes for COVID-19 patients. Serum cystatin C could be routinely monitored during hospitalization, which showed clinical importance in prognosticating for adult patients with COVID-19.