ABSTRACT
Semi-supervised learning (SSL) algorithms have attracted much attentions in medical image segmentation by leveraging unlabeled data, which challenge in acquiring massive pixel-wise annotated samples. However, most of the existing SSLs neglected the geometric shape constraint in object, leading to unsatisfactory boundary and non-smooth of object. In this paper, we propose a novel boundary-aware semi-supervised medical image segmentation network, named Graph-BAS(3)Net, which incorporates the boundary information and learns duality constraints between semantics and geometrics in the graph domain. Specifically, the proposed method consists of two components: a multi-task learning framework BAS(3)Net and a graph-based cross-task module BGCM. The BAS(3)Net improves the existing GAN-based SSL by adding a boundary detection task, which encodes richer features of object shape and surface. Moreover, the BGCM further explores the co-occurrence relations between the semantics segmentation and boundary detection task, so that the network learns stronger semantic and geometric correspondences from both labeled and unlabeled data. Experimental results on the LiTS dataset and COVID-19 dataset confirm that our proposed Graph-BAS(3) Net outperforms the state-of-the-art methods in semi-supervised segmentation task.
ABSTRACT
Objective: To analyze the course of disease and epidemiological parameters of COVID-19 and provide evidence for making prevention and control strategies. Methods: To display the distribution of course of disease of the infectors who had close contacts with COVID-19 cases from January 1 to March 15, 2020 in Guangdong Provincial, the models of Lognormal, Weibull and gamma distribution were applied. A descriptive analysis was conducted on the basic characteristics and epidemiological parameters of course of disease. Results: In total, 515 of 11 580 close contacts were infected, with an attack rate about 4.4%, including 449 confirmed cases and 66 asymptomatic cases. Lognormal distribution was fitting best for latent period, incubation period, pre-symptomatic infection period of confirmed cases and infection period of asymptomatic cases; Gamma distribution was fitting best for infectious period and clinical symptom period of confirmed cases; Weibull distribution was fitting best for latent period of asymptomatic cases. The latent period, incubation period, pre-symptomatic infection period, infectious period and clinical symptoms period of confirmed cases were 4.50 (95%CI:3.86-5.13) days, 5.12 (95%CI:4.63-5.62) days, 0.87 (95%CI:0.67-1.07) days, 11.89 (95%CI:9.81-13.98) days and 22.00 (95%CI:21.24-22.77) days, respectively. The latent period and infectious period of asymptomatic cases were 8.88 (95%CI:6.89-10.86) days and 6.18 (95%CI:1.89-10.47) days, respectively. Conclusion: The estimated course of COVID-19 and related epidemiological parameters are similar to the existing data.
Subject(s)
COVID-19 , Contact Tracing , Cohort Studies , Humans , Incidence , Prospective StudiesABSTRACT
Coronavirus Disease 2019 (COVID-19) has rapidly spread in 2020, emerging a mass of studies for lung infection segmentation from CT images. Though many methods have been proposed for this issue, it is a challenging task because of infections of various size appearing in different lobe zones. To tackle these issues, we propose a Graph-based Pyramid Global Context Reasoning (Graph-PGCR) module, which is capable of modeling long-range dependencies among disjoint infections as well as adapt size variation. We first incorporate graph convolution to exploit long-term contextual information from multiple lobe zones. Different from previous average pooling or maximum object probability, we propose a saliency-aware projection mechanism to pick up infection-related pixels as a set of graph nodes. After graph reasoning, the relation-aware features are reversed back to the original coordinate space for the down-stream tasks. We further construct multiple graphs with different sampling rates to handle the size variation problem. To this end, distinct multi-scale long-range contextual patterns can be captured. Our Graph-PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance. Experiments demonstrated that the proposed method consistently boost the performance of state-of-the-art backbone architectures on both of public and our private COVID-19 datasets.
ABSTRACT
The application of artificial intelligence (AI) to health has increased, including to COVID-19. This study aimed to provide a clear overview of COVID-19-related AI publication trends using longitudinal bibliometric analysis. A systematic literature search was conducted on the Web of Science for English language peer-reviewed articles related to AI application to COVID-19. A search strategy was developed to collect relevant articles and extracted bibliographic information (e.g., country, research area, sources, and author). VOSviewer (Leiden University) and Bibliometrix (R package) were used to visualize the co-occurrence networks of authors, sources, countries, institutions, global collaborations, citations, co-citations, and keywords. We included 729 research articles on the application of AI to COVID-19 published between 2020 and 2021. PLOS One (33/729, 4.52%), Chaos Solution Fractals (29/729, 3.97%), and Journal of Medical Internet Research (29/729, 3.97%) were the most common journals publishing these articles. The Republic of China (190/729, 26.06%), the USA (173/729, 23.73%), and India (92/729, 12.62%) were the most prolific countries of origin. The Huazhong University of Science and Technology, Wuhan University, and the Chinese Academy of Sciences were the most productive institutions. This is the first study to show a comprehensive picture of the global efforts to address COVID-19 using AI. The findings of this study also provide insights and research directions for academic researchers, policymakers, and healthcare practitioners who wish to collaborate in these domains in the future.