Secure and Efficient Smart Healthcare System Based on Federated Learning

The rapid development of smart healthcare system in the Internet of Things (IoT) has made the early detection of many chronic diseases more convenient, quick, and economical. However, when healthcare organizations collect users' health data through deployed IoT devices, there are issues of compromising users' privacy. In view of this situation, this paper introduces federated learning technology to solve the problem of data security. In this paper, we consider the two main problems of federated learning applications in IoT smart healthcare system: (1) how to reduce the time overhead of system running and (2) how to authenticate that the user device uploading data is deployed by the system itself. To solve the above problems, we propose the first federated learning scheme based on full dynamic secret sharing. First, we use a two-mask protocol to keep the user's local model parameters confidential during federated learning. Then, based on homogeneous linear recursive equation, homomorphic hash function, and elliptic curve cryptosystem, the full dynamic secret sharing and user identity authentication are realized. In addition, our scheme allows users to join or quit during training. Finally, we have carried out simulation test on this scheme. The experimental results show that the efficiency of our scheme is improved by about 60% on average in the case of no user dropping and by about 30% in the case of some users dropping.

Rational drug repositioning for coronavirus-associated diseases using directional mapping and side-effect inference.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the pathogen of coronavirus disease 2019 (COVID-19), has infected hundreds of millions of people and caused millions of deaths. Looking for valid druggable targets with minimal side effects for the treatment of COVID-19 remains critical. After discovering host genes from multiscale omics data, we developed an end-to-end network method to investigate drug-host gene(s)-coronavirus (CoV) paths and the mechanism of action between the drug and the host factor in a directional network. We also inspected the potential side effect of the candidate drug on several common comorbidities. We established a catalog of host genes associated with three CoVs. Rule-based prioritization yielded 29 Food and Drug Administration (FDA)-approved drugs via accounting for the effects of drugs on CoVs, comorbidities, and drug-target confidence information. Seven drugs are currently undergoing clinical trials as COVID-19 treatment. This catalog of druggable host genes associated with CoVs and the prioritized repurposed drugs will provide a new sight in therapeutics discovery for severe COVID-19 patients.

COVID-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework.

With the global outbreak of COVID-19 in early 2020, rapid diagnosis of COVID-19 has become the urgent need to control the spread of the epidemic. In clinical settings, lung infection segmentation from computed tomography (CT) images can provide vital information for the quantification and diagnosis of COVID-19. However, accurate infection segmentation is a challenging task due to (i) the low boundary contrast between infections and the surroundings, (ii) large variations of infection regions, and, most importantly, (iii) the shortage of large-scale annotated data. To address these issues, we propose a novel two-stage cross-domain transfer learning framework for the accurate segmentation of COVID-19 lung infections from CT images. Our framework consists of two major technical innovations, including an effective infection segmentation deep learning model, called nCoVSegNet, and a novel two-stage transfer learning strategy. Specifically, our nCoVSegNet conducts effective infection segmentation by taking advantage of attention-aware feature fusion and large receptive fields, aiming to resolve the issues related to low boundary contrast and large infection variations. To alleviate the shortage of the data, the nCoVSegNet is pre-trained using a two-stage cross-domain transfer learning strategy, which makes full use of the knowledge from natural images (i.e., ImageNet) and medical images (i.e., LIDC-IDRI) to boost the final training on CT images with COVID-19 infections. Extensive experiments demonstrate that our framework achieves superior segmentation accuracy and outperforms the cutting-edge models, both quantitatively and qualitatively.

Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images.

The capability of generalization to unseen domains is crucial for deep learning models when considering real-world scenarios. However, current available medical image datasets, such as those for COVID-19 CT images, have large variations of infections and domain shift problems. To address this issue, we propose a prior knowledge driven domain adaptation and a dual-domain enhanced self-correction learning scheme. Based on the novel learning scheme, a domain adaptation based self-correction model (DASC-Net) is proposed for COVID-19 infection segmentation on CT images. DASC-Net consists of a novel attention and feature domain enhanced domain adaptation model (AFD-DA) to solve the domain shifts and a self-correction learning process to refine segmentation results. The innovations in AFD-DA include an image-level activation feature extractor with attention to lung abnormalities and a multi-level discrimination module for hierarchical feature domain alignment. The proposed self-correction learning process adaptively aggregates the learned model and corresponding pseudo labels for the propagation of aligned source and target domain information to alleviate the overfitting to noises caused by pseudo labels. Extensive experiments over three publicly available COVID-19 CT datasets demonstrate that DASC-Net consistently outperforms state-of-the-art segmentation, domain shift, and coronavirus infection segmentation methods. Ablation analysis further shows the effectiveness of the major components in our model. The DASC-Net enriches the theory of domain adaptation and self-correction learning in medical imaging and can be generalized to multi-site COVID-19 infection segmentation on CT images for clinical deployment.

[Epidemiology, Treatment, and Epidemic Prevention and Control of the Coronavirus Disease 2019: a Review].

This review summarizes the ongoing researches regarding etiology, epidemiology, transmission dynamics, treatment, and prevention and control strategies of the coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), with comparison to severe acute respiratory syndrome coronavirus (SARS-CoV), Middle East respiratory syndrome coronavirus (MERS-CoV) and pandemic H1N1 virus. SARS-CoV-2 may be originated from bats, and the patients and asymptomatic carriers are the source of epidemic infection. The virus can be transmitted human-to-human through droplets and close contact, and people at all ages are susceptible to this virus. The main clinical symptoms of the patients are fever and cough, accompanied with leukocytopenia and lymphocytopenia. Effective drugs have been not yet available thus far. In terms of the prevention and control strategies, vaccine development as the primary prevention should be accelerated. Regarding the secondary prevention, ongoing efforts of the infected patients and close contacts quarantine, mask wearing promotion, regular disinfection in public places should be continued. Meanwhile, rapid detection kit for serological monitoring of the virus in general population is expected so as to achieve early detection, early diagnosis, early isolation and early treatment. In addition, public health education on this disease and prevention should be enhanced so as to mitigate panic and mobilize the public to jointly combat the epidemic.