MIC-Net: A deep network for cross-site segmentation of COVID-19 infection in the fog-assisted IoMT.

The automatic segmentation of COVID-19 pneumonia from a computerized tomography (CT) scan has become a major interest for scholars in developing a powerful diagnostic framework in the Internet of Medical Things (IoMT). Federated deep learning (FDL) is considered a promising approach for efficient and cooperative training from multi-institutional image data. However, the nonindependent and identically distributed (Non-IID) data from health care remain a remarkable challenge, limiting the applicability of FDL in the real world. The variability in features incurred by different scanning protocols, scanners, or acquisition parameters produces the learning drift phenomena during the training, which impairs both the training speed and segmentation performance of the model. This paper proposes a novel FDL approach for reliable and efficient multi-institutional COVID-19 segmentation, called MIC-Net. MIC-Net consists of three main building modules: the down-sampler, context enrichment (CE) module, and up-sampler. The down-sampler was designed to effectively learn both local and global representations from input CT scans by combining the advantages of lightweight convolutional and attention modules. The contextual enrichment (CE) module is introduced to enable the network to capture the contextual representation that can be later exploited to enrich the semantic knowledge of the up-sampler through skip connections. To further tackle the inter-site heterogeneity within the model, the approach uses an adaptive and switchable normalization (ASN) to adaptively choose the best normalization strategy according to the underlying data. A novel federated periodic selection protocol (FED-PCS) is proposed to fairly select the training participants according to their resource state, data quality, and loss of a local model. The results of an experimental evaluation of MIC-Net on three publicly available data sets show its robust performance, with an average dice score of 88.90% and an average surface dice of 87.53%.

Semantic Integration of Heterogeneous Data Sources Using Ontology-Based Domain Knowledge Modeling for Early Detection of COVID-19.

The enormous outbreak of biomedical knowledge, the aim of reducing computation and processing costs and the widespread availability of internet connection have created a profuse amount of electronic data. Such data are stored across the globe in various data sources that are semantically, structurally and syntactically different. This decentralized nature of biomedical data has made it difficult to obtain a unified view of the data. Data integration plays a crucial role in enhancing access to heterogeneous data making the retrieval easier and faster. A variety of ontology, machine learning, deep learning and fuzzy logic-based solutions are being developed for heterogeneous data integration. The proposed model concentrates on the automatic ontology-based data integration method that can be effectively deployed and used in the healthcare domain. The proposed model is divided into three phases. The first phase includes the automatic mapping of data and generation of local ontology across heterogeneous data sources, the second phase combines the local ontology models developed in the first phase to create a root global schema mapping and the third phase queries diverse databases to retrieve semantically analogous records. The model is created based on the medical records, chest X-ray details and COVID-19 symptom questionnaire data of various patients distributed across three data sources (SQL, mongodb and excel). Based on the data, the patients who have moderate/higher risk of developing serious illness from COVID-19 are retrieved.

Learning from heterogeneous data via contrastive learning: An application in multi-source covid-19 radiography

The ongoing COVID-19 pandemic has overloaded current healthcare systems, including radiology systems and departments. Machine learning-based medical imaging diagnostic approaches play an important role in tracking the spread of this virus, identifying high-risk patients, and controlling infections in real-time. Researchers aggregate radiographic samples from different data sources to establish a multi-source learning scheme to mitigate the insufficiency of COVID-19 samples from individual hospitals, especially in the early stage of the disease. However, data heterogeneity across different clinical centers with various imaging conditions is considered a significant limitation in model performance. This paper proposes a contrastive learning scheme for the automatic diagnosis of COVID-19 to effectively mitigate data heterogeneity in multi-source data and learn a robust and generalizable model. Inspired by advances in domain adaptation, we employ contrastive training objectives to promote intra-class cohesion across different data sources and inter-class separation of infected and non-infected cases. Extensive experiments on two public COVID-19 CT datasets demonstrate the effectiveness of the proposed method for tackling data heterogeneity problems with boosted diagnosis performance. Moreover, benefiting from the contrastive learning framework, our method can be generalized to solve data heterogeneity problems under a broader multi-source learning setting. © 2021 IEEE