Cross-Site Adaptation for COVID-19 Diagnosis Using Graph-Based Neural Networks

The SARS-CoV-2 outbreak has precipitated an unparalleled global health crisis, affecting numerous nations worldwide. As the incidence of new infections persists in rising, there is an urgent necessity for automated systems capable of detecting SARS-CoV-2 through computed tomography (CT) imaging. Such systems possess considerable potential to support clinical diagnostics and alleviate the substantial burden linked to manual image analysis. Enhancing the datasets utilized for developing machine learning models necessitates the inclusion of cases from diverse medical systems. This approach is essential for constructing models that are both robust and generalizable. In this investigation, we present an innovative methodology named Domain Adaptive Graph Alignment with Neural Network (DAGANN) for the accurate identification of SARS-CoV-2. DAGANN is engineered to effectively learn from heterogeneous datasets characterized by distributional variations, employing the resilient architecture of COVID-Net to boost both prediction accuracy and learning efficiency. The DAGANN model offers several significant contributions. Primarily, to our knowledge, this study is the first to incorporate graph-based information within a deep learning framework for SARS-CoV-2 detection. Additionally, the model integrates three distinct alignment mechanisms designed to learn domain-invariant and semantic representations, thereby reducing domain discrepancies and facilitating domain adaptation. We validate our approach using two publicly available, large-scale SARS-CoV-2 diagnostic datasets composed of CT images. Comprehensive experimental results demonstrate that our method consistently achieves superior performance across both datasets. Furthermore, our approach surpasses current leading multi-site learning techniques, underscoring its efficacy and superiority.