SARS-CoV-2 Detection: Radiology based Multi-modal Multi-task Framework

The global community is still grappling with the SARS-CoV-2 pandemic, declared by the World Health Organization in March 2020. Radiology is an important screening method for the early detection of SARS-CoV-2. Doctors typically recommend that patients undergo one of the radiology procedures during the early stages of diagnosis. Recent research has focused on developing deep learning-based architectures that use either X-Rays or CT-Scans, but not both. This paper presents a multi-modal, multi-task learning framework that uses either the X-Rays or CT-Scans to identify SARS-CoV-2 patients. The framework employs a shared feature embedding that utilizes common information from both X-Rays and CT-Scans, as well as task-specific feature embeddings that are independent of the type of chest screening. The shared and task-specific embeddings are combined to obtain the final classification results, which have been shown to have an accuracy of 98.23% and 98.83% in detecting SARS-CoV-2 using X-Rays and CT-Scans, respectively.