Longitudinal Self-Supervision for COVID-19 Pathology Quantification
This work addresses the problem of managing COVID-19 patient hospitalization for radiologists, but it is incremental as it builds on existing deep learning approaches with a novel training scheme.
The study tackled the challenge of limited longitudinal training data for deep learning-based COVID-19 pathology quantification on CT scans by proposing a new self-supervised learning method, which improved performance on two quantification tasks.
Quantifying COVID-19 infection over time is an important task to manage the hospitalization of patients during a global pandemic. Recently, deep learning-based approaches have been proposed to help radiologists automatically quantify COVID-19 pathologies on longitudinal CT scans. However, the learning process of deep learning methods demands extensive training data to learn the complex characteristics of infected regions over longitudinal scans. It is challenging to collect a large-scale dataset, especially for longitudinal training. In this study, we want to address this problem by proposing a new self-supervised learning method to effectively train longitudinal networks for the quantification of COVID-19 infections. For this purpose, longitudinal self-supervision schemes are explored on clinical longitudinal COVID-19 CT scans. Experimental results show that the proposed method is effective, helping the model better exploit the semantics of longitudinal data and improve two COVID-19 quantification tasks.