A multi-institutional research team is using deep learning for x-ray and CT images to study the long-term progression of COVID-19, thanks to a $3.7 million grant from the National Institutes of Health (NIH).
The researchers, based at Texas A&M University and the University of Iowa, are developing self-supervised deep learning technologies capable of recognizing subtypes of post-COVID lung progression phenotypes. The idea is that understanding these phenotypes helps determine appropriate care measures for long-COVID patients.
The deep-learning model uses x-rays and CT scans to differentiate post-COVID-19 subjects from healthy subjects while simultaneously identifying post-COVID-19 subtypes. The researchers said that using unlabeled images from patients increases the data available to train the model to diagnose and understand disease progression more accurately.
The team is planning a longitudinal human subject study that tracks post-COVID-19 individuals 48 to 60 months after their initial visits to continue building data and developing the model.
