COVID-19 in CXR: from Detection and Severity Scoring to Patient Disease Monitoring

TL;DR

This paper presents a deep learning approach for detecting and quantifying COVID-19 pneumonia severity in chest X-rays, enabling longitudinal patient monitoring through disease extent profiling.

Contribution

The study introduces a novel deep learning model for simultaneous detection and segmentation of pneumonia in CXR images, and a validation strategy using synthetic X-rays from CT scans.

Findings

Effective pneumonia segmentation in CXR images.

Correlation between disease severity profiles from synthetic X-rays and CT scans.

Potential for longitudinal disease monitoring in COVID-19 patients.

Abstract

In this work, we estimate the severity of pneumonia in COVID-19 patients and conduct a longitudinal study of disease progression. To achieve this goal, we developed a deep learning model for simultaneous detection and segmentation of pneumonia in chest Xray (CXR) images and generalized to COVID-19 pneumonia. The segmentations were utilized to calculate a "Pneumonia Ratio" which indicates the disease severity. The measurement of disease severity enables to build a disease extent profile over time for hospitalized patients. To validate the model relevance to the patient monitoring task, we developed a validation strategy which involves a synthesis of Digital Reconstructed Radiographs (DRRs - synthetic Xray) from serial CT scans; we then compared the disease progression profiles that were generated from the DRRs to those that were generated from CT volumes.