Pulmonary Edema Severity Estimation in Chest Radiographs Using Deep Learning

Xin Wang, Evan Schwab, Jonathan Rubin, Prescott Klassen, Ruizhi Liao, Seth Berkowitz, Polina Golland, Steven Horng, Sandeep Dalal

Keywords: congestive heart failure, pulmonary edema severity, chest x-ray, deep learning

Abstract: The detection of pulmonary edema in chest radiographs is critical for the physician to make timely treatment decisions for patients with congestive heart failure. However, assessing the severity of pulmonary edema is a challenging task that leads to low inter-rater agreement among experienced radiologists. We compare a number of deep learning approaches to estimate the severity of pulmonary edema using the large-scale MIMIC-CXR database of chest x-ray images and radiology reports.

Code Of Conduct: I have read and accept the code of conduct.

Remove If Rejected: Remove submission from public view if paper is rejected.