Deep Learning to Quantify Pulmonary Edema in Chest Radiographs
Name
2008.05975.pdf
Description
Accepted version
Size
1.85 MB
Format
Adobe PDF
Checksum (MD5)
2cc76f9a32f80ea6e3284305b4f078f5
Author(s)
Horng, Steven
Liao, Ruizhi
Wang, Xin
Dalal, Sandeep
Golland, Polina
Berkowitz, Seth J
Date Issued
2021
Journal
Radiology: Artificial Intelligence
Publisher
Radiological Society of North America (RSNA)
Citation
Horng, Steven, Liao, Ruizhi, Wang, Xin, Dalal, Sandeep, Golland, Polina et al. 2021. "Deep Learning to Quantify Pulmonary Edema in Chest Radiographs." Radiology: Artificial Intelligence, 3 (2).
Version
Author's final manuscript
Abstract
PURPOSE: To develop a machine learning model to classify the severity grades of pulmonary edema on chest radiographs. MATERIALS AND METHODS: In this retrospective study, 369 071 chest radiographs and associated radiology reports from 64 581 patients (mean age, 51.71 years; 54.51% women) from the MIMIC-CXR chest radiograph dataset were included. This dataset was split into patients with and without congestive heart failure (CHF). Pulmonary edema severity labels from the associated radiology reports were extracted from patients with CHF as four different ordinal levels: 0, no edema; 1, vascular congestion; 2, interstitial edema; and 3, alveolar edema. Deep learning models were developed using two approaches: a semisupervised model using a variational autoencoder and a pretrained supervised learning model using a dense neural network. Receiver operating characteristic curve analysis was performed on both models. RESULTS: The area under the receiver operating characteristic curve (AUC) for differentiating alveolar edema from no edema was 0.99 for the semisupervised model and 0.87 for the pretrained models. Performance of the algorithm was inversely related to the difficulty in categorizing milder states of pulmonary edema (shown as AUCs for semisupervised model and pretrained model, respectively): 2 versus 0, 0.88 and 0.81; 1 versus 0, 0.79 and 0.66; 3 versus 1, 0.93 and 0.82; 2 versus 1, 0.69 and 0.73; and 3 versus 2, 0.88 and 0.63. CONCLUSION: Deep learning models were trained on a large chest radiograph dataset and could grade the severity of pulmonary edema on chest radiographs with high performance.Supplemental material is available for this article.See also the commentary by Auffermann in this issue.© RSNA, 2021.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1148/RYAI.2021190228
