Pulmonary edema severity grades based on the MIMIC-CXR dataset, also available on PhysioNet.
Clinical management decisions for patients with acutely decompensated heart failure and many other diseases are often based on grades of pulmonary edema severity, rather than its mere absence or presence. Chest radiographs are commonly performed to assess pulmonary edema. The MIMIC-CXR dataset that consists of 377,110 chest radiographs with free-text radiology reports offers a tremendous opportunity to study this subject.
This dataset is curated based on MIMIC-CXR, containing 3 metadata files that consist of pulmonary edema severity grades extracted from the MIMIC-CXR dataset through different means: 1) by regular expression (regex) from radiology reports, 2) by expert labeling from radiology reports, and 3) by consensus labeling from chest radiographs.
This dataset aims to support the algorithmic development of pulmonary edema assessment from chest x-ray images and benchmark its performance. The metadata files have subject IDs, study IDs, DICOM IDs, and the numerical grades of pulmonary edema severity. The IDs listed in this dataset have the same mapping structure as in MIMIC-CXR.
Clinical management decisions for patients with acutely decompensated heart failure and many other diseases are often based on grades of pulmonary edema severity, rather than its mere absence or presence. Clinicians often monitor changes in pulmonary edema severity to assess the efficacy of therapy. Accurate monitoring of pulmonary edema is essential when competing clinical priorities complicate clinical management. The extracted pulmonary edema severity labels in this dataset were numerically coded as follows: 0, none; 1, vascular congestion; 2, interstitial edema; and 3, alveolar edema. Examples of the grades are shown below.
Large-scale and common datasets have been the catalyst for the rise of machine learning today. In 2019, investigators released MIMIC-CXR, a large-scale publicly available chest radiograph dataset with free-text radiology reports. This dataset builds upon MIMIC-CXR, aiming to catalyze and benchmark future algorithmic developments in grading pulmonary edema severity from chest radiographs.
We aimed to identify patients with congestive heart failure (CHF) within the MIMIC-CXR dataset to limit confounding labels from other disease processes. There were 17,857 images in MIMIC-CXR which were acquired during visits with an emergency department discharge diagnosis code consistent with CHF. This resulted in 16,108 radiology reports and 1,916 patients that were included that had CHF. The label curation described below is performed within this CHF cohort. The cohort information is summarized in auxiliary_metadata/mimic_cxr_metadata_available_CHF_view.csv.
The pulmonary edema severity grades are extracted from the MIMIC-CXR dataset through 3 different means, described as follows.
-
Regular expression labeling from radiology reports.
regex_report_edema_severity.csv. The edema severity grades were extracted from radiology reports using regular expression (regex). Each severity level is associated with several keyword terms that are representative of that severity group (e.g., "Kerley B lines" in "2-interstitial edema"). If multiple keyword terms are detected affirmed in a report, the most severe level will be assigned to that report. Within the 16,108 radiology reports in the CHF cohort, regex is able to label 6710 radiology reports.
-
Expert labeling from radiology reports.
expert_report_edema_severity.csv. A board-certified radiologist and two domain experts have read 485 radiology reports and give pulmonary edema severity grades based on the reports. More details can be found here.
-
Consensus labeling from chest radiographs.
consensus_image_edema_severity.csv. Three senior radiology residents and one attending radiologist have labeled 141 chest radiographs. They assessed the images independently, discussed and voted on the ones that they disagreed on until a consensus was reached, detailed below. This label set is the highest-quality among the three sets, and we recommend holding it out for testing.
The label curation efforts have been presented in the following publications:
G. Chauhan*, R. Liao*, W. Wells, J. Andreas, X. Wang, S. Berkowitz, S. Horng, P. Szolovits, P. Golland. Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2020. (* indicates equal contributions.)
S. Horng*, R. Liao*, X. Wang, S. Dalal, P. Golland, S. Berkowitz. Deep Learning to Quantify Pulmonary Edema in Chest Radiographs. Radiology: Artificial Intelligence. (* indicates equal contributions.)
R. Liao, J. Rubin, G. Lam, S. Berkowitz, S. Dalal, W. Wells, S. Horng, P. Golland. Semi-supervised Learning for Quantification of Pulmonary Edema in Chest X-Ray Images. arXiv:1902.10785.