Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation.

ABSTRACT:

Background

Acute respiratory distress syndrome (ARDS) is a common, but under-recognised, critical illness syndrome associated with high mortality. An important factor in its under-recognition is the variability in chest radiograph interpretation for ARDS. We sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs.

Methods

CNNs were pretrained on 595 506 radiographs from two centres to identify common chest findings (eg, opacity and effusion), and then trained on 8072 radiographs annotated for ARDS by multiple physicians using various transfer learning approaches. The best performing CNN was tested on chest radiographs in an internal and external cohort, including a subset reviewed by six physicians, including a chest radiologist

SUBMITTER: Sjoding MW 

PROVIDER: S-EPMC8182690 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature