Classification of cardioembolic stroke based on a deep neural network using chest radiographs

Han Gil Jeong, Beom Joon Kim, Tackeun Kim, Jihoon Kang, Jun Yup Kim, Joonghee Kim, Joon Tae Kim, Jong Moo Park, Jae Guk Kim, Jeong Ho Hong, Kyung Bok Lee, Tai Hwan Park, Dae Hyun Kim, Chang Wan Oh, Moon Ku Han, Hee Joon Bae

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Background: Although chest radiographs have not been utilised well for classifying stroke subtypes, they could provide a plethora of information on cardioembolic stroke. This study aimed to develop a deep convolutional neural network that could diagnose cardioembolic stroke based on chest radiographs. Methods: Overall, 4,064 chest radiographs of consecutive patients with acute ischaemic stroke were collected from a prospectively maintained stroke registry. Chest radiographs were randomly partitioned into training/validation (n = 3,255) and internal test (n = 809) datasets in an 8:2 ratio. A densely connected convolutional network (ASTRO-X) was trained to diagnose cardioembolic stroke based on chest radiographs. The performance of ASTRO-X was evaluated using the area under the receiver operating characteristic curve. Gradient-weighted class activation mapping was used to evaluate the region of focus of ASTRO-X. External testing was performed with 750 chest radiographs of patients with acute ischaemic stroke from 7 hospitals. Findings: The areas under the receiver operating characteristic curve of ASTRO-X were 0.86 (95% confidence interval [CI], 0.83–0.89) and 0.82 (95% CI, 0.79–0.85) during the internal and multicentre external testing, respectively. The gradient-weighted class activation map demonstrated that ASTRO-X was focused on the area where the left atrium was located. Compared with cases predicted as non-cardioembolism by ASTRO-X, cases predicted as cardioembolism by ASTRO-X had higher left atrial volume index and lower left ventricular ejection fraction in echocardiography. Interpretation: ASTRO-X, a deep neural network developed to diagnose cardioembolic stroke based on chest radiographs, demonstrated good classification performance and biological plausibility.

Original languageEnglish
Article number103466
JournalEBioMedicine
Volume69
DOIs
StatePublished - Jul 2021

Keywords

  • Cardioembolism
  • Chest radiograph
  • Classification
  • Deep learning
  • Stroke

Fingerprint

Dive into the research topics of 'Classification of cardioembolic stroke based on a deep neural network using chest radiographs'. Together they form a unique fingerprint.

Cite this