Assessment of Pulmonary Thromboembolism on Chest Radiographs Using Quantitative AI-Based Cardiovascular-Border Analysis.
Abstract
Purpose
To address the utility of an AI-based cardiovascular border analysis of chest radiographs (CXRs) in patients with pulmonary thromboembolism (PTE).Materials and methods
This retrospective single-center study included patients with PTE diagnosed using cardiothoracic ratio (CTR) pulmonary angiography between January 2023 and June 2024, along with age-matched and sex-matched controls. The AI model quantified distances from the midline to the cardiovascular borders, including the superior vena cava/ascending aorta (SVC/AO), right atrium (RA), aortic arch, pulmonary trunk (PT), left atrial appendage (LAA), and left ventricle (LV), as well as the CTR. Measurements were standardized as age-adjusted and sex-adjusted Z-scores. Diagnostic performance was assessed using receiver operating characteristic (ROC) analysis.Results
In total, 390 participants (195 with PTE and 195 controls; median age, 68 years) were included in the study. Patients with PTE showed greater values for the PT, SVC/AO, LAA, LV, and CTRs than the controls (p < 0.05). Among 165 patients with follow-up CXRs, post-treatment reductions in values for the PT, SVC/AO, RA, LAA, LV, and CTRs were observed (p < 0.05). ROC analysis showed modest discriminative performance, with the PT Z-score demonstrating the highest area under the curve (AUC, 0.658), improving further in the central PTE subgroup (AUC, 0.700).Conclusion
AI-based cardiovascular-border analysis of CXRs demonstrated modest diagnostic performance but may support treatment monitoring in patient with PTE.
Related
- Deep learning based detection of active pulmonary tuberculosis from chest radiographs in a retrospective prospective multicenter study
- Kartagener syndrome with pulmonary mycetoma and recurrent thromboembolism : A case report
- Single-leg versus double-leg weight-bearing radiographs for coronal alignment assessment in patients with lower extremity trauma
- Pulmonary thromboembolism with prolonged pulmonary infarction during intensive decongestion for severe heart failure : A case report
- Differentiating acute from chronic pulmonary thromboembolism: a preliminary study using dual-layer CT
BibTeX
@article{ok2026assessment,
title = {{Assessment of Pulmonary Thromboembolism on Chest Radiographs Using Quantitative AI-Based Cardiovascular-Border Analysis.}},
author = {Ji Yun Ok and Jong Eun Lee and Ki Seok Choo and Dong Hyun Yang},
journal = {Journal of the Korean Society of Radiology},
year = {2026},
month = aug,
doi = {10.3348/jksr.2025.0131},
url = {https://europepmc.org/article/MED/42903069},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Assessment of Pulmonary Thromboembolism on Chest Radiographs Using Quantitative AI-Based Cardiovascular-Border Analysis.
AU - Ji Yun Ok
AU - Jong Eun Lee
AU - Ki Seok Choo
AU - Dong Hyun Yang
PY - 2026
DA - 2026/08/19
JO - Journal of the Korean Society of Radiology
DO - 10.3348/jksr.2025.0131
UR - https://europepmc.org/article/MED/42903069
AB - Purpose To address the utility of an AI-based cardiovascular border analysis of chest radiographs (CXRs) in patients with pulmonary thromboembolism (PTE).Materials and methods This retrospective single-center study included patients with PTE diagnosed using cardiothoracic ratio (CTR) pulmonary angiography between January 2023 and June 2024, along with age-matched and sex-matched controls. The AI model quantified distances from the midline to the cardiovascular borders, including the superior vena cava/ascending aorta (SVC/AO), right atrium (RA), aortic arch, pulmonary trunk (PT), left atrial appendage (LAA), and left ventricle (LV), as well as the CTR. Measurements were standardized as age-adjusted and sex-adjusted Z-scores. Diagnostic performance was assessed using receiver operating characteristic (ROC) analysis.Results In total, 390 participants (195 with PTE and 195 controls; median age, 68 years) were included in the study. Patients with PTE showed greater values for the PT, SVC/AO, LAA, LV, and CTRs than the controls (p < 0.05). Among 165 patients with follow-up CXRs, post-treatment reductions in values for the PT, SVC/AO, RA, LAA, LV, and CTRs were observed (p < 0.05). ROC analysis showed modest discriminative performance, with the PT Z-score demonstrating the highest area under the curve (AUC, 0.658), improving further in the central PTE subgroup (AUC, 0.700).Conclusion AI-based cardiovascular-border analysis of CXRs demonstrated modest diagnostic performance but may support treatment monitoring in patient with PTE.
SN - 2951-0805
ER -