Truace
Subscribe

Radiological assessment of pulmonary vascularity in congenital heart disease: standardized clinician assessment versus deep learning-based prediction

Background Assessment of pulmonary vascularity on chest radiographs (CXRs) in congenital heart disease (CHD) is limited by subjectivity, and existing criteria lack sufficient validation. Artificial intelligence-based deep learning model (DLM) analysis may improve accuracy. We developed and validated structured criteria and a DLM to evaluate pulmonary vascularity and compared it with conventional clinical interpretation. Methods A total of 400 deidentified CXRs from CHD patients with Fick-derived pulmonary-to-sys…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-0848· cite & verify
Radiological assessment of pulmonary vascularity in congenital heart disease: standardized clinician assessment versus deep learning-based prediction
Cardio surgery 2 by Dominique Cappronnier. CC BY-SA 3.0 · https://creativecommons.org/licenses/by-sa/3.0

In brief

Background Assessment of pulmonary vascularity on chest radiographs (CXRs) in congenital heart disease (CHD) is limited by subjectivity, and existing criteria lack sufficient validation. Artificial intelligence-based deep learning model (DLM) analysis may improve accuracy.

Results Intraclass correlation between Fick- and DLM-derived Qp:Qs was 0.782 (P 1.5: 90% specificity, 98% sensitivity, area under the receiver operating characteristic curve [AUROC] 98%; predicting Qp:Qs Conclusion Deep learning-based analysis of CXRs enables accurate evaluation of pulmonary vascularity and outperforms structured assessment by clinicians.

Main points

  1. Background Assessment of pulmonary vascularity on chest radiographs (CXRs) in congenital heart disease (CHD) is limited by subjectivity, and existing criteria lack sufficient validation.
  2. Artificial intelligence-based deep learning model (DLM) analysis may improve accuracy.
  3. We developed and validated structured criteria and a DLM to evaluate pulmonary vascularity and compared it with conventional clinical interpretation.

The gain

Artificial intelligence-based deep learning model (DLM) analysis may improve accuracy. Results Intraclass correlation between Fick- and DLM-derived Qp:Qs was 0.782 (P 1.5: 90% specificity, 98% sensitivity, area under the receiver operating characteristic curve [AUROC] 98%; predicting Qp:Qs Conclusion Deep learning-based analysis of CXRs enables accurate evaluation of pulmonary vascularity and outperforms structured assessment by clinicians.

The rundown

We developed and validated structured criteria and a DLM to evaluate pulmonary vascularity and compared it with conventional clinical interpretation. Methods A total of 400 deidentified CXRs from CHD patients with Fick-derived pulmonary-to-systemic flow ratio (Qp:Qs) were evaluated by three experts and three trainees in pediatric cardiology and radiology using nine prespecified criteria.

Sources

  1. Peer-reviewedJournal of Cardiovascular Imaging2026-08-21

The debate