Key result
Volumetric deep learning PA/AAo ratio outperforms diameter measurements for detecting pulmonary hypertension with AUC ~0.85.
Why the study?
The study was conducted to assess the diagnostic accuracy of a deep learning model for quantifying pulmonary artery and ascending aorta diameters and volumes on non-contrast CT scans to detect pulmonary hypertension.
Does a deep learning-derived volumetric PA/AAo ratio on non-contrast CT improve diagnostic accuracy for detecting pulmonary hypertension compared to diameter-based assessments?
Cross-Sectional (n=522)
Yes
Does a deep learning-derived volumetric PA/AAo ratio on non-contrast CT improve diagnostic accuracy for detecting pulmonary hypertension compared to diameter-based assessments?
An automated, deep learning-based volumetric PA/AAo ratio on non-contrast CT offers high diagnostic accuracy for detecting pulmonary hypertension and could facilitate opportunistic screening.
Answers are grounded in this paper and cite their sources.
Volumetric DL PA/AAo ratio may aid opportunistic PH screening on CT; extends diameter-based methods but requires prospective validation before adoption.
Aims To assess the diagnostic accuracy of a deep learning (DL) model for quantifying the pulmonary artery (PA) and ascending aorta (AAo) diameters and volumes on non-contrast computed tomography (CT) scans for detecting pulmonary hypertension (PH). Methods and results The PA and AAo were segmented using a validated DL model on non-contrast CT scans. PA/AAo ratios were quantified using diameter and volume measurements. Testing was performed using two independent patient cohorts. A first cohort (n = 97) was used to compare DL-derived and manual diameter-based PA/AAo ratios and to evaluate their diagnostic accuracy against right heart catheterization (RHC). A second cohort (n = 425; 385 internal and 40 external patients) was then used to compare the diagnostic performance of the DL-derived diameter- and volume-based PA/AAo ratios using RHC as the reference standard. In the first cohort, 97 patients were included (mean age 63 ± 13 years, 50% female, and 62 patients with PH). Agreement with the diameter-based approach was good [Observer 1: intraclass correlation coefficient (ICC) = 0.79 (0.70–0.85); Observer 2: ICC = 0.79 (0.70–0.86)]. Agreement with volume-based PA/AAo ratio was moderate [Observer 1: ICC = 0.56 (0.41–0.68); Observer 2: ICC = 0.55 (0.39–0.67)]. The DL diameter-based (area under the curve (AUC) = 0.83) and volume-based (AUC = 0.84) PA/AAo ratio outperformed the manual measurements by Observer 1 (AUC=0.72) and Observer 2 (AUC = 0.74). The second cohort comprised 425 patients (385 internal and 40 external), with a mean age of 65 ± 12 years, 60% female, and 353 patients with PH. The volume-based approach achieved superior diagnostic accuracy compared with the diameter-based approach (AUC 0.85 vs. 0.73), with higher sensitivity (66% vs. 41%) and specificity (89% vs. 82%). Conclusion The PA/AAo volume ratio on non-contrast CT demonstrates high diagnostic accuracy for detecting PH and could assist with opportunistic detection of PH in patients undergoing routine chest imaging.
No takes yet. Share an insight, caveat, or question.
Alnasser et al. (2026) conducted a cross-sectional in Pulmonary hypertension (n=522). Deep learning-derived volume-based PA/AAo ratio vs. Deep learning-derived diameter-based PA/AAo ratio was evaluated on Diagnostic accuracy (AUC) for detecting pulmonary hypertension (mPAP >20 mmHg) (AUC 0.85, 95% CI 0.81-0.90, p=<0.001). The volumetric-based deep learning PA/AAo ratio achieved superior diagnostic accuracy compared to the diameter-based approach for detecting pulmonary hypertension.
Synapse has enriched 10 related papers. Consider them for comparative context: