Imaging Biomarkers for Pulmonary Hypertension: AI‐Based Vascular Analysis Through Non‐Contrast Chest Computed Tomography Scans
5 affiliations
- 1Respiratory Department University Hospital of Liège Liège Belgium
- 2Thirona Nijmegen The Netherlands
- 3Biostatistics and Research Methods Center (B‐STAT) University Hospital of Liège Liège Belgium
- 4Cardiology Department University Hospital of Liège Liège Belgium
- 5Radiology Department University Hospital of Liège Liège Belgium
Abstract
Pulmonary Hypertension (PH) is a progressive, debilitating condition characterized by elevated pressures in the pulmonary vasculature. Accurate diagnosis and appropriate classification are essential for effective management of this disorder. This study evaluated artificial intelligence (AI)‐based artery‐vein phenotyping analysis (AVX) of non‐contrast chest computed tomography (CT) scans as a means to improve diagnostic precision. A retrospective cohort study was conducted that enrolled patients who underwent non‐contrast chest CT and right heart catheterization within a 6‐month period. AVX provided segmentation and quantification of pulmonary arterial and venous trees, enabling an examination of vascular volume distribution. Radiological biomarkers were examined in the context of both PH classification and hemodynamic profiles. Significant differences in pulmonary vascular volumes were observed between three of the PH diagnostic groups (Group 1, Group 2, and Group 3, N = 163 patients). Patients stratified by hemodynamic profiles (pre‐, isolated post‐, and combined pre‐ and post‐capillary) also showed distinct patterns of arterial and venous volumes. Several CT‐derived vascular biomarkers were correlated with invasive hemodynamic measurements. Collectively, our findings suggest that the use of AI‐based artery‐vein quantification tools may provide complementary information for characterizing pulmonary vascular diseases. The results of principal component analysis highlight the value of this comprehensive approach. However, given the study's monocentric nature, the omission of PH Groups 4 and 5, and the lack of a healthy control cohort, larger‐scale validation studies will be needed to confirm these findings.
Related
- Bile acid dysregulation in pulmonary arterial hypertension: strengthening the liver-lung axis in pulmonary vascular disease
- Intratracheal Administration of Benzbromarone Attenuates Pulmonary Vascular Remodeling and Improves Survival in Rats with Monocrotaline-Induced Pulmonary Hypertension
- Quantitative comparison of virtual non-contrast and true non-contrast computed tomography pulmonary angiography images across eight thoracic tissue types: A retrospective cross-sectional study
- Inhaled nanogels ameliorate vascular remodeling in pulmonary arterial hypertension via normalization of endothelia-smooth muscle cell crosstalk
- hBM‐MSC‐Derived EVs Improved Pulmonary Vascular Remodeling and Right Ventricle Function in a Mouse Pulmonary Hypertension Model
BibTeX
@article{maloir2026imaging,
title = {{Imaging Biomarkers for Pulmonary Hypertension: AI‐Based Vascular Analysis Through Non‐Contrast Chest Computed Tomography Scans}},
author = {Quentin Maloir and Leticia Gallardo Estrella and Monique Henket and Marie Ernst and Benoit Ernst and Harm Tiddens and Cedric Davidsen and Raluca Elena Dulgheru and Colin Desir and Perrine Canivet and Paul Meunier and Fanny Gester and Patrizio Lancellotti and Renaud Louis and Jean‐Paul Charbonnier and Julien Guiot},
journal = {Pulmonary Circulation},
year = {2026},
month = nov,
doi = {10.1002/pul2.70453},
url = {https://doi.org/10.1002/pul2.70453},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Imaging Biomarkers for Pulmonary Hypertension: AI‐Based Vascular Analysis Through Non‐Contrast Chest Computed Tomography Scans
AU - Quentin Maloir
AU - Leticia Gallardo Estrella
AU - Monique Henket
AU - Marie Ernst
AU - Benoit Ernst
AU - Harm Tiddens
AU - Cedric Davidsen
AU - Raluca Elena Dulgheru
AU - Colin Desir
AU - Perrine Canivet
AU - Paul Meunier
AU - Fanny Gester
AU - Patrizio Lancellotti
AU - Renaud Louis
AU - Jean‐Paul Charbonnier
AU - Julien Guiot
PY - 2026
DA - 2026/11/12
JO - Pulmonary Circulation
DO - 10.1002/pul2.70453
UR - https://doi.org/10.1002/pul2.70453
AB - Pulmonary Hypertension (PH) is a progressive, debilitating condition characterized by elevated pressures in the pulmonary vasculature. Accurate diagnosis and appropriate classification are essential for effective management of this disorder. This study evaluated artificial intelligence (AI)‐based artery‐vein phenotyping analysis (AVX) of non‐contrast chest computed tomography (CT) scans as a means to improve diagnostic precision. A retrospective cohort study was conducted that enrolled patients who underwent non‐contrast chest CT and right heart catheterization within a 6‐month period. AVX provided segmentation and quantification of pulmonary arterial and venous trees, enabling an examination of vascular volume distribution. Radiological biomarkers were examined in the context of both PH classification and hemodynamic profiles. Significant differences in pulmonary vascular volumes were observed between three of the PH diagnostic groups (Group 1, Group 2, and Group 3, N = 163 patients). Patients stratified by hemodynamic profiles (pre‐, isolated post‐, and combined pre‐ and post‐capillary) also showed distinct patterns of arterial and venous volumes. Several CT‐derived vascular biomarkers were correlated with invasive hemodynamic measurements. Collectively, our findings suggest that the use of AI‐based artery‐vein quantification tools may provide complementary information for characterizing pulmonary vascular diseases. The results of principal component analysis highlight the value of this comprehensive approach. However, given the study's monocentric nature, the omission of PH Groups 4 and 5, and the lack of a healthy control cohort, larger‐scale validation studies will be needed to confirm these findings.
SN - 2045-8932
SN - 2045-8940
ER -