Fully automated Bayesian analysis for quantifying the extent and distribution of pulmonary perfusion changes on CT pulmonary angiography in CTEPH

Simple item page
dc.contributor.authorSuchánek, Vojtěchcs
dc.contributor.authorJakubíček, Romancs
dc.contributor.authorHrdlička, Jancs
dc.contributor.authorNovák, Matějcs
dc.contributor.authorMiksová, Luciecs
dc.contributor.authorJansa, Pavelcs
dc.contributor.authorBurgetová, Andreacs
dc.contributor.authorLambert, Lukášcs
dc.coverage.issueMaycs
dc.coverage.volume35cs
dc.date.accessioned2025-10-30T10:04:39Z
dc.date.available2025-10-30T10:04:39Z
dc.date.issued2025-05-28cs
dc.description.abstractObjectives This work aimed to develop an automated method for quantifying the distribution and severity of perfusion changes on CT pulmonary angiography (CTPA) in patients with chronic thromboembolic pulmonary hypertension (CTEPH) and to assess their associations with clinical parameters and expert annotations. Materials and methods Following automated segmentation of the chest, a machine-learning model assuming three distributions of attenuation in the pulmonary parenchyma (hyperemic, normal, and oligemic) was fitted to the attenuation histogram of CTPA images using Bayesian analysis. The proportion of each component, its spatial heterogeneity (entropy), and center-to-periphery distribution of the attenuation were calculated and correlated with the findings on CTPA semi-quantitatively evaluated by radiologists and with clinical function tests. Results CTPA scans from 52 patients (mean age, 65.2 +/- 13.0 years; 27 men) diagnosed with CTEPH were analyzed. An inverse correlation was observed between the proportion of normal parenchyma and brain natriuretic propeptide (proBNP, rho = -0.485, p = 0.001), mean pulmonary arterial pressure (rho = -0.417, p = 0.002) and pulmonary vascular resistance (rho = -0.556, p < 0.0001), mosaic attenuation (rho = -0.527, p < 0.0001), perfusion centralization (rho = -0.489, p = < 0.0001), and right ventricular diameter (rho = -0.451, p = 0.001). The entropy of hyperemic parenchyma showed a positive correlation with the pulmonary wedge pressure (rho = 0.402, p = 0.003). The slope of center-to-periphery attenuation distribution correlated with centralization (rho = -0.477, p < 0.0001), and with proBNP (rho = -0.463, p = 0.002). Conclusion This study validates an automated system that leverages Bayesian analysis to quantify the severity and distribution of perfusion changes in CTPA. The results show the potential of this method to support clinical evaluations of CTEPH by providing reproducible and objective measures.en
dc.description.abstractObjectives This work aimed to develop an automated method for quantifying the distribution and severity of perfusion changes on CT pulmonary angiography (CTPA) in patients with chronic thromboembolic pulmonary hypertension (CTEPH) and to assess their associations with clinical parameters and expert annotations. Materials and methods Following automated segmentation of the chest, a machine-learning model assuming three distributions of attenuation in the pulmonary parenchyma (hyperemic, normal, and oligemic) was fitted to the attenuation histogram of CTPA images using Bayesian analysis. The proportion of each component, its spatial heterogeneity (entropy), and center-to-periphery distribution of the attenuation were calculated and correlated with the findings on CTPA semi-quantitatively evaluated by radiologists and with clinical function tests. Results CTPA scans from 52 patients (mean age, 65.2 +/- 13.0 years; 27 men) diagnosed with CTEPH were analyzed. An inverse correlation was observed between the proportion of normal parenchyma and brain natriuretic propeptide (proBNP, rho = -0.485, p = 0.001), mean pulmonary arterial pressure (rho = -0.417, p = 0.002) and pulmonary vascular resistance (rho = -0.556, p < 0.0001), mosaic attenuation (rho = -0.527, p < 0.0001), perfusion centralization (rho = -0.489, p = < 0.0001), and right ventricular diameter (rho = -0.451, p = 0.001). The entropy of hyperemic parenchyma showed a positive correlation with the pulmonary wedge pressure (rho = 0.402, p = 0.003). The slope of center-to-periphery attenuation distribution correlated with centralization (rho = -0.477, p < 0.0001), and with proBNP (rho = -0.463, p = 0.002). Conclusion This study validates an automated system that leverages Bayesian analysis to quantify the severity and distribution of perfusion changes in CTPA. The results show the potential of this method to support clinical evaluations of CTEPH by providing reproducible and objective measures.en
dc.formattextcs
dc.format.extent6996-7003cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationEuropean radiology. 2025, vol. 35, issue May, p. 6996-7003.en
dc.identifier.doi10.1007/s00330-025-11678-ycs
dc.identifier.issn0938-7994cs
dc.identifier.orcid0000-0003-4293-260Xcs
dc.identifier.other198275cs
dc.identifier.researcheridD-3622-2018cs
dc.identifier.urihttps://hdl.handle.net/11012/255601
dc.language.isoencs
dc.relation.ispartofEuropean radiologycs
dc.relation.urihttps://link.springer.com/article/10.1007/s00330-025-11678-ycs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/0938-7994/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectHypertension (pulmonary)en
dc.subjectThromboembolism (pulmonary)en
dc.subjectComputed tomography angiographyen
dc.subjectPerfusion imagingen
dc.subjectImage interpretation (computer-assisted)en
dc.subjectHypertension (pulmonary)
dc.subjectThromboembolism (pulmonary)
dc.subjectComputed tomography angiography
dc.subjectPerfusion imaging
dc.subjectImage interpretation (computer-assisted)
dc.titleFully automated Bayesian analysis for quantifying the extent and distribution of pulmonary perfusion changes on CT pulmonary angiography in CTEPHen
dc.title.alternativeFully automated Bayesian analysis for quantifying the extent and distribution of pulmonary perfusion changes on CT pulmonary angiography in CTEPHen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-198275en
sync.item.dbtypeVAVen
sync.item.insts2025.10.30 11:04:39en
sync.item.modts2025.10.30 09:33:13en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav biomedicínského inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s0033002511678y.pdf
Size:
4.16 MB
Format:
Adobe Portable Document Format
Description:
file s0033002511678y.pdf
Download
Collections
Ústav biomedicínského inženýrství