Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Master's Award: Canada Graduate Scholarships

University of Calgary

$17,500.00

Development of modality-agnostic spatiotemporal cardiac anatomic models for the prediction of patient outcomes – demonstrated with risk prediction on patients with Aortic Stenosis

EF 2023-24

Résumé
Multi-phased 3D cardiac computerized tomography (CT) has become a ubiquitously performed test to guide minimally invasive aortic valve replacement. This 4D dataset offers unprecedented and incremental value for modeling post-procedural outcomes given its comprehensive description of multi-chamber and vascular cardiac pathophysiology. We hypothesize that a unique 4D cardiac anatomical modeling approach can be applied to this data to accurately predict heart failure and death early post valve replacement. Using a novel geometric deep learning (GDL) based approach we will leverage an established and curated 220 patient data set to i) establish a standardized mesh-based modeling of all cardiac chambers throughout multiple cardiac phases, and ii) deliver a proof-of-concept demonstration for GDL-based prediction of heart failure of death using pre-procedural multi-phase CT images.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
506400
Name
Marianchuk Rylan
Region
Alberta
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Development of modality-agnostic spatiotemporal cardiac anatomic models for the prediction of patient outcomes – demonstrated with risk prediction on patients with Aortic Stenosis
Programtype2
Studentship Programs
Orgnameinp2
University of Calgary
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Aortic Stenosis; Cardiac Imaging; Computer Automated Diagnosis; Digital Phenomics; Geometric Deep Learning; Machine Learning; Neural Networks; Precision Cardiology; Risk Prediction
Abstract
Multi-phased 3D cardiac computerized tomography (CT) has become a ubiquitously performed test to guide minimally invasive aortic valve replacement. This 4D dataset offers unprecedented and incremental value for modeling post-procedural outcomes given its comprehensive description of multi-chamber and vascular cardiac pathophysiology. We hypothesize that a unique 4D cardiac anatomical modeling approach can be applied to this data to accurately predict heart failure and death early post valve replacement. Using a novel geometric deep learning (GDL) based approach we will leverage an established and curated 220 patient data set to i) establish a standardized mesh-based modeling of all cardiac chambers throughout multiple cardiac phases, and ii) deliver a proof-of-concept demonstration for GDL-based prediction of heart failure of death using pre-procedural multi-phase CT images.
Competitiondate
202312
Approvedterm2
1 yr 0 mth
Pinamesdelim
Marianchuk, Rylan
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~