This study aims to develop and validate a fully automated imaging and modeling pipeline for the analysis of mitral valve prolapse (MVP) using real-time three-dimensional transesophageal echocardiography (RT3DE). The primary goal is to automatically segment mitral valve (MV) substructures, extract anatomical landmarks, and generate 3D models of the MV apparatus to characterize morphological and functional features of degenerative MVP. Advanced deep learning techniques and geometric processing tools will be applied to enable automated analysis.
A secondary objective is to build patient-specific finite element (FE) models based on RT3DE data to evaluate the biomechanical consequences of MVP and to simulate the effects of surgical repair. These simulations will assess stress distribution and force transmission within the MV apparatus.
Additionally, in cases where substantial surgical resection of MV tissue occurs, excised leaflet samples will be collected and preserved for histological and morphometric analysis.
Eligibility
Sex
ALL
Min age
18 Years
Max age
—
Healthy volunteers
No
Inclusion Criteria:
* Adult patients (age \> 18 years old);
* Documented symptomatic degenerative MR with indication to MVP surgical repair, following the Heart Team decision;
* Periprocedural transesophageal 3DRTE of the MV apparatus, which is clinical standard modality for morphological assessment and guidance during MVP surgical repair;
* Signed informed consent.
Exclusion Criteria:
* Inadequate quality of 3DRTE imaging, e.g., due to inadequate patient-specific acoustic window;
* 3DRTE imaging with a temporal resolution of \< 20 Hz;
* Patient treated through prosthetic MV replacement.
Primary outcome measure(s)
Accuracy of automated MV substructure segmentation and extraction of anatomical landmarks from RT3DE — 36 months The accuracy of AI-based automated segmentation of MV substructures (anterior and posterior leaflets, mitral annulus, and papillary muscles) from RT3DE is assessed using expert manual segmentation as reference standard and analyzing the following measures: i) Dice Similarity Coefficient (DSC, -); ii) Mean Surface Distance (MSD, mm); iii) Hausdorff Distance (HD, mm). Accuracy of AI-based automated identification of key MV anatomical landmarks relevant to degenerative mitral valve prolapse is assessed compared with expert manual annotation analyzing the Euclidean distance error (mm) between automated and expert-defined landmarks (annular hinge points, leaflet free-edge points, coaptation line, papillary muscle tips).
This page summarises publicly available registry data for informational purposes — not medical advice. Eligibility is determined by each study team; patients should discuss participation with their clinician.
We use cookies to analyse site traffic and improve your experience. With your consent, we may also use cookies for advertising. You can change your choice at any time.
