AI-Based Shape and Function Analysis of Mitral Valve Prolapse Using 3D Ultrasound (AI4MVP)

AI-Based Morphological Analysis and Biomechanical Numerical Evaluation of Mitral Valve Prolapse (MVP) From Real-Time 3D Echocardiography (RT3DE)

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.

Study Overview

• Status: Recruiting
• Conditions: Mitral Valve Prolapse; Myxomatous Mitral Valve Degeneration

Detailed Description

This prospective study aims to investigate the anatomical and biomechanical characteristics of MVP using RT3DEE and advanced artificial intelligence (AI)-based image analysis techniques. The goal is to develop an automated framework for the segmentation and morphological assessment of the MV apparatus, and to conduct FE modeling to evaluate the biomechanical implications of degenerative MVP and associated surgical repairs.

Imaging Protocol Intraoperative RT3DE will be performed in the operating room as part of the standard imaging protocol during surgical MVP repair. A Vivid S70N ultrasound system (GE Healthcare) equipped with a 6VT 4D multiplane RT3DE probe will be used. Standard mid-esophageal RT3DE views will be acquired, including full left ventricular (LV) chamber volumes and zoomed, gated 3D views of the MV complex (annulus, leaflets, and papillary muscles). To enhance image quality, zoomed acquisitions will be limited to the smallest pyramidal volume capturing the entire mitral complex, ensuring frame rates ≥20 Hz. All imaging datasets will be anonymized prior to analysis.

Surgical Protocol MVP surgical repair will be conducted under general anesthesia through a right mini-thoracotomy. Surgical techniques will include: i) leaflet resection (removal of excess leaflet tissue); ii) neochordal implantation (placement of expanded polytetrafluoroethylene, ePTFE, artificial chordae); annuloplasty (implantation of an annuloplasty ring or pericardial band for annular stabilization).

In cases where significant leaflet tissue is excised (≥10×10 mm), samples will be collected and stored in the institutional BioCor biobank for histological and morphometric analysis. Samples will be decontaminated, cryopreserved, and stored at -80°C. After histological evaluation, all biological material will be destroyed.

Clinical Data Collection Demographic (e.g., age, sex) and clinical data (e.g., diagnosis, medications, comorbidities) will be obtained from medical records and anonymized.

Neural Network Training for Image Segmentation Anonymized RT3DE datasets will be manually segmented by expert operators using advanced image analysis software (e.g., 3D Slicer). A minimum of 150 RT3DE acquisitions will be processed to generate binary masks of the MV annulus, leaflets, and papillary muscles.

These segmented datasets will be used to train a convolutional neural network (CNN), likely based on the 3D U-Net architecture; 70% of the datasets will be used as training data and 30% will be reserved for testing and validation.

The CNN will learn to automatically segment MV structures and generate 3D surface models. Key anatomical features-such as annulus contour, leaflet free margin, commissures, and papillary muscle positions-will be extracted automatically.

Quantitative geometric parameters will include annular area, perimeter, anteroposterior diameter, commissural width, annular height and ellipticity, leaflet dimensions, coaptation zones and billowing extent.

FE Analysis Patient-specific 3D models of the mitral valve will be reconstructed from the segmented RT3DE data. These models will undergo smoothing and remeshing to generate high-quality meshes for structural FE analysis. Chordae tendineae will be modeled based on established anatomical templates and tuned to match physiological lengths. Tissue material properties will be assigned based on published experimental data.

FE simulations will be used to quantify stress distribution on MV leaflets, assess load transfer between leaflets and papillary muscles and evaluate mechanical effects of surgical interventions (e.g., neochordal implantation, annuloplasty) These simulations are retrospective and exploratory; they will not influence surgical decision-making.

Follow-up No post-operative follow-up is required beyond standard clinical care. The study is focused on intraoperative imaging and tissue collection, followed by offline image analysis and computational modeling.

• Study Type: Observational
• Enrollment (Estimated): 150

Contacts and Locations

• Study Contact: Name: Francesco Sturla; Phone Number: +390252774353; Email: francesco.sturla@grupposandonato.it
• Study Contact Backup: Name: Diana Crina Benea; Phone Number: +390252774765; Email: dianacrina.benea@grupposandonato.it

Study Locations

• Italy
  • San Donato Milanese, Italy, 20097
    • Recruiting
    • IRCCS Policlinico San Donato
    • Contact: Francesco Sturla; Phone Number: +390252774353; Email: francesco.sturla@grupposandonato.it
    • Contact: Diana Benea; Phone Number: +390252774765; Email: dianacrina.benea@grupposandonato.it
    • Principal Investigator: Francesco Sturla
    • Sub-Investigator: Diana Crina Benea
    • Sub-Investigator: Marco Diena
    • Sub-Investigator: Davide Tondi
    • Sub-Investigator: Emiliano Votta

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

The study will focus on patients referred to IRCCS Policlinico San Donato for surgical MVP repair. The study will exploit the standard clinical imaging required during MVP surgical repair and will have no impact on the clinical procedure. No variation in prophylaxis or follow-up is expected compared to those of practice as suggested by the international guideline. Hence, there are no physical, psychological, and social risks and/or direct benefits associated with the activities carried out during the study.

Description

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.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of automated MV substructure segmentation and extraction of anatomical landmarks from RT3DE	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).	36 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Automated quantification of MV morphometric and functional descriptors	Ability of the automated pipeline to derive consistent quantification - compared to commercially available solutions for RT3DE processing - of clinically relevant morphometric and functional descriptors of degenerative MVP from RT3DE: i) mitral annular dimensions (projected area, mm²; perimeter, mm; antero-posterior and commissural diameters, mm; height, mm; ellipticity, -); ii) leaflet surface area and billowing volume (mm², mm³); leaflet prolapse height and prolapse volume (mm, mm³); coaptation length and coaptation area (mm, mm²).	36 months
Change in mechanical stress of MV leaflets following surgical MVP repair	Assessment of change in mechanical stress of MV leaflets following surgical MVP repair using patient-specific FE MV models derived from RT3DE, comparing peak and mean leaflet stress (kPa) between degenerative MVP and post-repair conditions.	Up to 1 month after MVP surgical repair
Change in mechanical load transfer to MV sub-apparatus following surgical MVP repair	Assessment of changes in the mechanical load transfer to MV sub-apparatus following MV surgical repair using patient-specific FE MV models derived from RT3DE, comparing chordal forces and load transfer to MV papillary muscles (N) between degenerative MVP and post-repair conditions.	Up to 1 month after MVP surgical repair
Change in mechanical stress of MV papillary muscles following surgical MVP repair	Assessment of change in mechanical stress acting on MV papillary muscles following surgical MVP repair using patient-specific FE MV models derived from RT3DE, comparing peak and mean stress (kPa) between degenerative MVP and post-repair conditions.	Up to 1 month after MVP surgical repair
Change in coaptation of MV leaflets following surgical MV repair	Assessment of change in MV leaflet coaptation following surgical MVP repair using patient-specific FE MV models derived from RT3DE, comparing coaptation length and area (mm, mm²) between degenerative MVP and post-repair conditions.	Up to 1 month after MVP surgical repair
Thickness of MV leaflet tissue excised during MVP surgical repair	Assessment of the thickness (mm) of MV leaflet tissue excised as a consequence of substantial leaflet resection during surgical MVP repair.	Up to 2 weeks after MVP surgical repair
Degree of myxomatous degeneration of excised MV leaflet tissue	Gross and histomorphometric assessment of the degree of myxomatous degeneration of MV leaflet tissue surgically excised during MVP surgical repair, using a semi-quantitative score (0-3): 0 = absent (no gross or histological evidence); 1 = mild (limited focal myxoid/proteoglycan extracellular matrix expansion with mild collagen disorganization); 2 = moderate (diffuse or multifocal myxoid/proteoglycan expansion with moderate collagen fragmentation/disorganization and leaflet thickening); 3 = severe (extensive/diffuse myxoid degeneration with marked extracellular matrix expansion, severe collagen disruption, and pronounced leaflet thickening/redundancy).	Up to 2 weeks after MVP surgical repair
Structural histological analysis of excised myxomatous MV leaflet tissue	Quantitative histological assessment of myxomatous degeneration of excised MV leaflet tissue obtained during mitral valve prolapse (MVP) surgical repair, quantifying collagen and elastin content (% of tissue area) through structural stains.	Up to 2 weeks after MVP surgical repair

Collaborators and Investigators

• Sponsor: IRCCS Policlinico S. Donato

Study record dates

Study Major Dates

• Study Start (Actual): May 26, 2025
• Primary Completion (Estimated): May 1, 2028
• Study Completion (Estimated): May 1, 2028

Study Registration Dates

• First Submitted: January 12, 2026
• First Submitted That Met QC Criteria: January 26, 2026
• First Posted (Actual): February 3, 2026

Study Record Updates

• Last Update Posted (Actual): February 3, 2026
• Last Update Submitted That Met QC Criteria: January 26, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Cardiovascular Diseases; Heart Diseases; Heart Valve Diseases; Heart Valve Prolapse; Mitral Valve Prolapse
• Other Study ID Numbers: AI4MVP

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No