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

What this Trial Is About

This research aims to develop and validate an automated imaging and modeling system to analyze mitral valve prolapse (MVP) using real-time three-dimensional transesophageal echocardiography (RT3DE). The study focuses on automatically segmenting the mitral valve substructures, extracting key anatomical landmarks, and creating 3D models to assess the shape and function of degenerative MVP. Advanced deep learning and geometric tools will be used to improve analysis. Additionally, patient-specific biomechanical models will be built to study the effects of MVP and surgical repairs on the valve's structure and forces. Imaging will be performed during surgery using a specialized ultrasound system in standard views of the mitral valve and left ventricle. Surgical repair techniques include leaflet tissue removal, artificial chordae implantation, and annuloplasty for valve stabilization. When significant valve tissue is removed, samples will be collected and preserved for detailed tissue analysis. The study also involves training a neural network on segmented images to enable automated processing and 3D model generation. Participants will undergo intraoperative imaging as part of their MVP surgery, with clinical data collected anonymously. The automated system will be tested for its accuracy in segmenting valve structures and extracting features over 36 months. Biomechanical simulations will evaluate changes after surgery. No extra follow-up is needed beyond standard care. The study focuses on image analysis and modeling performed after surgery, lasting up to the completion date in 2028.

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