This multicenter, retrospective study develops and validates artificial intelligence (AI)-based semantic segmentation algorithms for intraprocedural transesophageal echocardiography (TEE) during Transcatheter Mitral Edge-to-Edge Repair (TEER). Using pooled imaging data from multiple high-volume structural heart centers, the study aims to automate recognition of mitral leaflets and MitraClip components, measure leaflet insertion length in real time, and display clip position and orientation. Algorithm performance will be benchmarked against expert manual annotations.

Transcatheter Mitral Edge-to-Edge Repair (TEER) with the MitraClip device is an established minimally invasive treatment for patients with severe mitral regurgitation who are at high surgical risk. The success of TEER relies heavily on real-time transesophageal echocardiography (TEE) to guide precise clip positioning and leaflet capture. However, intraoperative image interpretation remains highly dependent on operator experience, and variability in image quality, patient anatomy, and the dynamic nature of cardiac structures continue to challenge procedural standardization across centers.

This multicenter, retrospective imaging study evaluates whether artificial intelligence (AI)-based semantic segmentation can automate the recognition of mitral valve anatomy and MitraClip device components on intraprocedural TEE images. Previously acquired TEE imaging from adult patients who underwent TEER at multiple participating high-volume structural heart centers will be pooled and analyzed. All data are derived from routine clinical care, and only patients with appropriate consent for research use of their clinical and imaging data are included.

The study has three objectives: (1) to develop deep learning models that automatically segment the anterior and posterior mitral leaflets and the MitraClip grippers and arms; (2) to automate real-time measurement of leaflet insertion length during the grasping process; and (3) to integrate three-dimensional imaging with intelligent tracking to display clip position and orientation. By drawing on a multicenter dataset, the study aims to improve the generalizability and robustness of the resulting models across diverse imaging environments, operator practices, and patient anatomies. Algorithm performance will be benchmarked against expert manual annotations using established image segmentation metrics.

Inclusion Criteria:

• Adult patients (≥18 years of age) at the time of the index procedure
• Confirmed diagnosis of degenerative or functional mitral regurgitation
• Underwent Transcatheter Mitral Edge-to-Edge Repair (TEER) with the MitraClip device at one of the participating centers
• Intraprocedural transesophageal echocardiographic (TEE) imaging available, complete, and of sufficient quality to support semantic segmentation and real-time measurement analyses
• Appropriate consent for research use of clinical and imaging data, as per the policy of each participating center

Exclusion Criteria:

• Incomplete or poor-quality intraprocedural TEE imaging unsuitable for accurate segmentation and measurement
• Ambiguous or unconfirmed diagnosis of mitral regurgitation
• Documented refusal to allow use of clinical or imaging data for research purposes
• Missing essential clinical documentation required to confirm eligibility

The study population consists of adult patients with degenerative or functional mitral regurgitation who underwent Transcatheter Mitral Edge-to-Edge Repair (TEER) with the MitraClip device at multiple participating high-volume structural heart centers. All data are derived from routine clinical care, including intraprocedural transesophageal echocardiographic (TEE) imaging and corresponding clinical records. Only patients with appropriate consent for research use of their data, as defined by the policy of each participating center, are included. The cohort reflects real-world TEER practice across diverse imaging environments, operator experience, and patient anatomies, supporting the development and validation of artificial intelligence-based segmentation and measurement tools with improved generalizability.

Individual participant data will not be shared. All clinical and imaging data are pseudonymized and stored under restricted access in accordance with the approved study protocol, applicable data protection regulations (Swiss Human Research Act, Swiss Federal Act on Data Protection, and applicable regulations at each participating center), and the sponsor's data governance policy. Aggregated and anonymized results will be disseminated through peer-reviewed publications and scientific presentations.