The aim of this study is to enhance the predictability of therapeutic success in transcatheter tricuspid valve intervention (TTVI) for patients with severe tricuspid regurgitation (TR). This will be achieved through automated analyses of pre-interventional computed tomography (CT) scans. Severe tricuspid regurgitation is associated with poor patient outcomes. In advanced stages, pharmacological therapy becomes ineffective, and surgical intervention carries a high mortality risk. Given this clinical challenge, catheter-based treatment of the tricuspid valve has become a focal point of research. One well-established treatment strategy is percutaneous tricuspid valve intervention, which aims to reduce regurgitation either through annuloplasty, leaflet-based edge-to-edge repair or valve replacement. This approach has been shown to significantly decrease the severity of regurgitation, leading to a dramatic reduction in symptom burden and a marked improvement in quality of life. However, predicting which patients will benefit most from TTVI and determining the optimal technique for each individual remain largely unresolved challenges. Artificial intelligence (AI)-powered software, such as heart.ai by LARALAB (Munich), enables automated measurement of anatomical structures captured via CT imaging. This technology already allows for rapid and precise assessment of cardiac chambers and the tricuspid annulus throughout the entire cardiac cycle, facilitating a comprehensive three-dimensional evaluation of right heart anatomy. To refine patient selection and optimize procedural strategies for TR treatment, the researcher work a multi-center collaboration to analyze treatment outcomes and patient response to specific therapeutic approaches.