Role of Imaging Techniques in Percutaneous Treatment of Mitral Regurgitation

Complications of the Percutaneous Mitral Valve Edge-To-Edge Repair: Role of Transesophageal Echocardiography

The use of transcatheter edge-to-edge repair for the treatment of mitral regurgitation has markedly increased in the last few years. The rate of adverse events related to the procedure is low; however, some of the complications that may occur are potentially dangerous. Due to the growing popularity of the technique, which is no longer limited to high-volume centers, knowledge of the complications related to the procedure is fundamental. Transesophageal echocardiography has a key role in the guidance of the intervention while allowing for the avoidance of most of these adverse events, as well as enabling us to diagnose them early. In this article, we review the main complications that might present during a transcatheter mitral edge-to-edge repair procedure (tamponade, thromboembolic events, single leaflet device attachment, device embolization, vascular injury…) while highlighting key aspects of transesophageal echocardiographic monitoring in the prevention and prompt diagnosis of these complications.

Real-Time Monitoring and Step-by-Step Guidance for Transapical Mitral Valve Edge-to-Edge Repair Using Transesophageal Echocardiography

MitraClip edge-to-edge (E2E) repair system is the only transcatheter device recommended in the current guidelines for treating mitral regurgitation (MR). The percutaneous femoral venous transseptal access of MitraClip requires a complex steerable delivery system and may thus be technically complex to optimally position and deploy the clip onto the mitral valve. A transapical approach for E2E repair has been devised to treat MR for the ease of operation (ValveClamp system, Hanyu Medical Technology, Shanghai). The first-in-human study of ValveClamp has demonstrated its early feasibility and effectiveness for the treatment of patients with degenerative MR. Transesophageal echocardiography (TEE) is the only imaging modality required for intraoperative guidance of ValveClamp implantation. Successful implantation depends on accurate localization and orientation of the clamp and efficient intraoperative communication between the echocardiographer and the intervention team. Thus, the focus of this review is on elaborating how two-dimensional (2D) and three-dimensional (3D) TEE are used in clinical practice to guide ValveClamp implantation and it may facilitate the understanding of simplicity and safety of this novel procedure. We also describe the implementation of several novel advancements in 3D TEE imaging, which improve the confidence of image interpretation for intraoperative guidance and expedite implantation times.

A deep learning approach for the automatic recognition of prosthetic mitral valve in echocardiographic images

The first step in the automatic evaluation of the cardiac prosthetic valve is the recognition of such valves in echocardiographic images. This research surveyed whether a deep convolutional neural network (DCNN) could improve the recognition of prosthetic mitral valve in conventional 2D echocardiographic images. An efficient intervention to decrease the misreading rate of the prosthetic mitral valve is required for non-expert cardiologists. This intervention could serve as a section of a fully-automated analysis chain, alleviate the cardiologist's workload, and improve precision and time management, especially in an emergent situation. Additionally, it might be suitable for pre-labeling large databases of unclassified images. We, therefore, introduce a large publicly-available annotated dataset for the purpose of prosthetic mitral valve recognition. We utilized 2044 comprehensive non-stress transthoracic echocardiographic studies. Totally, 1597 patients had natural mitral valves and 447 patients had prosthetic valves. Each case contained 1 cycle of echocardiographic images from the apical 4-chamber (A4C) and the parasternal long-axis (PLA) views. Thirteen versions of the state-of-the-art models were independently trained, and the ensemble predictions were performed using those versions. For the recognition of prosthetic mitral valves from natural mitral valves, the area under the receiver-operating characteristic curve (AUC) made by the deep learning algorithm was similar to that made by cardiologists (0.99). In this research, EfficientNetB3 architecture in the A4C view and the EfficientNetB4 architecture in the PLA view were the best models among the other pre-trained DCNN models.

Considerations on the use of MitraClip in the treatment of mitral regurgitation

Mitral regurgitation (MR) is, by occurrence, the second most common valvular heart disease in the Western world, with a significant impact on prognosis and mortality. A significant number of patients with significant mitral incompetence cannot be submitted to conventional surgery due to high surgical risk. The need for an adequate therapeutical strategy prompted the development of innovative endovascular techniques. Among them, the MitraClip percutaneous system, mimicking the ‘edge-to-edge’ surgical technique introduced by Alfieri in 2003 has emerged as the treatment of choice in patients not suitable for conventional surgery. Since its introduction, this procedure has been effectively carried out in more than 35 000 patients. The evidences from the first randomized clinical trial, EVEREST II, suggested that the MitraClip system is effective in improving survival and quality of life in patients with severe MR. Further randomized trials, MITRA-FR and COAPT, added some more information, showing that an appropriate patient selection, close attention to the specific anatomical characteristics of the mitral valve, and adequate experience of the centre providing the treatment, are important determinants of the outcome of the procedure.