Robotic-assisted real-time MRI-guided TAVR: from system deployment to in vivo experiment in swine model

Artificial Intelligence, Computational Simulations, and Extended Reality in Cardiovascular Interventions

Artificial intelligence, computational simulations, and extended reality, among other 21st century computational technologies, are changing the health care system. To collectively highlight the most recent advances and benefits of artificial intelligence, computational simulations, and extended reality in cardiovascular therapies, we coined the abbreviation AISER. The review particularly focuses on the following applications of AISER: 1) preprocedural planning and clinical decision making; 2) virtual clinical trials, and cardiovascular device research, development, and regulatory approval; and 3) education and training of interventional health care professionals and medical technology innovators. We also discuss the obstacles and constraints associated with the application of AISER technologies, as well as the proposed solutions. Interventional health care professionals, computer scientists, biomedical engineers, experts in bioinformatics and visualization, the device industry, ethics committees, and regulatory agencies are expected to streamline the use of AISER technologies in cardiovascular interventions and medicine in general.

Cardiac magnetic resonance imaging versus computed tomography to guide transcatheter aortic valve replacement: study protocol for a randomized trial (TAVR-CMR)

Background

The standard procedure for the planning of transcatheter aortic valve replacement (TAVR) is the combination of echocardiography, coronary angiography, and cardiovascular computed tomography (TAVR-CT) for the exact determination of the aortic valve dimensions, valve size, and implantation route. However, up to 80% of the patients undergoing TAVR suffer from chronic renal insufficiency. Alternatives to reduce the need for iodinated contrast agents are desirable. Cardiac magnetic resonance (CMR) imaging recently has emerged as such an alternative. Therefore, we aim to investigate, for the first time, the non-inferiority of TAVR-CMR to TAVR-CT regarding efficacy and safety end-points.

Methods

This is a prospective, randomized, open-label trial. It is planned to include 250 patients with symptomatic severe aortic stenosis scheduled for TAVR based on a local heart-team decision. Patients will be randomized in a 1:1 fashion to receive a predefined TAVR-CMR protocol or to receive a standard TAVR-CT protocol within 2 weeks after inclusion. Follow-up will be performed at hospital discharge after TAVR and after 1 and 2 years. The primary efficacy outcome is device implantation success at discharge. The secondary endpoints are a combined safety endpoint and a combined clinical efficacy endpoint at baseline and at 1 and 2 years, as well as a comparison of imaging procedure related variables. Endpoint definitions are based on the updated 2012 VARC-2 consensus document.

Discussion

TAVR-CMR might be an alternative to TAVR-CT for planning a TAVR procedure. If proven to be effective and safe, a broader application of TAVR-CMR might reduce the incidence of acute kidney injury after TAVR and thus improve outcomes.

Trial registration

The trial is registered at ClinicalTrials.gov (NCT03831087). The results will be disseminated at scientific meetings and publication in peer-reviewed journals.

Aortography Keypoint Tracking for Transcatheter Aortic Valve Implantation Based on Multi-Task Learning

Currently, transcatheter aortic valve implantation (TAVI) represents the most efficient treatment option for patients with aortic stenosis, yet its clinical outcomes largely depend on the accuracy of valve positioning that is frequently complicated when routine imaging modalities are applied. Therefore, existing limitations of perioperative imaging underscore the need for the development of novel visual assistance systems enabling accurate procedures. In this paper, we propose an original multi-task learning-based algorithm for tracking the location of anatomical landmarks and labeling critical keypoints on both aortic valve and delivery system during TAVI. In order to optimize the speed and precision of labeling, we designed nine neural networks and then tested them to predict 11 keypoints of interest. These models were based on a variety of neural network architectures, namely MobileNet V2, ResNet V2, Inception V3, Inception ResNet V2 and EfficientNet B5. During training and validation, ResNet V2 and MobileNet V2 architectures showed the best prediction accuracy/time ratio, predicting keypoint labels and coordinates with 97/96% accuracy and 4.7/5.6% mean absolute error, respectively. Our study provides evidence that neural networks with these architectures are capable to perform real-time predictions of aortic valve and delivery system location, thereby contributing to the proper valve positioning during TAVI.

ValveTech: A Novel Robotic Approach for Minimally Invasive Aortic Valve Replacement

OBJECTIVE

Aortic valve disease is the most common heart disease in the elderly calling for replacement with an artificial valve. The presented surgical robot aims to provide a highly controllable instrument for efficient delivery of an artificial valve by the help of integrated endoscopic vision.

METHODS

A robot (called ValveTech), intended for minimally invasive surgery (MIS) and consisting of a flexible cable driven manipulator, a passive arm, and a control unit has been designed and prototyped. The flexible manipulator has several features (e.g., stabilizing flaps, tiny cameras, dexterous introducer and custom cartridge) to help the proper valve placement. It provides 5 degrees of freedom for reaching the operative site via mini-thoracotomy; it adjusts the valve and expands it at the optimal position. The robot was evaluated by ten cardiac surgeons following a real surgical scenario in artificial chest simulator with an aortic mockup. Moreover, after each delivery, the expanded valve was evaluated objectively in comparison with the ideal position.

RESULTS

The robot performances were evaluated positively by surgeons. The trials resulted in faster delivery and an average misalignment distance of 3.8 mm along the aorta axis; 16.3 degrees rotational angle around aorta axis and 8.8 degrees misalignment of the valve commissure plane to the ideal plane were measured.

CONCLUSION

The trials successfully proved the proposed system for valve delivery under endoscopic vision.

SIGNIFICANCE

The ValveTech robot can be an alternative solution for minimally invasive aortic valve surgery and improve the quality of the operation both for surgeons and patients.

Multi-Modality Imaging in the Evaluation and Treatment of Tricuspid Regurgitation

PURPOSE OF REVIEW

The goal of this review is to cover the epidemiology of tricuspid regurgitation (TR), anatomy of the tricuspid valve (TV), and the mechanisms and modern treatment of TR. The focus will be on the role of echocardiography, cardiac CT, and MRI to determine the mechanism, severity, and management strategies of TR.

RECENT FINDINGS

The evaluation and management of TR is a rapidly growing field with significant advances in both imaging and interventions. Important advances have been made to understand TV anatomy and physiology in 3D echo, CT, and MRI. Additional understanding of the abnormal outcomes in both primary TR and secondary TR have been appreciated. Multiple transcatheter devices have reached the stage of early trials in high surgical risk cohorts with favorable initial findings. TR is a significant cardiovascular problem and vastly undertreated in the present era. There has been tremendous growth in knowledge of mechanisms of TR, its prognostic implications, timing of intervention, and development of novel treatment strategies. Multimodality imaging plays a key role in evaluation and treatment of this condition.