C-THV measures of self-expandable valve positioning and correlation with implant outcomes

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.

Adjuncts to transcatheter aortic valve implantation

INTRODUCTION

The appreciable rise in percutaneous valve procedures has been pursued by a wave of development in advanced technology to help guide straightforward, streamlined and safe intervention. This review article aims to highlight the adjunctive devices, tools and techniques currently used in transcatheter aortic valve implantation procedures to avoid potential pitfalls. Areas covered: The software and devices featured here are at the forefront of technological advances, most of which are not yet in widespread use. These products have been discussed in national and international structural intervention conferences and the authors felt it important to showcase particularly well designed adjuncts that improve procedural efficacy and safety. Whilst vascular pre-closure systems are used routinely and are an integral part of these complex cardiovascular procedures, these have been well summarised elsewhere and are beyond the scope of this article. Expert commentary: The rising volume of patients with aortic stenosis who are treatable with TAVI means that this exponential increase in procedures must be accompanied by a steady decline in procedural complications. This section provides an overview of our current perspective, and what we feel the direction of travel will be.