Optimal C-arm angulation during transcatheter aortic valve replacement: Accuracy of a rotational C-arm computed tomography based three dimensional heart model

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.

Distribution of C-arm projections in native and bioprosthetic aortic valves cusps: Implication for BASILICA procedures

OBJECTIVES

We sought to document aortic cusps fluoroscopic projections and their distributions using leaflet alignment which is a novel concept to optimize visualization of leaflets and for guiding BASILICA (bioprosthetic or native aortic scallop intentional laceration to prevent coronary artery obstruction) and determine whether these projections were feasible in catheter laboratory.

BACKGROUND

Optimal fluoroscopic projections of aortic valve cusps have not been well described.

METHODS

A total of 128 pre-transcatheter aortic valve replacement (pre-TAVR) computed tomographies (CT) (72 native valves and 56 bioprosthetic surgical valves) were analyzed. Using CT software (3Mensio, Pie medical imaging, the Netherlands), leaflet alignment was performed and the feasibility of these angles, which were defined as rate of obtainable with efforts (within LAO/RAO of 85° and CRA/CAU of 50°) were evaluated.

RESULTS

High feasibility was seen in right coronary cusp (RCC) front view (100%) and left coronary cusp (LCC) side view (99.2%), followed by noncoronary cusp side view (95.3%). In contrast, low feasibility of RCC side view (7.8%) and LCC front view (47.6%) was observed. No statistical differences were seen between the distribution of native valves and bioprosthetic surgical valves. With patient/table tilt of 20°LAO and 10°CRA, the feasibility of RCC side view and LCC front view increased to 43.7 and 85.2%, respectively.

CONCLUSION

Distributions of each cusp's leaflet alignment follows "sigmoid curve" which can provide better understanding of aortic valve cusp orientation in TAVR and BASILICA. RCC side view used in right cusp BASILICA is commonly unachievable in catheter laboratory and may improve with patient/table tilt.