Aortic root evaluation prior to transcatheter aortic valve implantation-Correlation of manual and semi-automatic measurements

A fully automated artificial intelligence-driven software for planning of transcatheter aortic valve replacement

BACKGROUND

Transcatheter aortic valve replacement (TAVR) is increasingly performed for the treatment of aortic stenosis. Computed tomography (CT) analysis is essential for pre-procedural planning. Currently available software packages for TAVR planning require substantial human interaction. We describe development and validation of an artificial intelligence (AI) powered software to automatically rend anatomical measurements and other information required for TAVR planning and implantation.

METHODS

Automated measurements from 100 CTs were compared to measurements from three expert clinicians and TAVR operators using commercially available software packages. Correlation coefficients and mean differences were calculated to assess precision and accuracy.

RESULTS

AI-generated annular measurements had excellent agreements with manual measurements by expert operators yielding correlation coefficients of 0.97 for both perimeter and area. There was no relevant bias with a mean difference of -0.07 mm and - 1.4 mm2 for perimeter and area, respectively. For the ascending aorta measured 5 cm above the annular plane, correlation coefficient was 0.95 and mean difference was 1.4 mm. Instruction for use-based sizing yielded agreement with the effective implant size in 87-88 % of patients for self-expanding valves (perimeter-based sizing) and in 88 % for balloon-expandable valves (area-based sizing).

CONCLUSIONS

A fully automated software enables accurate and precise anatomical segmentation and measurements required for TAVR planning without human interaction and with high reliability.

CT angiography prior to endovascular procedures: can artificial intelligence improve reporting?

CT angiography prior to endovascular aortic surgery is the standard non-invasive imaging method for evaluation of aortic dimensions and access sites. A detailed report is crucial to a proper planning. We assessed Artificial Intelligence (AI)-algorithm accuracy to measure vessels diameters at CT prior to transcatheter aortic valve implantation (TAVI). CT scans of 50 patients were included. Two Radiologists with experience in vascular imaging together manually assessed diameters at nine landmark positions according to the American Heart Association guidelines: 450 values were obtained. We implemented TOST (Two One-Sided Test) to determine whether the measurements were equivalent to the values obtained from the AI algorithm. When the equivalence bound was a range of ± 2 mm the test showed equivalence for every point; if the range was equal to ± 1 mm the two measurements were not equivalent in 6 points out of 9 (p-value > 0.05), close to the aortic valve. The time for automatic evaluation (average 1 min 47 s) was significantly lower compared with manual measurements (5 min 41 s) (p < 0.01). In conclusion, our results indicate that AI-algorithms can measure aortic diameters at CT prior to endovascular surgery with high accuracy. AI-assisted reporting promises high efficiency, reduced inter-reader variabilities and time saving. In order to perform optimal TAVI procedure planning aortic root analysis could be improved, including annulus dimensions.

Usability and accuracy of two different aortic annulus sizing software programs in patients undergoing transcatheter aortic valve replacement

BACKGROUND

Semi-automated software is essential for planning and prosthesis selection prior transcatheter aortic valve replacement (TAVR). Reliable data on the usability of software programs for planning a TAVR is missing. The aim of this study was to compare software programs 'Valve Assist 2' (GE Healthcare) and 3mensio 'Structural Heart' (Pie Medical Imaging) regarding usability and accuracy of prosthesis size selection in program-inexperienced users.

METHODS

Thirty-one participants (n = 31) were recruited and divided into program-inexperienced users (beginners) (n = 22) and experts (n = 9). After software training, beginners evaluated 3 patient cases in 129 measurements (n = 129) using either Valve Assist 2 (n = 11) or Structural Heart (n = 11) on 2 test days (T1, T2). System Usability Scale (SUS) and ISONORM 9241/110-S (ISONORM) questionnaire were used after the test. The valve size selected by each beginner was compared with the valve size selected from expert group.

RESULTS

Valve Assist 2 had higher SUS Score: median 78.75 (25th, 75th percentile: 67.50, 85.00) compared to Structural Heart: median 65.00 (25th, 75th percentile: 47.50, 73.75), (p < 0,001, r = 0.557). Also, Valve Assist 2 showed a higher ISONORM score: median 1.05 (25th, 75th percentile: - 0.19, 1.71) compared to Structural Heart with a median 0.05 (25th, 75th percentile: - 0.49, 0.13), (p = 0.036, r = 0.454). Correctly selected valve sizes were stable over time using Valve Assist 2: 72.73% to 69.70% compared to Structural Heart program: 93.94% to 40% (χ2 (1) = 21.10, p < 0.001, φ = 0.579).

CONCLUSION

The study shows significant better usability scores for Valve Assist 2 compared to 3mensio Structural Heart in program-inexperienced users.

Preoperative TAVR Planning: How to Do It

Transcatheter aortic valve replacement (TAVR) is a well-established treatment option for patients with severe symptomatic aortic stenosis (AS) whose procedural efficacy and safety have been continuously improving. Appropriate preprocedural planning, including aortic valve annulus measurements, transcatheter heart valve choice, and possible procedural complication anticipation is mandatory to a successful procedure. The gold standard for preoperative planning is still to perform a multi-detector computed angiotomography (MDCT), which provides all the information required. Nonetheless, 3D echocardiography and magnet resonance imaging (MRI) are great alternatives for some patients. In this article, we provide an updated comprehensive review, focusing on preoperative TAVR planning and the standard steps required to do it properly.

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.

Retrospectively ECG-gated helical vs. non-ECG-synchronized high-pitch CTA of the aortic root for TAVI planning

Background

Multidetector computed tomography (MDCT) plays a key role in patient assessment prior to transcatheter aortic valve implantation (TAVI). However, to date no consensus has been established on what is the optimal pre-procedural imaging protocol. Variability in pre-TAVI acquisition protocols may lead to discrepancies in aortic annulus measurements and may potentially influence prosthesis size selection.

Purpose

The current study evaluates the magnitude of differences in aortic annulus measurements using max-systolic, end-diastolic, and non-ECG-synchronized imaging, as well as the impact of method on prosthesis size selection.

Material and methods

Fifty consecutive TAVI-candidates, who underwent retrospectively-ECG-gated CT angiography (CTA) of the aortic root, directly followed by non-ECG-synchronized high-pitch CT of the entire aorta, were retrospectively included. Aortic root dimensions were assessed at each 10% increment of the R-R interval (0–100%) and on the non-ECG-synchronized scan. Dimensional changes within the cardiac cycle were evaluated using a 1-way repeated ANOVA. Agreement in measurements between max-systole, end-diastole and non-ECG-synchronized scans was assessed with Bland-Altman analysis.

Results

Maximal dimensions of the aortic root structures and minimum annulus-coronary ostia distances were measured during systole. Max-systolic measurements were significantly and substantially larger than end-diastolic (p<0.001) and non-ECG-synchronized measurements (p<0.001). Due to these discrepancies, the three methods resulted in the same prosthesis size selection in only 48–62% of patients.

Conclusions

The systematic differences between max-systolic, end-diastolic and non-ECG-synchronized measurements for relevant aortic annular dimensions are both statistically significant and clinically relevant. Imaging strategy impacts prosthesis size selection in nearly half the TAVI-candidates. End-diastolic and non-ECG-synchronized imaging does not provide optimal information for prosthesis size selection. Systolic image acquisition is necessary for assessment of maximal annular dimensions and minimum annulus-coronary ostia distances.