Artificial Intelligence-Based Intraoperative Endoleak Visualization on Completion Digital Subtraction Angiography during Endovascular Aneurysm Repair

 

Introduction: Completion DSA is typically performed at the end of the EVAR and assessed by visual inspection of the surgical team. DSA images contain information on the stent graft position, possible endoleaks, patency of arteries and stent-graft limbs, and blood flow dynamics.³ We propose to analyse these images with artificial intelligence methods using deep learning and perfusion DSA parameters.^4,5 We hypothesize that intraoperative automatic endoleak visualisation during EVAR is possible with objective endoleak analysis, and can aid the physician in intraoperative clinical-decision-making.

Methods: We performed a single-centre, experimental study with retrospective collected data to create a deep-learning based intra-operative endoleak visualization. Recent EVAR procedural imaging to treat an infrarenal aortic aneurysm was collected. Images were acquired in the hybrid operating room with Azurion FlexMove 7 C20 (Philips, Best, The Netherlands) in the Amsterdam UMC, between May 2017 and April 2019. The completion DSA was extracted from the procedural images and reviewed by an expert panel consisting of two vascular surgeons and two interventional radiologists on endoleak presence and type (1,2,3,4 or unknown). The completion DSA images of 97 patients were collected, of which 49 with an endoleak. The location of each endoleak was labelled with a rectangular bounding box.

A two-dimensional convolutional neural network (CNN) with a U-Net architecture was trained for automatic endoleak visualisation.⁶ Perfusion DSA parameters were calculated per pixel; peak density (PD), time of arrival (TOA), time to peak (TTP) and area under the curve (AUC) (Figure 1). The model was implemented in Pytorch and Medical Open Network for Artificial Intelligence (MONAI) and networks were trained and evaluated using an NVIDIA GeForce RTX 3090 GPU. Statistical analysis was performed by sensitivity and specificity calculation and a receiver operating characteristic (ROC)-curve was created with corresponding AUC.

Results: It was possible to transform all completion DSA into perfusion DSA. After training, the network was able to detect endoleaks on the test set which contains completion DSA never shown before. This resulted in endoleak prediction heatmaps on each completion DSA (Figure 2). From the ROC-curve, the calculated AUC of the sensitivity and specificity was 0.84.

Conclusion: We developed a fully automatic endoleak visualisation method based on the completion digital subtraction angiography during EVAR.

This objective analysis of intraoperative information can extract detailed knowledge and aid the physician in the endovascular hybrid operating room in clinical decision making with a deep learning algorithm. Future developments will focus on the classification of endoleak types.

References

1. Doelare SAN, Smorenburg SPM, van Schaik TG, et al. Image Fusion During Standard and Complex Endovascular Aortic Repair, to Fuse or Not to Fuse? A Meta-analysis and Additional Data From a Single-Center Retrospective Cohort. J Endovasc Ther 2021;28(1):78–92 10.1177/1526602820960444 PubMed

2. Stangenberg L, Shuja F, Carelsen B, Elenbaas T, Wyers MC, Schermerhorn ML. A novel tool for three-dimensional roadmapping reduces radiation exposure and contrast agent dose in complex endovascular interventions. J Vasc Surg 2015;62(2):448–455 10.1016/j.jvs.2015.03.041 PubMed

3. Cho H, Lee JG, Kang SJ, et al. Angiography-Based Machine Learning for Predicting Fractional Flow Reserve in Intermediate Coronary Artery Lesions. J Am Heart Assoc 2019;8(4):e011685 10.1161/JAHA.118.011685 PubMed

4. Charalambous S, Kontopodis N, Papadakis AE, Ioannou CV, Tsetis D. Perfusion Digital Subtraction Angiography: Is it Time to Step Towards Functional Imaging of Endovascular Aneurysm Repair Patients? Eur J Vasc Endovasc Surg 2021;62(5):821–822 10.1016/j.ejvs.2021.07.018 PubMed

5. Raffort J, Adam C, Carrier M, et al. Artificial intelligence in abdominal aortic aneurysm. J Vasc Surg 2020;72(1):321–333.e1 10.1016/j.jvs.2019.12.026 PubMed

6. Ronneberger O, Fischer F, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015;abs/1505.04597. Accessed Mon, 13 Aug 2018 16:46:52 +0200. http://arxiv.org/abs/1505.04597

Publication History

Article published online:
10 June 2022

© 2022. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA