Learning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions

Computers in Biology and Medicine, vol. 196, pp. 110844

Abstract

Endovascular interventions are a life-saving treatment for many diseases, but they suffer from drawbacks such as radiation exposure and the potential scarcity of proficient physicians. Robotic assistance during these interventions could be a promising support for these problems. Research focusing on autonomous endovascular interventions using artificial intelligence-based methodologies is gaining popularity. However, variability in assessment environments hinders the comparability of different approaches, primarily due to each study employing a unique evaluation framework. In this study, we present autonomous endovascular instrument navigation based on deep reinforcement learning for three distinct digital benchmark interventions: BasicWireNav, ArchVariety, and DualDeviceNav. The benchmarks focus on aortic arch to supra-aortic navigation, representing fundamental large-vessel navigation skills. The benchmark interventions were implemented with our modular simulation framework stEVE (simulated EndoVascular Environment). Autonomous controllers were trained solely in simulation and evaluated in simulation and on physical test benches with camera and fluoroscopy feedback. Autonomous control for BasicWireNav and ArchVariety reached success rates up to 98/100 in simulation and was successfully transferred to the physical test benches with a success rate of up to 97/100. The experiments demonstrate the feasibility of stEVE and its potential to transfer simulation-trained controllers to real-world scenarios. However, they also reveal areas that offer opportunities for future research. Furthermore, this work reduces barriers to entry and increases the comparability of research on learning-based assistance systems for endovascular navigation by providing open-source training scripts, benchmarks, and the stEVE framework. • Novel benchmark environments for autonomous endovascular navigation using stEVE. • Successful simulation-to-reality transfer with 98% to 97% success rate. • Multi-instrument coordination challenges identified in DualDeviceNav benchmark. • Open-source framework enables reproducible endovascular robotics research. • Reward design ablation shows two-component combinations accelerate learning.

Authors 10

1. Lennart Karstensen

   Friedrich-Alexander-Universität Erlangen-Nürnberg

   Affiliation as printed

   Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University, Erlangen, 91052, Germany

2. Johannes Hatzl

   Heidelberg University · University Hospital Heidelberg

   Affiliation as printed

   Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, Heidelberg, 69120, Germany

3. Benjamin M. Jackson

   King's College London

   Affiliation as printed

   School of Biomedical Engineering and Imaging Sciences, King's College London, London, WC2R 2LS, United Kingdom

4. Jens Langejürgen

   Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Clinical Health Technologies, Fraunhofer IPA, Mannheim, 68167, Germany

5. Katharina Breininger

   Friedrich-Alexander-Universität Erlangen-Nürnberg · University of Würzburg

   Affiliation as printed

   Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University, Erlangen, 91052, Germany; Center for AI and Data Science, Julius-Maximilians-Universität Würzburg, Würzburg, 97074, Germany

6. Christian Uhl Aachen Department of Vascular Surgery

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Department of Vascular Surgery, University Hospital RWTH Aachen, Aachen, 52074, Germany

7. Seyed Mohammad Hadi Sadati

   King's College London

   Affiliation as printed

   School of Biomedical Engineering and Imaging Sciences, King's College London, London, WC2R 2LS, United Kingdom

8. Thomas Calvert Booth

   King's College London · King's College Hospital

   Affiliation as printed

   School of Biomedical Engineering and Imaging Sciences, King's College London, London, WC2R 2LS, United Kingdom; Department of Neuroradiology, Kings College Hospital, Ruskin Wing, London, SE5 9RS, United Kingdom

9. Christos Bergeles

   King's College London

   Affiliation as printed

   School of Biomedical Engineering and Imaging Sciences, King's College London, London, WC2R 2LS, United Kingdom

10. Franziska Mathis-Ullrich corresponding

    Friedrich-Alexander-Universität Erlangen-Nürnberg

    Affiliation as printed

    Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University, Erlangen, 91052, Germany. Electronic address: franziska.mathis-ullrich@fau.de