Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Reporting transparency in veterinary pathology deep learning: A systematic review of reproducibility-critical details.

Veterinary pathology·2026

Same author

Data set creation for supervised deep learning-based analysis of microscopic images: Review of important considerations and recommendations.

Veterinary pathology·2026

Same author

Comparison of endovascular procedures of the lower extremities and iliac arteries with and without navigation assistance Vascular Navigation PAD: study protocol for a prospective multicenter randomized clinical trial.

Trials·2026

Same author

10-Butyl Ether Minocycline (BEM) Reduced Ethanol Consumption in Binge Drinking Mice.

Alcoholism treatment quarterly·2026

Same author

Streamlining stereo-differentiable rendering for marker-free real-time tracking of surgical robots.

International journal of computer assisted radiology and surgery·2026

Same author

Chromosome-level genomes of scleractinian corals: gene prediction and functional annotation.

Scientific data·2026

Same journal

A computational model of chemically- and mechanically-induced thrombus formation in cerebral aneurysms.

Computers in biology and medicine·2026

Same journal

An improved catch fish optimization based deep learning model for Parkinson disease classification using EEG signal.

Computers in biology and medicine·2026

Same journal

Assessing the robustness of evaluation metrics for synthetic ECG signal quality.

Computers in biology and medicine·2026

Same journal

Integrating stemness and epithelial-mesenchymal transition signatures with machine learning identifies RUNX1 as a therapeutic vulnerability in colorectal cancer.

Computers in biology and medicine·2026

Same journal

Differential regional textural attributes of tongue in normal and acidity patients in the light of traditional Chinese medicine.

Computers in biology and medicine·2026

Same journal

SC-MSDNet: Spatial-consistent multi-view self-distillation for retinal OCT classification.

Computers in biology and medicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 11, 2025

Simulator Training for Endovascular Neurosurgery

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

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

Lennart Karstensen¹, Harry Robertshaw², Johannes Hatzl³

¹Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University, Erlangen, 91052, Germany.

Computers in Biology and Medicine

|August 15, 2025

Summary

This summary is machine-generated.

Autonomous robotic navigation for endovascular interventions shows high success rates. This AI-driven approach, using the stEVE framework, transfers simulation training to real-world scenarios, improving safety and physician training.

Keywords:

Autonomous navigation Benchmark environments Endovascular robotics Learning-based control Simulation to reality

More Related Videos

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Related Experiment Videos

Last Updated: Sep 11, 2025

Simulator Training for Endovascular Neurosurgery

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Area of Science:

Medical Robotics
Artificial Intelligence in Medicine
Endovascular Surgery

Background:

Endovascular interventions are critical but face challenges like radiation exposure and limited physician expertise.
Robotic assistance and AI-driven autonomous systems offer potential solutions to these limitations.
Current research lacks standardized assessment environments, hindering comparability of different AI approaches.

Purpose of the Study:

To present an AI-based system for autonomous endovascular instrument navigation.
To introduce three distinct digital benchmark interventions (BasicWireNav, ArchVariety, DualDeviceNav) for evaluating navigation skills.
To demonstrate the feasibility of transferring simulation-trained AI controllers to physical test benches.

Main Methods:

Developed autonomous endovascular instrument navigation using deep reinforcement learning.
Implemented three benchmark interventions within the modular simulation framework, stEVE (simulated EndoVascular Environment).
Trained AI controllers exclusively in simulation and evaluated their performance in both simulated and physical environments using camera and fluoroscopy feedback.

Main Results:

Achieved high success rates for autonomous control in BasicWireNav and ArchVariety benchmarks, up to 98/100 in simulation.
Successfully transferred simulation-trained controllers to physical test benches, reaching success rates up to 97/100.
Demonstrated the feasibility of the stEVE framework for training and real-world transfer of autonomous navigation controllers.

Conclusions:

The study validates the potential of AI-driven autonomous navigation in endovascular interventions.
The stEVE framework and open-source resources facilitate research and improve comparability of learning-based assistance systems.
This work reduces barriers to entry for developing and testing AI for endovascular navigation.