Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Artificial Intelligence in the Autonomous Navigation of Endovascular Interventions: A Systematic Review

Harry Robertshaw, Lennart Karstensen, Benjamin Jackson, Hadi Sadati, Kawal Rhode, Sebastien Ourselin, Alejandro Granados, Thomas C Booth

TL;DR

This systematic review evaluates AI-enabled autonomous navigation of catheters and guidewires in endovascular interventions. It finds that reinforcement learning dominates the literature (primarily in vitro/in silico studies with phantom vasculature) and notes a lack of clinical validation, standardized reference standards, and consistent performance metrics, placing the field at roughly technology readiness level 3. The authors emphasize the need for standardized benchmarks and reporting to enable meaningful comparisons and guide translational progress toward clinical use. They also call for regulatory considerations and a staged approach (level 1–3 autonomy) to safely advance autonomous endovascular navigation.

Abstract

Purpose: Autonomous navigation of devices in endovascular interventions can decrease operation times, improve decision-making during surgery, and reduce operator radiation exposure while increasing access to treatment. This systematic review explores recent literature to assess the impact, challenges, and opportunities artificial intelligence (AI) has for the autonomous endovascular intervention navigation. Methods: PubMed and IEEEXplore databases were queried. Eligibility criteria included studies investigating the use of AI in enabling the autonomous navigation of catheters/guidewires in endovascular interventions. Following PRISMA, articles were assessed using QUADAS-2. PROSPERO: CRD42023392259. Results: Among 462 studies, fourteen met inclusion criteria. Reinforcement learning (9/14, 64%) and learning from demonstration (7/14, 50%) were used as data-driven models for autonomous navigation. Studies predominantly utilised physical phantoms (10/14, 71%) and in silico (4/14, 29%) models. Experiments within or around the blood vessels of the heart were reported by the majority of studies (10/14, 71%), while simple non-anatomical vessel platforms were used in three studies (3/14, 21%), and the porcine liver venous system in one study. We observed that risk of bias and poor generalisability were present across studies. No procedures were performed on patients in any of the studies reviewed. Studies lacked patient selection criteria, reference standards, and reproducibility, resulting in low clinical evidence levels. Conclusions: AI's potential in autonomous endovascular navigation is promising, but in an experimental proof-of-concept stage, with a technology readiness level of 3. We highlight that reference standards with well-identified performance metrics are crucial to allow for comparisons of data-driven algorithms proposed in the years to come.

Artificial Intelligence in the Autonomous Navigation of Endovascular Interventions: A Systematic Review

TL;DR

This systematic review evaluates AI-enabled autonomous navigation of catheters and guidewires in endovascular interventions. It finds that reinforcement learning dominates the literature (primarily in vitro/in silico studies with phantom vasculature) and notes a lack of clinical validation, standardized reference standards, and consistent performance metrics, placing the field at roughly technology readiness level 3. The authors emphasize the need for standardized benchmarks and reporting to enable meaningful comparisons and guide translational progress toward clinical use. They also call for regulatory considerations and a staged approach (level 1–3 autonomy) to safely advance autonomous endovascular navigation.

Abstract

Purpose: Autonomous navigation of devices in endovascular interventions can decrease operation times, improve decision-making during surgery, and reduce operator radiation exposure while increasing access to treatment. This systematic review explores recent literature to assess the impact, challenges, and opportunities artificial intelligence (AI) has for the autonomous endovascular intervention navigation. Methods: PubMed and IEEEXplore databases were queried. Eligibility criteria included studies investigating the use of AI in enabling the autonomous navigation of catheters/guidewires in endovascular interventions. Following PRISMA, articles were assessed using QUADAS-2. PROSPERO: CRD42023392259. Results: Among 462 studies, fourteen met inclusion criteria. Reinforcement learning (9/14, 64%) and learning from demonstration (7/14, 50%) were used as data-driven models for autonomous navigation. Studies predominantly utilised physical phantoms (10/14, 71%) and in silico (4/14, 29%) models. Experiments within or around the blood vessels of the heart were reported by the majority of studies (10/14, 71%), while simple non-anatomical vessel platforms were used in three studies (3/14, 21%), and the porcine liver venous system in one study. We observed that risk of bias and poor generalisability were present across studies. No procedures were performed on patients in any of the studies reviewed. Studies lacked patient selection criteria, reference standards, and reproducibility, resulting in low clinical evidence levels. Conclusions: AI's potential in autonomous endovascular navigation is promising, but in an experimental proof-of-concept stage, with a technology readiness level of 3. We highlight that reference standards with well-identified performance metrics are crucial to allow for comparisons of data-driven algorithms proposed in the years to come.
Paper Structure (22 sections, 2 figures, 3 tables)

This paper contains 22 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Selection criteria
  4. Eligibility criteria
  5. Information sources and search strategy
  6. Selection and data collection process
  7. Data items, effect measures and synthesis methods
  8. Study risk of bias, reporting bias and certainty assessment
  9. Results
  10. Studies
  11. AI models
  12. RL methods
  13. Other ML types
  14. Level of autonomy
  15. Experimental design
  16. ...and 7 more sections

Figures (2)

  • Figure 1: Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) flow diagram showing the number of articles searched and excluded at each stage of the literature search after screening titles, abstracts, and full texts.
  • Figure 2: Diagram depicting the general vessels of interest for each study. *Study is in more than one area. Studies using non-anatomical platforms are also shown.