Purpose Mechanical thrombectomy (MT) is a time-critical intervention for acute ischemic stroke; however, access remains limited due to a shortage of neuroradiologists and specialized centers. Reinforcement learning (RL) offers potential to automate endovascular navigation and improve accessibility, yet current models lack standardized frameworks to assess navigation difficulty for model training and evaluation. This study aims to identify vascular metrics associated with navigation difficulty and to develop an automated pipeline for quantitative vascular feature extraction, enabling future complexity grading. Methods Vascular trees were segmented from computed tomography angiograms from 61 patients, and vascular metrics including aortic arch type, presence of bovine arch, vessel length, tortuosity, take-off angle, number of reverse curves were measured using a custom pipeline. A Soft Actor-Critic RL algorithm was used for 120 s autonomous navigation. Outcomes were analyzed using both mixed-effects linear and logistic regression . Results On the left side, the presence of a bovine arch and aortic arch type II/III increased the navigation time by 30.19 s and 37.92 s, respectively, while greater tortuosity (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">$\beta = 118.20$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>β</mi> <mo>=</mo> <mn>118.20</mn> </mrow> </math></EquationSource> </InlineEquation>) further prolonged the procedure and reduced success probability. On the right side, type II/III arches extended the procedure time by 45.94 s, while each additional reverse curve was associated with 3.96 s longer navigation time and lower probability of success . Conclusions These findings demonstrate for the first time that MT agent navigation difficulty is strongly influenced by vascular geometry. The proposed automated pipeline enables objective and quantitative characterization of vascular features, providing a foundation for future development of standardized complexity grading and RL model evaluation, without aiming to demonstrate clinically generalizable autonomous navigation. Our code for automated vascular metrics quantification is available at http://github.com/SurgicalDataScienceKCL/AI-VascularGeometryCharacterisation

Vascular geometry characterization for AI-based endovascular navigation

期刊论文
出版模式：

开放获取
发表日期：

2026年7月2日

查看全文

Han-Ru Wu,
Harry Robertshaw,
Lisa Dwyer-Joyce,
Thomas C Booth,
Alejandro Granados

摘要

Purpose

Mechanical thrombectomy (MT) is a time-critical intervention for acute ischemic stroke; however, access remains limited due to a shortage of neuroradiologists and specialized centers. Reinforcement learning (RL) offers potential to automate endovascular navigation and improve accessibility, yet current models lack standardized frameworks to assess navigation difficulty for model training and evaluation. This study aims to identify vascular metrics associated with navigation difficulty and to develop an automated pipeline for quantitative vascular feature extraction, enabling future complexity grading.

Methods

Vascular trees were segmented from computed tomography angiograms from 61 patients, and vascular metrics including aortic arch type, presence of bovine arch, vessel length, tortuosity, take-off angle, number of reverse curves were measured using a custom pipeline. A Soft Actor-Critic RL algorithm was used for 120 s autonomous navigation. Outcomes were analyzed using both mixed-effects linear and logistic regression .

Results

On the left side, the presence of a bovine arch and aortic arch type II/III increased the navigation time by 30.19 s and 37.92 s, respectively, while greater tortuosity ( $\beta = 118.20$ $β = 118.20$ ) further prolonged the procedure and reduced success probability. On the right side, type II/III arches extended the procedure time by 45.94 s, while each additional reverse curve was associated with 3.96 s longer navigation time and lower probability of success .

Conclusions

These findings demonstrate for the first time that MT agent navigation difficulty is strongly influenced by vascular geometry. The proposed automated pipeline enables objective and quantitative characterization of vascular features, providing a foundation for future development of standardized complexity grading and RL model evaluation, without aiming to demonstrate clinically generalizable autonomous navigation. Our code for automated vascular metrics quantification is available at http://github.com/SurgicalDataScienceKCL/AI-VascularGeometryCharacterisation