[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82210-en":3,"doc-seo-82210-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82210,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Vascular Geometry Characterization for AI-Based Endovascular Navigation","Mechanical thrombectomy (MT) for acute ischemic stroke requires timely access, yet endovascular navigation remains difficult to standardize for reinforcement learning (RL) because no consistent framework quantifies navigation difficulty. Vascular trees were segmented from computed tomography angiograms of 61 patients, and metrics such as aortic arch type, bovine arch presence, vessel length, tortuosity, take-off angle, and reverse curves were measured using a custom automated pipeline. A Soft Actor-Critic agent performed 120 s autonomous navigation. Mixed-effects regressions showed geometry-driven increases in time and reduced success probability, supporting future standardized complexity grading and RL evaluation.","VASCULAR GEOMETRY CHARACTERIZATION FOR AI–BASED  \nENDOVASCULAR NAVIGATION ∗  \nHan-Ru Wu†  \nDepartment of Medical Imaging Science National Taiwan University Hospital Taiwan  \nHarry Robertshaw†, Thomas C. Booth, Alejandro Granados‡  \nSurgical & Interventional Engineering School of Biomedical Engineering & Imaging Sciences Kings College London  \nUK  \narXiv :2607 .09130v1 [ cs .RO] 10 Jul 2026  \nLisa Dwyer-Joyce  \nChelsea & Westminster Hospital  \nUK  \nABSTRACT  \nPurpose: Mechanical thrombectomy (MT) is a time-critical intervention for acute ischemic stroke;  \nhowever, access remains limited due to a shortage of neuroradiologists and specialized centers.  \nReinforcement 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.  \nOutcomes 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 navigation time by 30.19 sand 37.92 s, respectively, while greater tortuosity (β = 118 .20) further prolonged the procedure and reduced success probability. On the right side, type II/III arches extended 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. Conclusion: 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  \n1 Introduction  \nMechanical thrombectomy (MT) is now an established gold-standard treatment for large-vessel occlusions in acute ischemic stroke, the second leading cause of death worldwide [1, 2] . However, timely access to MT remains uneven, particularly in rural and remote regions [3] . As a result, AI-driven strategies, especially reinforcement learning (RL), have been proposed to support and potentially automate endovascular navigation during MT [4] . Despite the growing  \n∗  Citation: Wu, HR., Robertshaw, H., Dwyer-Joyce, L. et al. Vascular geometry characterization for AI-based endovascular navigation. Int J CARS (2026). [https://doi.org/10.1007/s11548-026-03742-9](https://doi.org/10.1007/s11548-026-03742-9)  \n†Equal contribution  \n‡Corresponding author: [alejandro.granados@kcl.ac.uk](alejandro.granados@kcl.ac.uk)  \nVascular Geometry Characterization for AI–Based Endovascular Navigation  \npopularity of RL-based approaches in endovascular navigation, the lack of standardized vascular metric quantification limits the ability to effectively compare models [5] . This limitation is further compounded by the fact that many existing open-source benchmarks rely on simplified vessel geometries. Consequently, the establishment of an automated and standardized vascular geometry quantification pipeline is crucial for advancing the field.  \nReinforcement learning has increasingly been applied to robotic control and autonomous navigation ta","cbCaishYnShYOijT","https://ap.wps.com/l/cbCaishYnShYOijT","pdf",4009631,1,10,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does the study address in AI-based endovascular navigation?\",\"answer\":\"The study targets the lack of standardized vascular metrics to quantify navigation difficulty for training and evaluating reinforcement learning models in mechanical thrombectomy.\"},{\"question\":\"How were vascular features measured for the analysis?\",\"answer\":\"Vascular trees were segmented from CT angiograms of 61 patients, and metrics including aortic arch type, bovine arch presence, vessel length, tortuosity, take-off angle, and reverse curves were quantified using a custom pipeline.\"},{\"question\":\"Which vascular geometry factors were linked to longer navigation time and lower success?\",\"answer\":\"On the left side, bovine arch presence and aortic arch type II/III increased navigation time, while greater tortuosity prolonged procedures and reduced success probability. On the right side, type II/III arches extended time, and additional reverse curves increased time and lowered success probability.\"}]",1784178834,25,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"vascular-geometry-characterization-for-ai-based-endovascular-navigation","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/vascular-geometry-characterization-for-ai-based-endovascular-navigation/82210/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the study address in AI-based endovascular navigation?","Question",{"text":74,"@type":75},"The study targets the lack of standardized vascular metrics to quantify navigation difficulty for training and evaluating reinforcement learning models in mechanical thrombectomy.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How were vascular features measured for the analysis?",{"text":79,"@type":75},"Vascular trees were segmented from CT angiograms of 61 patients, and metrics including aortic arch type, bovine arch presence, vessel length, tortuosity, take-off angle, and reverse curves were quantified using a custom pipeline.",{"name":81,"@type":72,"acceptedAnswer":82},"Which vascular geometry factors were linked to longer navigation time and lower success?",{"text":83,"@type":75},"On the left side, bovine arch presence and aortic arch type II/III increased navigation time, while greater tortuosity prolonged procedures and reduced success probability. On the right side, type II/III arches extended time, and additional reverse curves increased time and lowered success probability.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":21,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]