Article Text
PDF
Abstract
Background In mechanical thrombectomy (MT), extracranial vascular tortuosity is among the main determinants of procedure duration and success. Currently, no rapid and reliable method exists to identify the anatomical features precluding fast and stable access to the cervical vessels.
Methods A retrospective sample of 513 patients were included in this study. Patients underwent first-line transfemoral MT following anterior circulation large vessel occlusion stroke. Difficult transfemoral access (DTFA) was defined as impossible common carotid catheterization or time from groin puncture to first carotid angiogram >30 min. A machine learning model based on 29 anatomical features automatically extracted from head-and-neck computed tomography angiography (CTA) was developed to predict DTFA. Three experienced raters independently assessed the likelihood of DTFA on a reduced cohort of 116 cases using a Likert scale as benchmark for the model, using preprocedural CTA as well as automatic 3D vascular segmentation separately.
Results Among the study population, 11.5% of procedures (59/513) presented DTFA. Six different features from the aortic, supra-aortic, and cervical regions were included in the model. Cross-validation resulted in an area under the receiver operating characteristic (AUROC) curve of 0.76 (95% CI 0.75 to 0.76) for DTFA prediction, with high sensitivity for impossible access identification (0.90, 95% CI 0.81 to 0.94). The model outperformed human assessment in the reduced cohort [F1-score (95% CI) by experts with CTA: 0.43 (0.37 to 0.50); experts with 3D segmentation: 0.50 (0.46 to 0.54); and model: 0.70 (0.65 to 0.75)].
Conclusions A fully automatic model for DTFA prediction was developed and validated. The presented method improved expert assessment of difficult access prediction in stroke MT. Derived information could be used to guide decisions regarding arterial access for MT.
- Stroke
- Thrombectomy
- Artery
- Catheter
- CT Angiography
Data availability statement
Data used for this study were accepted for internal use by the local institutional review board, and is not publicly available. It may, however, be made available upon reasonable request.
Statistics from Altmetric.com
Data availability statement
Data used for this study were accepted for internal use by the local institutional review board, and is not publicly available. It may, however, be made available upon reasonable request.
Footnotes
X @pere_canals_, @marcriboj
Contributors PC: study design, data acquisition, data analysis, data interpretation, manuscript preparation, guarantor. MRe: data analysis. MJ: data analysis. AG-T: study design, data analysis, data interpretation, draft revision. JL: data analysis. SB: automatic feature extraction tool design, draft revision. OD: automatic feature extraction tool design, draft revision. AT: data acquisition. MRi: study design, data analysis, data interpretation, draft revision. AI was used for minimal paraphrasing modifications to improve the quality of the language. Use was anecdotic, and practically the entirety of all text was written by humans.
Funding This work was partially supported by the Catalan Health Department (Departament de Salut, Generalitat de Catalunya) with a predoctoral scholarship (PERIS PIF-Salut 2021, grant number SLT017/20/000180) and the Spanish Health Institute Carlos III (Instituto de Salud Carlos III, Ministerio de Ciencia e Innovación, Gobierno de España) with a PI21 grant (PI21/01967).
Competing interests The code used for the present study is stored in the private repository of the Universitat de Barcelona (Barcelona, Spain) (http://diposit.ub.edu/dspace/handle/2445/180158) and is registered for copyright protection on the Safe Creative platform (registry number: 2109279362548) under the title of "ARTERI-AL: an AI framework for stroke operation planning through the automated characterization of vascular tortuosity". AT reports receiving consulting fees from Anaconda Biomed, Balt, Medtronic, MicroVention, Cerus, Merlin Medical, and Stryker. AG-T received consulting fees from Apta Targets. MRi received research funding from Medtronic and Vesalio. MRi declares ownership of Anaconda Biomed and Methinks shares. MRi received consulting fees from Anaconda Biomed, Apta Targets, Medtronic, Stryker, Cerenovus, and Philips.
Provenance and peer review Not commissioned; externally peer reviewed.
Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.