You are here

Article Text

Article menu
Vascular neurology
Diagnostic performance of an algorithm for automated large vessel occlusion detection on CT angiography
  1. Sven P R Luijten1,
  2. Lennard Wolff1,
  3. Martijne H C Duvekot2,3,
  4. Pieter-Jan van Doormaal1,
  5. Walid Moudrous4,
  6. Henk Kerkhoff3,
  7. Geert J Lycklama a Nijeholt5,
  8. Reinoud P H Bokkers6,
  9. Lonneke S F Yo7,
  10. Jeannette Hofmeijer8,
  11. Wim H van Zwam9,
  12. Adriaan C G M van Es10,
  13. Diederik W J Dippel2,
  14. Bob Roozenbeek1,2,
  15. Aad van der Lugt1
  16. on behalf of the MR CLEAN Registry and PRESTO investigators
    1. 1 Radiology & Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, The Netherlands
    2. 2 Neurology, Erasmus MC University Medical Center, Rotterdam, The Netherlands
    3. 3 Neurology, Albert Schweitzer Hospital, Dordrecht, The Netherlands
    4. 4 Neurology, Maasstad Ziekenhuis, Rotterdam, Zuid-Holland, The Netherlands
    5. 5 Radiology, HMC Westeinde, Den Haag, Zuid-Holland, The Netherlands
    6. 6 Radiology, University Medical Center Groningen, Groningen, The Netherlands
    7. 7 Radiology, Catharina Hospital, Eindhoven, The Netherlands
    8. 8 Neurology, Rijnstate Hospital, Arnhem, The Netherlands
    9. 9 Radiology, Maastricht University Medical Center, Maastricht, The Netherlands
    10. 10 Radiology, Leiden University Medical Center, Leiden, Zuid-Holland, The Netherlands
    1. Correspondence to Dr Sven P R Luijten, Radiology & Nuclear Medicine, Erasmus Medical Center, Rotterdam, Netherlands; s.luijten{at}erasmusmc.nl

    Abstract

    Background Machine learning algorithms hold the potential to contribute to fast and accurate detection of large vessel occlusion (LVO) in patients with suspected acute ischemic stroke. We assessed the diagnostic performance of an automated LVO detection algorithm on CT angiography (CTA).

    Methods Data from the MR CLEAN Registry and PRESTO were used including patients with and without LVO. CTA data were analyzed by the algorithm for detection and localization of LVO (intracranial internal carotid artery (ICA)/ICA terminus (ICA-T), M1, or M2). Assessments done by expert neuroradiologists were used as reference. Diagnostic performance was assessed for detection of LVO and per occlusion location by means of sensitivity, specificity, and area under the curve (AUC).

    Results We analyzed CTAs of 1110 patients from the MR CLEAN Registry (median age (IQR) 71 years (60–80); 584 men; 1110 with LVO) and of 646 patients from PRESTO (median age (IQR) 73 years (62–82); 358 men; 141 with and 505 without LVO). For detection of LVO, the algorithm yielded a sensitivity of 89% in the MR CLEAN Registry and a sensitivity of 72%, specificity of 78%, and AUC of 0.75 in PRESTO. Sensitivity per occlusion location was 88% for ICA/ICA-T, 94% for M1, and 72% for M2 occlusion in the MR CLEAN Registry, and 80% for ICA/ICA-T, 95% for M1, and 49% for M2 occlusion in PRESTO.

    Conclusion The algorithm provided a high detection rate for proximal LVO, but performance varied significantly by occlusion location. Detection of M2 occlusion needs further improvement.

    • CT Angiography
    • stroke
    • thrombectomy

    Data availability statement

    No data are available. Individual participant data cannot be made available, as no patient approval has been obtained for sharing coded data. However, analytical methods such as the R syntax and output files of the analyses will be made available on request.

    http://creativecommons.org/licenses/by-nc/4.0/

    This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.

    https://doi.org/10.1136/neurintsurg-2021-017842

    Statistics from Altmetric.com

      Request Permissions

      If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

      Data availability statement

      No data are available. Individual participant data cannot be made available, as no patient approval has been obtained for sharing coded data. However, analytical methods such as the R syntax and output files of the analyses will be made available on request.

      View Full Text

      Supplementary materials

      • Supplementary Data

        This web only file has been produced by the BMJ Publishing Group from an electronic file supplied by the author(s) and has not been edited for content.

      • Supplementary Data

        This web only file has been produced by the BMJ Publishing Group from an electronic file supplied by the author(s) and has not been edited for content.

      Footnotes

      • SPRL and LW contributed equally.

      • Collaborators MR CLEAN Registry and PRESTO Investigators: Robert J van Oostenbrugge; Jelis Boiten; Charles B.L.M. Majoie; Yvo BWEM Roos; Jan Albert Vos; Ivo GH Jansen; Maxim JHL Mulder; Robert-Jan B Goldhoorn; Kars CJ Compagne; Manon Kappelhof; Wouter J Schonewille; Jonathan M Coutinho; Marieke JH Wermer; Marianne AA van Walderveen; Julie Staals; Jasper M Martens; Bart J Emmer; Sebastiaan F de Bruijn; Lukas C van Dijk; Bart van der Worp; Rob H Lo; Ewoud J van Dijk; Hieronymus D Boogaarts; Paul LM de Kort; Julia van Tuijl; Jo JP Peluso; Jan SP van den Berg; Boudewijn AAM van Hasselt; Leo AM Aerden; René J Dallinga; Maarten Uyttenboogaart; Omid Eshghi; Tobien HCML Schreuder; Roel JJ Heijboer; Koos Keizer; Heleen M den Hertog; Emiel JC Sturm; Marieke ES Sprengers; Sjoerd FM Jenniskens; René van den Berg; Albert J Yoo; Ludo FM Beenen; Alida A Postma; Stefan D Roosendaal; Bas FW van der Kallen; Ido R van den Wijngaard; Joost Bot, Pieter-Jan van Doormaal; Zwenneke Flach; Hester F Lingsma; Naziha el Ghannouti; Martin Sterrenberg; Corina Puppels; Wilma Pellikaan; Rita Sprengers; Marjan Elfrink; Joke de Meris;Tamara Vermeulen; Annet Geerlings; Gina van Vemde; Tiny Simons; Cathelijn van Rijswijk; Gert Messchendorp; Hester Bongenaar; Karin Bodde; Sandra Kleijn; Jasmijn Lodico; Hanneke Droste; M Wollaert; D Jeurrissen; Ernas Bos; Yvonne Drabbe; Nicoline Aaldering; Berber Zweedijk; Mostafa Khalilzada; Esmee Venema; Vicky Chalos; Ralph R Geuskens; Tim van Straaten; Saliha Ergezen; Roger RM Harmsma; Daan Muijres; Anouk de Jong; Wouter Hinsenveld; Olvert A Berkhemer; J Huguet; PFC Groot; Marieke A Mens; Katinka R Kranendonk; Kilian M Treurniet; Manon L Tolhuijsen; Heitor Alves; Anouk D Rozeman; Frédérique H. Vermeij; Kees CL Alblas; Laus JMM Mulder; Annemarie D Wijnhoud; Lisette Maasland; Roeland PJ van Eijkelenburg; Marileen Biekart; ML Willeboer; Bianca Buijck; Jeannette Bakker; Jan-Hein Hensen, Aarnout Plaisier; Amber Hoek; Erick Oskam; Mandy MA van der Zon; Egon D Zwets; Jan Willem Kuiper; Bruno JM van Moll; Mirjam Woudenberg; Arnoud M de Leeuw; Anja Noordam-Reijm; Timo Bevelander; Vicky Chalos; Eveline JA Wiegers; Dennis C van Kalkeren; Jochem van den Biggelaar

      • Contributors SPRL, LW and AvdL were responsible for study concept and design. SPRL, LW, AvdL, MHCD, PJvD, WM, HK, GJLaN, RPHB, LSFY, JH, WHvZ, ACGMvE, DWJD, BR were responsible for or contributed to data acquisition. SPRL, LW and AvdL were responsible for analysis and interpretation of the data and drafting the manuscript. MHCD, PJvD, WM, HK, GJLaN, RPHB, LSFY, JH, WHvZ, ACGMvE, DWJD, BR were responsible for critical revision of the manuscript.

      • Funding The MR CLEAN Registry was partly funded by TWIN Foundation, Erasmus MC University Medical Center, Maastricht University Medical Center, and Amsterdam University Medical Center. PRESTO was funded by BeterKeten Collaboration and Theia Foundation (Zilveren Kruis).

      • Competing interests WHvZ reports grants from Stryker and Cerenovus, all paid to the institution. DWJD reports funding from the Dutch Heart Foundation, Brain Foundation Netherlands, The Netherlands Organisation for Health Research and Development, Health Holland Top Sector Life Sciences and Health, and unrestricted grants from Penumbra, Stryker, Medtronic, Thrombolytic Science, LLC, and Cerenovus, all paid to the institution. AvdL reports grants from Penumbra, Stryker, Cerenovus, and Medtronic, all paid to the institution.

      • 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.