Spatio-temporal deep learning for automatic detection of intracranial vessel perforation in digital subtraction angiography during endovascular thrombectomy

Ruisheng Su (Corresponding author), Matthijs van der Sluijs, Sandra A.P. Cornelissen, Geert Lycklama, Jeannette Hofmeijer, Charles B.L.M. Majoie, Pieter Jan van Doormaal, Adriaan C.G.M. van Es, Danny Ruijters, Wiro J. Niessen, Aad van der Lugt, Theo van Walsum

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

13 Citaten (Scopus)
100 Downloads (Pure)

Samenvatting

Intracranial vessel perforation is a peri-procedural complication during endovascular therapy (EVT). Prompt recognition is important as its occurrence is strongly associated with unfavorable treatment outcomes. However, perforations can be hard to detect because they are rare, can be subtle, and the interventionalist is working under time pressure and focused on treatment of vessel occlusions. Automatic detection holds potential to improve rapid identification of intracranial vessel perforation. In this work, we present the first study on automated perforation detection and localization on X-ray digital subtraction angiography (DSA) image series. We adapt several state-of-the-art single-frame detectors and further propose temporal modules to learn the progressive dynamics of contrast extravasation. Application-tailored loss function and post-processing techniques are designed. We train and validate various automated methods using two national multi-center datasets (i.e., MR CLEAN Registry and MR CLEAN-NoIV Trial), and one international multi-trial dataset (i.e., the HERMES collaboration). With ten-fold cross-validation, the proposed methods achieve an area under the curve (AUC) of the receiver operating characteristic of 0.93 in terms of series level perforation classification. Perforation localization precision and recall reach 0.83 and 0.70 respectively. Furthermore, we demonstrate that the proposed automatic solutions perform at similar level as an expert radiologist.

Originele taal-2Engels
Artikelnummer102377
Aantal pagina's14
TijdschriftMedical Image Analysis
Volume77
DOI's
StatusGepubliceerd - apr. 2022

Bibliografische nota

Copyright © 2022 The Author(s). Published by Elsevier B.V. All rights reserved.

Financiering

The authors would like to thank the MR CLEAN Registry investigators, MR CLEAN NoIV investigators, and the HERMES collaboration investigators (including MR CLEAN, ESCAPE, REVASCAT, SWIFT PRIME, THRACE, EXTEND-IA, and PISTE randomized controlled trials) for sharing the DSA image data. The MR CLEAN Registry was funded and carried out by the Erasmus University Medical Centre, Amsterdam UMC location AMC, and Maastricht University Medical Centre. The study was additionally funded by the Applied Scientific Institute for Neuromodulation (Toegepast Wetenschappelijk Instituut voor Neuromodulatie). MR CLEAN NoIV study was performed in the framework of the CONTRAST consortium which acknowledges the support from the Netherlands Cardiovascular Research Initiative, an initiative of the Dutch Heart Foundation (CVON2015-01: CONTRAST), and from the Brain Foundation Netherlands (HA2015.01.06). The collaboration project is additionally financed by the Ministry of Economic Affairs by means of the PPP Allowance made available by the Top Sector Life Sciences & Health to stimulate public-private partnerships (LSHM17016). This work was funded in part through unrestricted funding by Stryker, Medtronic and Cerenovus. The current work on perforation detection was supported by Health-Holland (TKI Life Sciences and Health) through the Q-Maestro project under Grant EMCLSH19006 and Philips Healthcare (Best, The Netherlands). The authors would like to thank the MR CLEAN Registry investigators, MR CLEAN NoIV investigators, and the HERMES collaboration investigators (including MR CLEAN, ESCAPE, REVASCAT, SWIFT PRIME, THRACE, EXTEND-IA, and PISTE randomized controlled trials) for sharing the DSA image data. The MR CLEAN Registry was funded and carried out by the Erasmus University Medical Centre, Amsterdam UMC location AMC, and Maastricht University Medical Centre. The study was additionally funded by the Applied Scientific Institute for Neuromodulation (Toegepast Wetenschappelijk Instituut voor Neuromodulatie). MR CLEAN NoIV study was performed in the framework of the CONTRAST consortium which acknowledges the support from the Netherlands Cardiovascular Research Initiative, an initiative of the Dutch Heart Foundation (CVON2015-01: CONTRAST), and from the Brain Foundation Netherlands (HA2015.01.06). The collaboration project is additionally financed by the Ministry of Economic Affairs by means of the PPP Allowance made available by the Top Sector Life Sciences & Health to stimulate public-private partnerships (LSHM17016). This work was funded in part through unrestricted funding by Stryker, Medtronic and Cerenovus. The current work on perforation detection was supported by Health-Holland (TKI Life Sciences and Health) through the Q-Maestro project under Grant EMCLSH19006 and Philips Healthcare (Best, The Netherlands).

FinanciersFinanciernummer
Erasmus Medical Center
Maastricht University Medical Center
Ministerie van Economische Zaken en KlimaatLSHM17016

    Vingerafdruk

    Duik in de onderzoeksthema's van 'Spatio-temporal deep learning for automatic detection of intracranial vessel perforation in digital subtraction angiography during endovascular thrombectomy'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit