DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy

dc.contributor.authorKelly, Brendan
dc.contributor.authorMartinez, Mesha
dc.contributor.authorDo, Huy
dc.contributor.authorHayden, Joel
dc.contributor.authorHuang, Yuhao
dc.contributor.authorYedavalli, Vivek
dc.contributor.authorHo, Chang
dc.contributor.authorKeane, Pearse A.
dc.contributor.authorKilleen, Ronan
dc.contributor.authorLawlor, Aonghus
dc.contributor.authorMoseley, Michael E.
dc.contributor.authorYeom, Kristen W.
dc.contributor.authorLee, Edward H.
dc.contributor.departmentRadiology and Imaging Sciences, School of Medicine
dc.date.accessioned2024-02-14T14:01:05Z
dc.date.available2024-02-14T14:01:05Z
dc.date.issued2023
dc.description.abstractObjectives: Treatment and outcomes of acute stroke have been revolutionised by mechanical thrombectomy. Deep learning has shown great promise in diagnostics but applications in video and interventional radiology lag behind. We aimed to develop a model that takes as input digital subtraction angiography (DSA) videos and classifies the video according to (1) the presence of large vessel occlusion (LVO), (2) the location of the occlusion, and (3) the efficacy of reperfusion. Methods: All patients who underwent DSA for anterior circulation acute ischaemic stroke between 2012 and 2019 were included. Consecutive normal studies were included to balance classes. An external validation (EV) dataset was collected from another institution. The trained model was also used on DSA videos post mechanical thrombectomy to assess thrombectomy efficacy. Results: In total, 1024 videos comprising 287 patients were included (44 for EV). Occlusion identification was achieved with 100% sensitivity and 91.67% specificity (EV 91.30% and 81.82%). Accuracy of location classification was 71% for ICA, 84% for M1, and 78% for M2 occlusions (EV 73, 25, and 50%). For post-thrombectomy DSA (n = 194), the model identified successful reperfusion with 100%, 88%, and 35% for ICA, M1, and M2 occlusion (EV 89, 88, and 60%). The model could also perform classification of post-intervention videos as mTICI < 3 with an AUC of 0.71. Conclusions: Our model can successfully identify normal DSA studies from those with LVO and classify thrombectomy outcome and solve a clinical radiology problem with two temporal elements (dynamic video and pre and post intervention).
dc.eprint.versionFinal published version
dc.identifier.citationKelly B, Martinez M, Do H, et al. DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy. Eur Radiol. 2023;33(8):5728-5739. doi:10.1007/s00330-023-09478-3
dc.identifier.urihttps://hdl.handle.net/1805/38478
dc.language.isoen_US
dc.publisherSpringer
dc.relation.isversionof10.1007/s00330-023-09478-3
dc.relation.journalEuropean Radiology
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.sourcePMC
dc.subjectRadiology
dc.subjectDeep learning
dc.subjectStroke
dc.subjectAngiography
dc.subjectThrombectomy
dc.titleDEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
330_2023_Article_9478.pdf
Size:
1.27 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.99 KB
Format:
Item-specific license agreed upon to submission
Description: