Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Evaluation of CINA® LVO artificial intelligence software for detection of large vessel occlusion in brain CT angiography

Mellander, Helena LU orcid ; Hillal, Amir LU ; Ullberg, Teresa LU and Wassélius, Johan LU (2024) In European Journal of Radiology Open 12.
Abstract

Objective: To systematically evaluate the ability of the CINA® LVO software to detect large vessel occlusions eligible for mechanical thrombectomy on CTA using conventional neuroradiological assessment as gold standard. Methods: Retrospectively, two hundred consecutive patients referred for a brain CTA and two hundred patients that had been subject for endovascular thrombectomy, with an accessible preceding CTA, were assessed for large vessel occlusions (LVO) using the CINA® LVO software. The patients were sub-grouped by occlusion site. The original radiology report was used as ground truth and cases with disagreement were reassessed. Two-by-two tables were created and measures for LVO detection were calculated. Results: A total of... (More)

Objective: To systematically evaluate the ability of the CINA® LVO software to detect large vessel occlusions eligible for mechanical thrombectomy on CTA using conventional neuroradiological assessment as gold standard. Methods: Retrospectively, two hundred consecutive patients referred for a brain CTA and two hundred patients that had been subject for endovascular thrombectomy, with an accessible preceding CTA, were assessed for large vessel occlusions (LVO) using the CINA® LVO software. The patients were sub-grouped by occlusion site. The original radiology report was used as ground truth and cases with disagreement were reassessed. Two-by-two tables were created and measures for LVO detection were calculated. Results: A total of four-hundred patients were included; 221 LVOs were present in 215 patients (54 %). The overall specificity was high for LVOs in the anterior circulation (93 %). The overall sensitivity for LVOs in the anterior circulation was 54 % with the highest sensitivity for the M1 segment of the middle cerebral artery (87 %) and T-type internal carotid occlusions (84 %). The sensitivity was low for occlusions in the M2 segment of the middle cerebral artery (13 % and 0 % for proximal and distal M2 occlusions respectively) and in posterior circulation occlusions (0 %, not included in the intended use of the software). Conclusions: LVO detection sensitivity for the CINA® LVO software differs largely depending on the location of the occlusion, with low sensitivity for detection of some LVOs potentially eligible for mechanical thrombectomy. Further development of the software to increase sensitivity to all LVO locations would increase the clinical usefulness.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Acute Ischemic stroke, Artificial Intelligence, Computed Tomography Angiography, Diagnostic Tests, Software Validation
in
European Journal of Radiology Open
volume
12
article number
100542
publisher
Elsevier
external identifiers
  • pmid:38188638
  • scopus:85180409297
ISSN
2352-0477
DOI
10.1016/j.ejro.2023.100542
language
English
LU publication?
yes
id
e9a1619c-eb82-4ca5-a1f0-4ae4465861c0
date added to LUP
2024-01-31 11:59:57
date last changed
2024-04-17 00:14:17
@article{e9a1619c-eb82-4ca5-a1f0-4ae4465861c0,
  abstract     = {{<p>Objective: To systematically evaluate the ability of the CINA® LVO software to detect large vessel occlusions eligible for mechanical thrombectomy on CTA using conventional neuroradiological assessment as gold standard. Methods: Retrospectively, two hundred consecutive patients referred for a brain CTA and two hundred patients that had been subject for endovascular thrombectomy, with an accessible preceding CTA, were assessed for large vessel occlusions (LVO) using the CINA® LVO software. The patients were sub-grouped by occlusion site. The original radiology report was used as ground truth and cases with disagreement were reassessed. Two-by-two tables were created and measures for LVO detection were calculated. Results: A total of four-hundred patients were included; 221 LVOs were present in 215 patients (54 %). The overall specificity was high for LVOs in the anterior circulation (93 %). The overall sensitivity for LVOs in the anterior circulation was 54 % with the highest sensitivity for the M1 segment of the middle cerebral artery (87 %) and T-type internal carotid occlusions (84 %). The sensitivity was low for occlusions in the M2 segment of the middle cerebral artery (13 % and 0 % for proximal and distal M2 occlusions respectively) and in posterior circulation occlusions (0 %, not included in the intended use of the software). Conclusions: LVO detection sensitivity for the CINA® LVO software differs largely depending on the location of the occlusion, with low sensitivity for detection of some LVOs potentially eligible for mechanical thrombectomy. Further development of the software to increase sensitivity to all LVO locations would increase the clinical usefulness.</p>}},
  author       = {{Mellander, Helena and Hillal, Amir and Ullberg, Teresa and Wassélius, Johan}},
  issn         = {{2352-0477}},
  keywords     = {{Acute Ischemic stroke; Artificial Intelligence; Computed Tomography Angiography; Diagnostic Tests; Software Validation}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{European Journal of Radiology Open}},
  title        = {{Evaluation of CINA® LVO artificial intelligence software for detection of large vessel occlusion in brain CT angiography}},
  url          = {{http://dx.doi.org/10.1016/j.ejro.2023.100542}},
  doi          = {{10.1016/j.ejro.2023.100542}},
  volume       = {{12}},
  year         = {{2024}},
}