Automated assessment of ischemic core on non-contrast computed tomography: a multicenter comparative analysis with CT perfusion.

CT CT perfusion stroke

Journal

Journal of neurointerventional surgery
ISSN: 1759-8486
Titre abrégé: J Neurointerv Surg
Pays: England
ID NLM: 101517079

Informations de publication

Date de publication:
02 Nov 2023
Historique:
received: 26 08 2023
accepted: 13 10 2023
medline: 3 11 2023
pubmed: 3 11 2023
entrez: 2 11 2023
Statut: aheadofprint

Résumé

Application of machine learning (ML) algorithms has shown promising results in estimating ischemic core volumes using non-contrast CT (NCCT). To assess the performance of the e-Stroke Suite software (Brainomix) in assessing ischemic core volumes on NCCT compared with CT perfusion (CTP) in patients with acute ischemic stroke. In this retrospective multicenter study, patients with anterior circulation large vessel occlusions who underwent pretreatment NCCT and CTP, successful reperfusion (modified Thrombolysis in Cerbral Infarction ≥2b), and post-treatment MRI, were included from three stroke centers. Automated calculation of ischemic core volumes was obtained on NCCT scans using ML algorithm deployed by e-Stroke Suite and from CTP using Olea software (Olea Medical). Comparative analysis was performed between estimated core volumes on NCCT and CTP and against MRI calculated final infarct volume (FIV). A total of 111 patients were included. Estimated ischemic core volumes (mean±SD, mL) were 20.4±19.0 on NCCT and 19.9±18.6 on CTP, not significantly different (P=0.82). There was moderate (r=0.40) and significant (P<0.001) correlation between estimated core on NCCT and CTP. The mean difference between FIV and estimated core volume on NCCT and CTP was 29.9±34.6 mL and 29.6±35.0 mL, respectively (P=0.94). Correlations between FIV and estimated core volume were similar for NCCT (r=0.30, P=0.001) and CTP (r=0.36, P<0.001). Results show that ML-based estimated ischemic core volumes on NCCT are comparable to those obtained from concurrent CTP in magnitude and in degree of correlation with MR-assessed FIV.

Sections du résumé

BACKGROUND BACKGROUND
Application of machine learning (ML) algorithms has shown promising results in estimating ischemic core volumes using non-contrast CT (NCCT).
OBJECTIVE OBJECTIVE
To assess the performance of the e-Stroke Suite software (Brainomix) in assessing ischemic core volumes on NCCT compared with CT perfusion (CTP) in patients with acute ischemic stroke.
METHODS METHODS
In this retrospective multicenter study, patients with anterior circulation large vessel occlusions who underwent pretreatment NCCT and CTP, successful reperfusion (modified Thrombolysis in Cerbral Infarction ≥2b), and post-treatment MRI, were included from three stroke centers. Automated calculation of ischemic core volumes was obtained on NCCT scans using ML algorithm deployed by e-Stroke Suite and from CTP using Olea software (Olea Medical). Comparative analysis was performed between estimated core volumes on NCCT and CTP and against MRI calculated final infarct volume (FIV).
RESULTS RESULTS
A total of 111 patients were included. Estimated ischemic core volumes (mean±SD, mL) were 20.4±19.0 on NCCT and 19.9±18.6 on CTP, not significantly different (P=0.82). There was moderate (r=0.40) and significant (P<0.001) correlation between estimated core on NCCT and CTP. The mean difference between FIV and estimated core volume on NCCT and CTP was 29.9±34.6 mL and 29.6±35.0 mL, respectively (P=0.94). Correlations between FIV and estimated core volume were similar for NCCT (r=0.30, P=0.001) and CTP (r=0.36, P<0.001).
CONCLUSIONS CONCLUSIONS
Results show that ML-based estimated ischemic core volumes on NCCT are comparable to those obtained from concurrent CTP in magnitude and in degree of correlation with MR-assessed FIV.

Identifiants

DOI: 10.1136/jnis-2023-020954 PMID: 37918907
pubmed: 37918907
pii: jnis-2023-020954
doi: 10.1136/jnis-2023-020954
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© Author(s) (or their employer(s)) 2023. No commercial re-use. See rights and permissions. Published by BMJ.

Déclaration de conflit d'intérêts

Competing interests: GPC: Stryker Neurovascular, MicroVention, Medtronic, Rapid Medical; JLS: Medtronic Cerenovus, Boehringer Ingelheim, NeuroVasc, Rapid Medical; DSL: Cerenovus, Genentech, Medtronic, Stryker, Olea; KN: Olea Medical, Brainomix; Achala Vagal: Viz AI.

Auteurs

Puja Shahrouki (P)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.
ORCID: 0000-0002-8554-2794

Shingo Kihira (S)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.
ORCID: 0000-0003-1001-8741

Elham Tavakkol (E)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Joe X Qiao (JX)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Achala Vagal (A)

Department of Radiology, University of Cincinnati Medical Center, Cincinnati, Ohio, USA.

Pooja Khatri (P)

Department of Neurology, University of Cincinnati, Cincinnati, Ohio, USA.

Mersedeh Bahr-Hosseini (M)

Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Geoffrey P Colby (GP)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.
Department of Neurosurgery, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Reza Jahan (R)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Gary Duckwiler (G)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Viktor Szeder (V)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.
Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Luke Ledbetter (L)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Stephen Cai (S)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Banafsheh Salehi (B)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Amish H Doshi (AH)

Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.

Puneet Belani (P)

Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.

Johanna T Fifi (JT)

Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA.

Reade De Leacy (R)

Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA.

J Mocco (J)

Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
ORCID: 0000-0001-5489-2524

Jeffrey L Saver (JL)

Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.
ORCID: 0000-0001-9141-2251

David S Liebeskind (DS)

Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA.

Kambiz Nael (K)

Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA kambiznael@gmail.com.

Classifications MeSH