Machine learning and acute stroke imaging.


Journal

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

Informations de publication

Date de publication:
Feb 2023
Historique:
received: 17 11 2021
accepted: 08 05 2022
pubmed: 26 5 2022
medline: 14 1 2023
entrez: 25 5 2022
Statut: ppublish

Résumé

In recent years, machine learning (ML) has had notable success in providing automated analyses of neuroimaging studies, and its role is likely to increase in the future. Thus, it is paramount for clinicians to understand these approaches, gain facility with interpreting ML results, and learn how to assess algorithm performance. To provide an overview of ML, present its role in acute stroke imaging, discuss methods to evaluate algorithms, and then provide an assessment of existing approaches. In this review, we give an overview of ML techniques commonly used in medical imaging analysis and methods to evaluate performance. We then review the literature for relevant publications. Searches were run in November 2021 in Ovid Medline and PubMed. Inclusion criteria included studies in English reporting use of artificial intelligence (AI), machine learning, or similar techniques in the setting of, and in applications for, acute ischemic stroke or mechanical thrombectomy. Articles that included image-level data with meaningful results and sound ML approaches were included in this discussion. Many publications on acute stroke imaging, including detection of large vessel occlusion, detection and quantification of intracranial hemorrhage and detection of infarct core, have been published using ML methods. Imaging inputs have included non-contrast head CT, CT angiograph and MRI, with a range of performances. We discuss and review several of the most relevant publications. ML in acute ischemic stroke imaging has already made tremendous headway. Additional applications and further integration with clinical care is inevitable. Thus, facility with these approaches is critical for the neurointerventional clinician.

Sections du résumé

BACKGROUND BACKGROUND
In recent years, machine learning (ML) has had notable success in providing automated analyses of neuroimaging studies, and its role is likely to increase in the future. Thus, it is paramount for clinicians to understand these approaches, gain facility with interpreting ML results, and learn how to assess algorithm performance.
OBJECTIVE OBJECTIVE
To provide an overview of ML, present its role in acute stroke imaging, discuss methods to evaluate algorithms, and then provide an assessment of existing approaches.
METHODS METHODS
In this review, we give an overview of ML techniques commonly used in medical imaging analysis and methods to evaluate performance. We then review the literature for relevant publications. Searches were run in November 2021 in Ovid Medline and PubMed. Inclusion criteria included studies in English reporting use of artificial intelligence (AI), machine learning, or similar techniques in the setting of, and in applications for, acute ischemic stroke or mechanical thrombectomy. Articles that included image-level data with meaningful results and sound ML approaches were included in this discussion.
RESULTS RESULTS
Many publications on acute stroke imaging, including detection of large vessel occlusion, detection and quantification of intracranial hemorrhage and detection of infarct core, have been published using ML methods. Imaging inputs have included non-contrast head CT, CT angiograph and MRI, with a range of performances. We discuss and review several of the most relevant publications.
CONCLUSIONS CONCLUSIONS
ML in acute ischemic stroke imaging has already made tremendous headway. Additional applications and further integration with clinical care is inevitable. Thus, facility with these approaches is critical for the neurointerventional clinician.

Identifiants

pubmed: 35613840
pii: neurintsurg-2021-018142
doi: 10.1136/neurintsurg-2021-018142
pmc: PMC10523646
mid: NIHMS1931027
doi:

Types de publication

Journal Article Review

Langues

eng

Sous-ensembles de citation

IM

Pagination

195-199

Subventions

Organisme : NINDS NIH HHS
ID : R01 NS121154
Pays : United States

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: PK is on the editorial board of JNIS.

Références

Cerebrovasc Dis. 2021;50(4):450-455
pubmed: 33849032
Lancet. 2018 Dec 1;392(10162):2388-2396
pubmed: 30318264
J Neurointerv Surg. 2020 Feb;12(2):156-164
pubmed: 31594798
Neuroradiology. 2020 Oct;62(10):1231-1238
pubmed: 32382795
J Chronic Dis. 1987;40(5):373-83
pubmed: 3558716
Front Neurol. 2018 Sep 04;9:717
pubmed: 30233482
J Neurol. 2020 Sep;267(9):2632-2641
pubmed: 32394015
Neuroimage. 2012 Aug 15;62(2):782-90
pubmed: 21979382
Stroke. 2020 Oct;51(10):3133-3137
pubmed: 32842922
Stroke. 2019 Sep;50(9):2379-2388
pubmed: 31409267
Eur Radiol. 2019 Nov;29(11):6285-6292
pubmed: 31076862
Brain Sci. 2021 Jun 23;11(7):
pubmed: 34201775
IEEE Trans Med Imaging. 2010 Jan;29(1):196-205
pubmed: 19923044
Radiology. 2021 Jun;299(3):675-681
pubmed: 33787336
Stroke. 2020 Dec;51(12):3541-3551
pubmed: 33040701
Interv Neuroradiol. 2020 Oct;26(5):615-622
pubmed: 32847449
Diagnostics (Basel). 2020 Sep 30;10(10):
pubmed: 33007929
AJNR Am J Neuroradiol. 2021 Jan;42(2):240-246
pubmed: 33414230
Stroke. 2021 Jul;52(7):2328-2337
pubmed: 33957774
Stroke. 2019 May;50(5):1263-1265
pubmed: 30890116
Front Neuroinform. 2014 Feb 20;8:13
pubmed: 24600387
N Engl J Med. 2017 Sep 28;377(13):1209-1211
pubmed: 28953443
Neurosurg Focus. 2021 Jul;51(1):E13
pubmed: 34198252
Radiology. 2020 Mar;294(3):638-644
pubmed: 31990267
J Neurointerv Surg. 2021 May;13(5):406-408
pubmed: 33234600
Neuroimage. 2016 Apr 1;129:460-469
pubmed: 26808333
AJNR Am J Neuroradiol. 2021 Jan;42(2):247-254
pubmed: 33384294
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Circ Cardiovasc Qual Outcomes. 2021 Apr;14(4):e006989
pubmed: 33757311
Stroke. 2020 Mar;51(3):860-866
pubmed: 31987014
Med Image Anal. 2019 Feb;52:128-143
pubmed: 30579222
IEEE Trans Pattern Anal Mach Intell. 2013 Aug;35(8):1798-828
pubmed: 23787338
Neurology. 2020 Nov 3;95(18):e2465-e2475
pubmed: 32943483
Stroke. 2020 Aug;51(8):2488-2494
pubmed: 32684141
Neuroimage. 2012 Aug 15;62(2):774-81
pubmed: 22248573
World Neurosurg. 2021 Apr;148:e58-e65
pubmed: 33359736

Auteurs

Sunil A Sheth (SA)

Department of Neurology, UTHealth McGovern Medical School, Houston, Texas, USA Sunil.A.Sheth@uth.tmc.edu.

Luca Giancardo (L)

Center for Precision Health, School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA.

Marco Colasurdo (M)

Department of Neurosurgery, The University of Texas Medical Branch at Galveston, Galveston, Texas, USA.
Department of Neuroradiology, The University of Texas Medical Branch at Galveston, Galveston, Texas, USA.

Visish M Srinivasan (VM)

Department of Neurosurgery, Barrow Neurological Institute, Phoenix, Arizona, USA.

Arash Niktabe (A)

Department of Neurology, UTHealth McGovern Medical School, Houston, Texas, USA.

Peter Kan (P)

Department of Neurosurgery, The University of Texas Medical Branch at Galveston, Galveston, Texas, USA.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH