Performance of Automated ASPECTS Software and Value as a Computer-Aided Detection Tool.
Journal
AJNR. American journal of neuroradiology
ISSN: 1936-959X
Titre abrégé: AJNR Am J Neuroradiol
Pays: United States
ID NLM: 8003708
Informations de publication
Date de publication:
08 2023
08 2023
Historique:
received:
06
03
2023
accepted:
14
06
2023
pmc-release:
01
08
2024
medline:
11
8
2023
pubmed:
28
7
2023
entrez:
27
7
2023
Statut:
ppublish
Résumé
ASPECTS quantifies early ischemic changes in anterior circulation stroke on NCCT but has interrater variability. We examined the agreement of conventional and automated ASPECTS and studied the value of computer-aided detection. We retrospectively collected imaging data from consecutive patients with acute ischemic stroke with large-vessel occlusion undergoing thrombectomy. Five raters scored conventional ASPECTS on baseline NCCTs, which were also processed by RAPID software. Conventional and automated ASPECTS were compared with a consensus criterion standard. We determined the agreement over the full ASPECTS range as well as dichotomized, reflecting thrombectomy eligibility according to the guidelines (ASPECTS 0-5 versus 6-10). Raters subsequently scored ASPECTS on the same NCCTs with assistance of the automated ASPECTS outputs, and agreement was obtained. For the total of 175 cases, agreement among raters individually and the criterion standard varied from fair to good (weighted κ = between 0.38 and 0.76) and was moderate (weighted κ = 0.59) for the automated ASPECTS. The agreement of all raters individually versus the criterion standard improved with software assistance, as did the interrater agreement (overall Fleiss κ = 0.15-0.23; Automated ASPECTS had agreement with the criterion standard similar to that of conventional ASPECTS. However, including automated ASPECTS during the evaluation of NCCT in acute stroke improved the agreement with the criterion standard and improved interrater agreement, which could, therefore, result in more uniform scoring in clinical practice.
Sections du résumé
BACKGROUND AND PURPOSE
ASPECTS quantifies early ischemic changes in anterior circulation stroke on NCCT but has interrater variability. We examined the agreement of conventional and automated ASPECTS and studied the value of computer-aided detection.
MATERIALS AND METHODS
We retrospectively collected imaging data from consecutive patients with acute ischemic stroke with large-vessel occlusion undergoing thrombectomy. Five raters scored conventional ASPECTS on baseline NCCTs, which were also processed by RAPID software. Conventional and automated ASPECTS were compared with a consensus criterion standard. We determined the agreement over the full ASPECTS range as well as dichotomized, reflecting thrombectomy eligibility according to the guidelines (ASPECTS 0-5 versus 6-10). Raters subsequently scored ASPECTS on the same NCCTs with assistance of the automated ASPECTS outputs, and agreement was obtained.
RESULTS
For the total of 175 cases, agreement among raters individually and the criterion standard varied from fair to good (weighted κ = between 0.38 and 0.76) and was moderate (weighted κ = 0.59) for the automated ASPECTS. The agreement of all raters individually versus the criterion standard improved with software assistance, as did the interrater agreement (overall Fleiss κ = 0.15-0.23;
CONCLUSIONS
Automated ASPECTS had agreement with the criterion standard similar to that of conventional ASPECTS. However, including automated ASPECTS during the evaluation of NCCT in acute stroke improved the agreement with the criterion standard and improved interrater agreement, which could, therefore, result in more uniform scoring in clinical practice.
Identifiants
pubmed: 37500286
pii: ajnr.A7956
doi: 10.3174/ajnr.A7956
pmc: PMC10411841
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
894-900Informations de copyright
© 2023 by American Journal of Neuroradiology.
Références
AJNR Am J Neuroradiol. 2019 Dec;40(12):2033-2038
pubmed: 31727750
Biochem Med (Zagreb). 2012;22(3):276-82
pubmed: 23092060
Int J Stroke. 2017 Aug;12(6):615-622
pubmed: 27899743
Expert Rev Cardiovasc Ther. 2018 Feb;16(2):143-153
pubmed: 29265903
Int J Stroke. 2016 Jun;11(4):438-45
pubmed: 26880058
Neuroradiology. 2020 Oct;62(10):1231-1238
pubmed: 32382795
AJNR Am J Neuroradiol. 2017 Aug;38(8):1594-1599
pubmed: 28596195
Stroke. 2019 Nov;50(11):3277-3279
pubmed: 31500555
J Neuroimaging. 2021 Mar;31(2):341-347
pubmed: 33421036
N Engl J Med. 2023 Apr 6;388(14):1272-1283
pubmed: 36762852
N Engl J Med. 2023 Apr 6;388(14):1259-1271
pubmed: 36762865
J Neurointerv Surg. 2020 Jul;12(7):720-723
pubmed: 31818971
Stroke. 2019 Dec;50(12):e344-e418
pubmed: 31662037
J Neuroimaging. 2019 Mar;29(2):198-202
pubmed: 30230093
Front Neurol. 2023 Apr 06;14:1170955
pubmed: 37090971
AJNR Am J Neuroradiol. 2012 Jun;33(6):1046-9
pubmed: 22322602
Neuroradiology. 2018 Dec;60(12):1267-1272
pubmed: 30219935
Ann Neurol. 2022 Dec;92(6):943-957
pubmed: 36053916
Lancet. 2000 May 13;355(9216):1670-4
pubmed: 10905241
J Neurointerv Surg. 2020 Nov;12(11):1069-1071
pubmed: 32024784
Stroke. 2004 May;35(5):e103-5
pubmed: 15073381
Clin Neuroradiol. 2021 Dec;31(4):1093-1100
pubmed: 33502563
J Stroke Cerebrovasc Dis. 2021 Jul;30(7):105829
pubmed: 33989968
J Neurointerv Surg. 2020 Apr;12(4):350-355
pubmed: 31401563
Stroke. 2015 Feb;46(2):407-12
pubmed: 25538199
Eur Radiol. 2019 Nov;29(11):6285-6292
pubmed: 31076862
Biom J. 2017 Sep;59(5):1016-1034
pubmed: 28464322
Neurology. 2016 Jul 19;87(3):249-56
pubmed: 27316243
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571
Radiology. 2019 Apr;291(1):141-148
pubmed: 30720400
Radiat Prot Dosimetry. 2010 Apr-May;139(1-3):42-51
pubmed: 20200105