Predicting DWI-FLAIR mismatch on NCCT: the role of artificial intelligence in hyperacute decision making

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00159816%3A_____%2F23%3A00078764" target="_blank" >RIV/00159816:_____/23:00078764 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216224:14110/23:00133283

Výsledek na webu

<a href="https://www.frontiersin.org/articles/10.3389/fneur.2023.1201223/full" target="_blank" >https://www.frontiersin.org/articles/10.3389/fneur.2023.1201223/full</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3389/fneur.2023.1201223" target="_blank" >10.3389/fneur.2023.1201223</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Predicting DWI-FLAIR mismatch on NCCT: the role of artificial intelligence in hyperacute decision making

Popis výsledku v původním jazyce

BackgroundThe presence of diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) mismatch was used to determine eligibility for intravenous thrombolysis in clinical trials. However, due to the restricted availability of MRI and the ambiguity of image assessment, it is not widely implemented in clinical practice. MethodsA total of 222 acute ischemic stroke patients underwent non-contrast computed tomography (NCCT), DWI, and FLAIR within 1 h of one another. Human experts manually segmented ischemic lesions on DWI and FLAIR images and independently graded the presence of DWI-FLAIR mismatch. Deep learning (DL) models based on the nnU-net architecture were developed to predict ischemic lesions visible on DWI and FLAIR images using NCCT images. Inexperienced neurologists evaluated the DWI-FLAIR mismatch on NCCT images without and with the model&apos;s results. ResultsThe mean age of included subjects was 71.8 &amp; PLUSMN; 12.8 years, 123 (55%) were male, and the baseline NIHSS score was a median of 11 [IQR, 6-18]. All images were taken in the following order: NCCT - DWI - FLAIR, starting after a median of 139 [81-326] min after the time of the last known well. Intravenous thrombolysis was administered in 120 patients (54%) after NCCT. The DL model&apos;s prediction on NCCT images revealed a Dice coefficient and volume correlation of 39.1% and 0.76 for DWI lesions and 18.9% and 0.61 for FLAIR lesions. In the subgroup with 15 mL or greater lesion volume, the evaluation of DWI-FLAIR mismatch from NCCT by inexperienced neurologists improved in accuracy (from 0.537 to 0.610) and AUC-ROC (from 0.493 to 0.613). ConclusionThe DWI-FLAIR mismatch may be reckoned using NCCT images through advanced artificial intelligence techniques.

Název v anglickém jazyce

Predicting DWI-FLAIR mismatch on NCCT: the role of artificial intelligence in hyperacute decision making

Popis výsledku anglicky

BackgroundThe presence of diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) mismatch was used to determine eligibility for intravenous thrombolysis in clinical trials. However, due to the restricted availability of MRI and the ambiguity of image assessment, it is not widely implemented in clinical practice. MethodsA total of 222 acute ischemic stroke patients underwent non-contrast computed tomography (NCCT), DWI, and FLAIR within 1 h of one another. Human experts manually segmented ischemic lesions on DWI and FLAIR images and independently graded the presence of DWI-FLAIR mismatch. Deep learning (DL) models based on the nnU-net architecture were developed to predict ischemic lesions visible on DWI and FLAIR images using NCCT images. Inexperienced neurologists evaluated the DWI-FLAIR mismatch on NCCT images without and with the model&apos;s results. ResultsThe mean age of included subjects was 71.8 &amp; PLUSMN; 12.8 years, 123 (55%) were male, and the baseline NIHSS score was a median of 11 [IQR, 6-18]. All images were taken in the following order: NCCT - DWI - FLAIR, starting after a median of 139 [81-326] min after the time of the last known well. Intravenous thrombolysis was administered in 120 patients (54%) after NCCT. The DL model&apos;s prediction on NCCT images revealed a Dice coefficient and volume correlation of 39.1% and 0.76 for DWI lesions and 18.9% and 0.61 for FLAIR lesions. In the subgroup with 15 mL or greater lesion volume, the evaluation of DWI-FLAIR mismatch from NCCT by inexperienced neurologists improved in accuracy (from 0.537 to 0.610) and AUC-ROC (from 0.493 to 0.613). ConclusionThe DWI-FLAIR mismatch may be reckoned using NCCT images through advanced artificial intelligence techniques.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

30210 - Clinical neurology

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Frontiers in Neurology

ISSN

1664-2295

e-ISSN

—

Svazek periodika

14

Číslo periodika v rámci svazku

JUN 12

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

10

Strana od-do

1201223

Kód UT WoS článku

001013166500001

EID výsledku v databázi Scopus

2-s2.0-85163631325