Machine learning volumetry of ischemic brain lesions on CT
after thrombectomy-prospective diagnostic accuracy study in
ischemic stroke patients

J 2020

Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients

KRÁL, Jiří, Martin CABAL, Linda MACHOVÁ, Jaroslav HAVELKA, Tomáš JONSZTA et. al.

Základní údaje

Originální název

Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients

Autoři

KRÁL, Jiří (203 Česká republika, domácí), Martin CABAL (203 Česká republika), Linda MACHOVÁ (203 Česká republika), Jaroslav HAVELKA (203 Česká republika), Tomáš JONSZTA, Ondřej VOLNÝ (203 Česká republika, domácí) a Michal BAR (203 Česká republika, garant)

Vydání

NEURORADIOLOGY, NEW YORK, SPRINGER, 2020, 0028-3940

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30103 Neurosciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 2.804

Kód RIV

RIV/00216224:14110/20:00115700

Organizační jednotka

Lékařská fakulta

DOI

http://dx.doi.org/10.1007/s00234-020-02419-7

UT WoS

000528133300001

Klíčová slova anglicky

Computed tomography; Software; Automatic; Final ischemia

Štítky

14110127, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 13. 9. 2021 14:59, Mgr. Tereza Miškechová

Anotace

V originále

Purpose Ischemic lesion volume (ILV) is an important radiological predictor of functional outcome in patients with anterior circulation stroke. Our aim was to assess the agreement between automated ILV measurements on NCCT using the Brainomix software and manual ILV measurements on diffusion-weighted imaging (DWI). Methods This was a prospective single-center observational study of patients with CT angiography (CTA) proven anterior circulation occlusion treated with endovascular thrombectomy (May 2018 to May 2019). NCCT ILV was measured automatically by the Brainomix software. DWI ILV was measured manually. The McNemar's test was used to test sensitivity and specificity. The Somer's delta was used to test the differences between concordant and discordant ASPECTS regions. The Bland-Altman plot was calculated to compare the differences between Brainomix and DWI ILVs. Results Forty-five patients were included. Median Brainomix ILV was 23 ml (interquartile range [IQR], 15-39 ml), and median DWI ILV was 11.5 ml (IQR, 7-32 ml) in the TICI 2b-3 group. In the TICI 0-2a, the NCCT ILV was 39 ml (IQR, 18-62 ml) and DWI ILV was 30 (IQR, 11-105 ml). The DWI ILVs in patients with good clinical outcome (mRS 0-2) was significantly lower compared with patients with mRS >= 3 (10 mL vs 59 mL, p = 0.002). Similar trend was observed for Brainomix ILV measurements (21 mL vs 39 mL, p = 0.012). There was a high correlation and accuracy in the detection of follow-up ischemic changes in particular ASPECTS regions. Conclusion NCCT ILV measured automatically by the Brainomix software might be considered a valuable radiological outcome measure.

Citovat

KRÁL, Jiří, Martin CABAL, Linda MACHOVÁ, Jaroslav HAVELKA, Tomáš JONSZTA, Ondřej VOLNÝ a Michal BAR. Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients. NEURORADIOLOGY. NEW YORK: SPRINGER, 2020, roč. 62, č. 10, s. 1239-1245. ISSN 0028-3940. Dostupné z: https://dx.doi.org/10.1007/s00234-020-02419-7.

@article{1658556,
   author = {Král, Jiří and Cabal, Martin and Machová, Linda and Havelka, Jaroslav and Jonszta, Tomáš and Volný, Ondřej and Bar, Michal},
   article_location = {NEW YORK},
   article_number = {10},
   doi = {http://dx.doi.org/10.1007/s00234-020-02419-7},
   keywords = {Computed tomography; Software; Automatic; Final ischemia},
   language = {eng},
   issn = {0028-3940},
   journal = {NEURORADIOLOGY},
   title = {Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients},
   url = {https://link.springer.com/article/10.1007%2Fs00234-020-02419-7},
   volume = {62},
   year = {2020}
}

TY  - JOUR
ID  - 1658556
AU  - Král, Jiří - Cabal, Martin - Machová, Linda - Havelka, Jaroslav - Jonszta, Tomáš - Volný, Ondřej - Bar, Michal
PY  - 2020
TI  - Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients
JF  - NEURORADIOLOGY
VL  - 62
IS  - 10
SP  - 1239-1245
EP  - 1239-1245
PB  - SPRINGER
SN  - 00283940
KW  - Computed tomography
KW  - Software
KW  - Automatic
KW  - Final ischemia
UR  - https://link.springer.com/article/10.1007%2Fs00234-020-02419-7
L2  - https://link.springer.com/article/10.1007%2Fs00234-020-02419-7
N2  - Purpose Ischemic lesion volume (ILV) is an important radiological predictor of functional outcome in patients with anterior circulation stroke. Our aim was to assess the agreement between automated ILV measurements on NCCT using the Brainomix software and manual ILV measurements on diffusion-weighted imaging (DWI). Methods This was a prospective single-center observational study of patients with CT angiography (CTA) proven anterior circulation occlusion treated with endovascular thrombectomy (May 2018 to May 2019). NCCT ILV was measured automatically by the Brainomix software. DWI ILV was measured manually. The McNemar's test was used to test sensitivity and specificity. The Somer's delta was used to test the differences between concordant and discordant ASPECTS regions. The Bland-Altman plot was calculated to compare the differences between Brainomix and DWI ILVs. Results Forty-five patients were included. Median Brainomix ILV was 23 ml (interquartile range [IQR], 15-39 ml), and median DWI ILV was 11.5 ml (IQR, 7-32 ml) in the TICI 2b-3 group. In the TICI 0-2a, the NCCT ILV was 39 ml (IQR, 18-62 ml) and DWI ILV was 30 (IQR, 11-105 ml). The DWI ILVs in patients with good clinical outcome (mRS 0-2) was significantly lower compared with patients with mRS >= 3 (10 mL vs 59 mL, p = 0.002). Similar trend was observed for Brainomix ILV measurements (21 mL vs 39 mL, p = 0.012). There was a high correlation and accuracy in the detection of follow-up ischemic changes in particular ASPECTS regions. Conclusion NCCT ILV measured automatically by the Brainomix software might be considered a valuable radiological outcome measure.
ER  -

KRÁL, Jiří, Martin CABAL, Linda MACHOVÁ, Jaroslav HAVELKA, Tomáš JONSZTA, Ondřej VOLNÝ a Michal BAR. Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients. \textit{NEURORADIOLOGY}. NEW YORK: SPRINGER, 2020, roč.~62, č.~10, s.~1239-1245. ISSN~0028-3940. Dostupné z: https://dx.doi.org/10.1007/s00234-020-02419-7.

Podrobný výpis o publikaci