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.

Basic information

Original name

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

Authors

KRÁL, Jiří (203 Czech Republic, belonging to the institution), Martin CABAL (203 Czech Republic), Linda MACHOVÁ (203 Czech Republic), Jaroslav HAVELKA (203 Czech Republic), Tomáš JONSZTA, Ondřej VOLNÝ (203 Czech Republic, belonging to the institution) and Michal BAR (203 Czech Republic, guarantor)

Edition

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

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30103 Neurosciences

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 2.804

RIV identification code

RIV/00216224:14110/20:00115700

Organization unit

Faculty of Medicine

DOI

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

UT WoS

000528133300001

Keywords in English

Computed tomography; Software; Automatic; Final ischemia

Abstract

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 and 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, vol. 62, No 10, p. 1239-1245. ISSN 0028-3940. Available from: 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 and 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, vol.~62, No~10, p.~1239-1245. ISSN~0028-3940. Available from: https://dx.doi.org/10.1007/s00234-020-02419-7.

Detailed Information on Publication Record