Validation of a machine learning software tool for automated
large vessel occlusion detection in patients with suspected
acute stroke

J 2022

Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke

CIMFLOVÁ, Petra, Rotem GOLAN, Johanna M OSPEL, Alireza SOJOUDI, Chris DUSZYNSKI et. al.

Základní údaje

Originální název

Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke

Autoři

CIMFLOVÁ, Petra (203 Česká republika, garant, domácí), Rotem GOLAN, Johanna M OSPEL, Alireza SOJOUDI, Chris DUSZYNSKI, Ibukun ELEBUTE, Houssam EL-HARIRI, Seyed Hossein MOUSAVI, Luis A Souto Maior NETO, Najratun PINKY, Benjamin BELAND, Fouzi BALA, Nima R KASHANI, William HU, Manish JOSHI, Wu QIU a Bijoy K MENON

Vydání

NEURORADIOLOGY, NEW YORK, SPRINGER, 2022, 0028-3940

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30224 Radiology, nuclear medicine and medical imaging

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 2.800

Kód RIV

RIV/00216224:14110/22:00128327

Organizační jednotka

Lékařská fakulta

DOI

http://dx.doi.org/10.1007/s00234-022-02978-x

UT WoS

000800996700001

Klíčová slova anglicky

Machine learning; Large vessel occlusion; Stroke; Automatic detection

Štítky

14110119, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 27. 1. 2023 13:05, Mgr. Tereza Miškechová

Anotace

V originále

Purpose CT angiography (CTA) is the imaging standard for large vessel occlusion (LVO) detection in patients with acute ischemic stroke. StrokeSENS LVO is an automated tool that utilizes a machine learning algorithm to identify anterior large vessel occlusions (LVO) on CTA. The aim of this study was to test the algorithm's performance in LVO detection in an independent dataset. Methods A total of 400 studies (217 LVO, 183 other/no occlusion) read by expert consensus were used for retrospective analysis. The LVO was defined as intracranial internal carotid artery (ICA) occlusion and M1 middle cerebral artery (MCA) occlusion. Software performance in detecting anterior LVO was evaluated using receiver operator characteristics (ROC) analysis, reporting area under the curve (AUC), sensitivity, and specificity. Subgroup analyses were performed to evaluate if performance in detecting LVO differed by subgroups, namely M1 MCA and ICA occlusion sites, and in data stratified by patient age, sex, and CTA acquisition characteristics (slice thickness, kilovoltage tube peak, and scanner manufacturer). Results AUC, sensitivity, and specificity overall were as follows: 0.939, 0.894, and 0.874, respectively, in the full cohort; 0.927, 0.857, and 0.874, respectively, in the ICA occlusion cohort; 0.945, 0.914, and 0.874, respectively, in the M1 MCA occlusion cohort. Performance did not differ significantly by patient age, sex, or CTA acquisition characteristics. Conclusion The StrokeSENS LVO machine learning algorithm detects anterior LVO with high accuracy from a range of scans in a large dataset.

Citovat

CIMFLOVÁ, Petra, Rotem GOLAN, Johanna M OSPEL, Alireza SOJOUDI, Chris DUSZYNSKI, Ibukun ELEBUTE, Houssam EL-HARIRI, Seyed Hossein MOUSAVI, Luis A Souto Maior NETO, Najratun PINKY, Benjamin BELAND, Fouzi BALA, Nima R KASHANI, William HU, Manish JOSHI, Wu QIU a Bijoy K MENON. Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke. NEURORADIOLOGY. NEW YORK: SPRINGER, 2022, roč. 64, č. 12, s. 2245-2255. ISSN 0028-3940. Dostupné z: https://dx.doi.org/10.1007/s00234-022-02978-x.

@article{2250060,
   author = {Cimflová, Petra and Golan, Rotem and Ospel, Johanna M and Sojoudi, Alireza and Duszynski, Chris and Elebute, Ibukun and ElandHariri, Houssam and Mousavi, Seyed Hossein and Neto, Luis A Souto Maior and Pinky, Najratun and Beland, Benjamin and Bala, Fouzi and Kashani, Nima R and Hu, William and Joshi, Manish and Qiu, Wu and Menon, Bijoy K},
   article_location = {NEW YORK},
   article_number = {12},
   doi = {http://dx.doi.org/10.1007/s00234-022-02978-x},
   keywords = {Machine learning; Large vessel occlusion; Stroke; Automatic detection},
   language = {eng},
   issn = {0028-3940},
   journal = {NEURORADIOLOGY},
   title = {Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke},
   url = {https://link.springer.com/article/10.1007/s00234-022-02978-x},
   volume = {64},
   year = {2022}
}

TY  - JOUR
ID  - 2250060
AU  - Cimflová, Petra - Golan, Rotem - Ospel, Johanna M - Sojoudi, Alireza - Duszynski, Chris - Elebute, Ibukun - El-Hariri, Houssam - Mousavi, Seyed Hossein - Neto, Luis A Souto Maior - Pinky, Najratun - Beland, Benjamin - Bala, Fouzi - Kashani, Nima R - Hu, William - Joshi, Manish - Qiu, Wu - Menon, Bijoy K
PY  - 2022
TI  - Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke
JF  - NEURORADIOLOGY
VL  - 64
IS  - 12
SP  - 2245-2255
EP  - 2245-2255
PB  - SPRINGER
SN  - 00283940
KW  - Machine learning
KW  - Large vessel occlusion
KW  - Stroke
KW  - Automatic detection
UR  - https://link.springer.com/article/10.1007/s00234-022-02978-x
N2  - Purpose CT angiography (CTA) is the imaging standard for large vessel occlusion (LVO) detection in patients with acute ischemic stroke. StrokeSENS LVO is an automated tool that utilizes a machine learning algorithm to identify anterior large vessel occlusions (LVO) on CTA. The aim of this study was to test the algorithm's performance in LVO detection in an independent dataset. Methods A total of 400 studies (217 LVO, 183 other/no occlusion) read by expert consensus were used for retrospective analysis. The LVO was defined as intracranial internal carotid artery (ICA) occlusion and M1 middle cerebral artery (MCA) occlusion. Software performance in detecting anterior LVO was evaluated using receiver operator characteristics (ROC) analysis, reporting area under the curve (AUC), sensitivity, and specificity. Subgroup analyses were performed to evaluate if performance in detecting LVO differed by subgroups, namely M1 MCA and ICA occlusion sites, and in data stratified by patient age, sex, and CTA acquisition characteristics (slice thickness, kilovoltage tube peak, and scanner manufacturer). Results AUC, sensitivity, and specificity overall were as follows: 0.939, 0.894, and 0.874, respectively, in the full cohort; 0.927, 0.857, and 0.874, respectively, in the ICA occlusion cohort; 0.945, 0.914, and 0.874, respectively, in the M1 MCA occlusion cohort. Performance did not differ significantly by patient age, sex, or CTA acquisition characteristics. Conclusion The StrokeSENS LVO machine learning algorithm detects anterior LVO with high accuracy from a range of scans in a large dataset.
ER  -

CIMFLOVÁ, Petra, Rotem GOLAN, Johanna M OSPEL, Alireza SOJOUDI, Chris DUSZYNSKI, Ibukun ELEBUTE, Houssam EL-HARIRI, Seyed Hossein MOUSAVI, Luis A Souto Maior NETO, Najratun PINKY, Benjamin BELAND, Fouzi BALA, Nima R KASHANI, William HU, Manish JOSHI, Wu QIU a Bijoy K MENON. Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke. \textit{NEURORADIOLOGY}. NEW YORK: SPRINGER, 2022, roč.~64, č.~12, s.~2245-2255. ISSN~0028-3940. Dostupné z: https://dx.doi.org/10.1007/s00234-022-02978-x.

Podrobný výpis o publikaci