Diagnostic performance of an algorithm for automated large vessel occlusion detection on CT angiography
© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ..
BACKGROUND: Machine learning algorithms hold the potential to contribute to fast and accurate detection of large vessel occlusion (LVO) in patients with suspected acute ischemic stroke. We assessed the diagnostic performance of an automated LVO detection algorithm on CT angiography (CTA).
METHODS: Data from the MR CLEAN Registry and PRESTO were used including patients with and without LVO. CTA data were analyzed by the algorithm for detection and localization of LVO (intracranial internal carotid artery (ICA)/ICA terminus (ICA-T), M1, or M2). Assessments done by expert neuroradiologists were used as reference. Diagnostic performance was assessed for detection of LVO and per occlusion location by means of sensitivity, specificity, and area under the curve (AUC).
RESULTS: We analyzed CTAs of 1110 patients from the MR CLEAN Registry (median age (IQR) 71 years (60-80); 584 men; 1110 with LVO) and of 646 patients from PRESTO (median age (IQR) 73 years (62-82); 358 men; 141 with and 505 without LVO). For detection of LVO, the algorithm yielded a sensitivity of 89% in the MR CLEAN Registry and a sensitivity of 72%, specificity of 78%, and AUC of 0.75 in PRESTO. Sensitivity per occlusion location was 88% for ICA/ICA-T, 94% for M1, and 72% for M2 occlusion in the MR CLEAN Registry, and 80% for ICA/ICA-T, 95% for M1, and 49% for M2 occlusion in PRESTO.
CONCLUSION: The algorithm provided a high detection rate for proximal LVO, but performance varied significantly by occlusion location. Detection of M2 occlusion needs further improvement.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:14 |
---|---|
Enthalten in: |
Journal of neurointerventional surgery - 14(2022), 8 vom: 20. Aug., Seite 794-798 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Luijten, Sven P R [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 18.07.2022 Date Revised 13.08.2022 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1136/neurintsurg-2021-017842 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM329566830 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM329566830 | ||
003 | DE-627 | ||
005 | 20231225205407.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1136/neurintsurg-2021-017842 |2 doi | |
028 | 5 | 2 | |a pubmed24n1098.xml |
035 | |a (DE-627)NLM329566830 | ||
035 | |a (NLM)34413245 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Luijten, Sven P R |e verfasserin |4 aut | |
245 | 1 | 0 | |a Diagnostic performance of an algorithm for automated large vessel occlusion detection on CT angiography |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 18.07.2022 | ||
500 | |a Date Revised 13.08.2022 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. | ||
520 | |a BACKGROUND: Machine learning algorithms hold the potential to contribute to fast and accurate detection of large vessel occlusion (LVO) in patients with suspected acute ischemic stroke. We assessed the diagnostic performance of an automated LVO detection algorithm on CT angiography (CTA) | ||
520 | |a METHODS: Data from the MR CLEAN Registry and PRESTO were used including patients with and without LVO. CTA data were analyzed by the algorithm for detection and localization of LVO (intracranial internal carotid artery (ICA)/ICA terminus (ICA-T), M1, or M2). Assessments done by expert neuroradiologists were used as reference. Diagnostic performance was assessed for detection of LVO and per occlusion location by means of sensitivity, specificity, and area under the curve (AUC) | ||
520 | |a RESULTS: We analyzed CTAs of 1110 patients from the MR CLEAN Registry (median age (IQR) 71 years (60-80); 584 men; 1110 with LVO) and of 646 patients from PRESTO (median age (IQR) 73 years (62-82); 358 men; 141 with and 505 without LVO). For detection of LVO, the algorithm yielded a sensitivity of 89% in the MR CLEAN Registry and a sensitivity of 72%, specificity of 78%, and AUC of 0.75 in PRESTO. Sensitivity per occlusion location was 88% for ICA/ICA-T, 94% for M1, and 72% for M2 occlusion in the MR CLEAN Registry, and 80% for ICA/ICA-T, 95% for M1, and 49% for M2 occlusion in PRESTO | ||
520 | |a CONCLUSION: The algorithm provided a high detection rate for proximal LVO, but performance varied significantly by occlusion location. Detection of M2 occlusion needs further improvement | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a CT Angiography | |
650 | 4 | |a stroke | |
650 | 4 | |a thrombectomy | |
700 | 1 | |a Wolff, Lennard |e verfasserin |4 aut | |
700 | 1 | |a Duvekot, Martijne H C |e verfasserin |4 aut | |
700 | 1 | |a van Doormaal, Pieter-Jan |e verfasserin |4 aut | |
700 | 1 | |a Moudrous, Walid |e verfasserin |4 aut | |
700 | 1 | |a Kerkhoff, Henk |e verfasserin |4 aut | |
700 | 1 | |a Lycklama A Nijeholt, Geert J |e verfasserin |4 aut | |
700 | 1 | |a Bokkers, Reinoud P H |e verfasserin |4 aut | |
700 | 1 | |a Yo, Lonneke S F |e verfasserin |4 aut | |
700 | 1 | |a Hofmeijer, Jeannette |e verfasserin |4 aut | |
700 | 1 | |a van Zwam, Wim H |e verfasserin |4 aut | |
700 | 1 | |a van Es, Adriaan C G M |e verfasserin |4 aut | |
700 | 1 | |a Dippel, Diederik W J |e verfasserin |4 aut | |
700 | 1 | |a Roozenbeek, Bob |e verfasserin |4 aut | |
700 | 1 | |a van der Lugt, Aad |e verfasserin |4 aut | |
700 | 0 | |a MR CLEAN Registry and PRESTO investigators |e verfasserin |4 aut | |
700 | 1 | |a Oostenbrugge, Robert J van |e investigator |4 oth | |
700 | 1 | |a Boiten, Jelis |e investigator |4 oth | |
700 | 1 | |a Vos, Jan Albert |e investigator |4 oth | |
700 | 1 | |a Jansen, Ivo Gh |e investigator |4 oth | |
700 | 1 | |a Mulder, Maxim Jhl |e investigator |4 oth | |
700 | 1 | |a Goldhoorn, Robert-Jan B |e investigator |4 oth | |
700 | 1 | |a Compagne, Kars Cj |e investigator |4 oth | |
700 | 1 | |a Kappelhof, Manon |e investigator |4 oth | |
700 | 1 | |a Schonewille, Wouter J |e investigator |4 oth | |
700 | 1 | |a Coutinho, Jonathan M |e investigator |4 oth | |
700 | 1 | |a Wermer, Marieke Jh |e investigator |4 oth | |
700 | 1 | |a Walderveen, Marianne Aa van |e investigator |4 oth | |
700 | 1 | |a Staals, Julie |e investigator |4 oth | |
700 | 1 | |a Martens, Jasper M |e investigator |4 oth | |
700 | 1 | |a Emmer, Bart J |e investigator |4 oth | |
700 | 1 | |a de Bruijn, Sebastiaan F |e investigator |4 oth | |
700 | 1 | |a Dijk, Lukas C van |e investigator |4 oth | |
700 | 1 | |a van der Worp, Bart |e investigator |4 oth | |
700 | 1 | |a Lo, Rob H |e investigator |4 oth | |
700 | 1 | |a Dijk, Ewoud J van |e investigator |4 oth | |
700 | 1 | |a Boogaarts, Hieronymus D |e investigator |4 oth | |
700 | 1 | |a Kort, Paul Lm de |e investigator |4 oth | |
700 | 1 | |a Tuijl, Julia van |e investigator |4 oth | |
700 | 1 | |a Peluso, Jo Jp |e investigator |4 oth | |
700 | 1 | |a Berg, Jan Sp van den |e investigator |4 oth | |
700 | 1 | |a Hasselt, Boudewijn Aam van |e investigator |4 oth | |
700 | 1 | |a Aerden, Leo Am |e investigator |4 oth | |
700 | 1 | |a Dallinga, René J |e investigator |4 oth | |
700 | 1 | |a Uyttenboogaart, Maarten |e investigator |4 oth | |
700 | 1 | |a Eshghi, Omid |e investigator |4 oth | |
700 | 1 | |a Schreuder, Tobien Hcml |e investigator |4 oth | |
700 | 1 | |a Heijboer, Roel Jj |e investigator |4 oth | |
700 | 1 | |a Keizer, Koos |e investigator |4 oth | |
700 | 1 | |a Hertog, Heleen M den |e investigator |4 oth | |
700 | 1 | |a Sturm, Emiel Jc |e investigator |4 oth | |
700 | 1 | |a Sprengers, Marieke Es |e investigator |4 oth | |
700 | 1 | |a Jenniskens, Sjoerd Fm |e investigator |4 oth | |
700 | 1 | |a Berg, René van den |e investigator |4 oth | |
700 | 1 | |a Yoo, Albert J |e investigator |4 oth | |
700 | 1 | |a Beenen, Ludo Fm |e investigator |4 oth | |
700 | 1 | |a Postma, Alida A |e investigator |4 oth | |
700 | 1 | |a Roosendaal, Stefan D |e investigator |4 oth | |
700 | 1 | |a van der Kallen, Bas Fw |e investigator |4 oth | |
700 | 1 | |a van den Wijngaard, Ido R |e investigator |4 oth | |
700 | 1 | |a Bot, Joost |e investigator |4 oth | |
700 | 1 | |a van Doormaal, Pieter-Jan |e investigator |4 oth | |
700 | 1 | |a Flach, Zwenneke |e investigator |4 oth | |
700 | 1 | |a Lingsma, Hester F |e investigator |4 oth | |
700 | 1 | |a Ghannouti, Naziha El |e investigator |4 oth | |
700 | 1 | |a Sterrenberg, Martin |e investigator |4 oth | |
700 | 1 | |a Puppels, Corina |e investigator |4 oth | |
700 | 1 | |a Pellikaan, Wilma |e investigator |4 oth | |
700 | 1 | |a Sprengers, Rita |e investigator |4 oth | |
700 | 1 | |a Elfrink, Marjan |e investigator |4 oth | |
700 | 1 | |a de Meris, Joke |e investigator |4 oth | |
700 | 1 | |a Geerlings, Annet |e investigator |4 oth | |
700 | 1 | |a Vemde, Gina van |e investigator |4 oth | |
700 | 1 | |a Simons, Tiny |e investigator |4 oth | |
700 | 1 | |a Rijswijk, Cathelijn van |e investigator |4 oth | |
700 | 1 | |a Messchendorp, Gert |e investigator |4 oth | |
700 | 1 | |a Bongenaar, Hester |e investigator |4 oth | |
700 | 1 | |a Bodde, Karin |e investigator |4 oth | |
700 | 1 | |a Kleijn, Sandra |e investigator |4 oth | |
700 | 1 | |a Lodico, Jasmijn |e investigator |4 oth | |
700 | 1 | |a Droste, Hanneke |e investigator |4 oth | |
700 | 1 | |a Wollaert, M |e investigator |4 oth | |
700 | 1 | |a Jeurrissen, D |e investigator |4 oth | |
700 | 1 | |a Bos, Ernas |e investigator |4 oth | |
700 | 1 | |a Drabbe, Yvonne |e investigator |4 oth | |
700 | 1 | |a Aaldering, Nicoline |e investigator |4 oth | |
700 | 1 | |a Zweedijk, Berber |e investigator |4 oth | |
700 | 1 | |a Khalilzada, Mostafa |e investigator |4 oth | |
700 | 1 | |a Venema, Esmee |e investigator |4 oth | |
700 | 1 | |a Chalos, Vicky |e investigator |4 oth | |
700 | 1 | |a Geuskens, Ralph R |e investigator |4 oth | |
700 | 1 | |a Straaten, Tim van |e investigator |4 oth | |
700 | 1 | |a Ergezen, Saliha |e investigator |4 oth | |
700 | 1 | |a Harmsma, Roger Rm |e investigator |4 oth | |
700 | 1 | |a Muijres, Daan |e investigator |4 oth | |
700 | 1 | |a Jong, Anouk de |e investigator |4 oth | |
700 | 1 | |a Hinsenveld, Wouter |e investigator |4 oth | |
700 | 1 | |a Berkhemer, Olvert A |e investigator |4 oth | |
700 | 1 | |a Huguet, J |e investigator |4 oth | |
700 | 1 | |a Groot, Pfc |e investigator |4 oth | |
700 | 1 | |a Mens, Marieke A |e investigator |4 oth | |
700 | 1 | |a Kranendonk, Katinka R |e investigator |4 oth | |
700 | 1 | |a Treurniet, Kilian M |e investigator |4 oth | |
700 | 1 | |a Tolhuijsen, Manon L |e investigator |4 oth | |
700 | 1 | |a Alves, Heitor |e investigator |4 oth | |
700 | 1 | |a Rozeman, Anouk D |e investigator |4 oth | |
700 | 1 | |a Vermeij, Frédérique H |e investigator |4 oth | |
700 | 1 | |a Alblas, Kees Cl |e investigator |4 oth | |
700 | 1 | |a Mulder, Laus Jmm |e investigator |4 oth | |
700 | 1 | |a Wijnhoud, Annemarie D |e investigator |4 oth | |
700 | 1 | |a Maasland, Lisette |e investigator |4 oth | |
700 | 1 | |a Eijkelenburg, Roeland Pj van |e investigator |4 oth | |
700 | 1 | |a Biekart, Marileen |e investigator |4 oth | |
700 | 1 | |a Willeboer, M L |e investigator |4 oth | |
700 | 1 | |a Buijck, Bianca |e investigator |4 oth | |
700 | 1 | |a Bakker, Jeannette |e investigator |4 oth | |
773 | 0 | 8 | |i Enthalten in |t Journal of neurointerventional surgery |d 2009 |g 14(2022), 8 vom: 20. Aug., Seite 794-798 |w (DE-627)NLM19772521X |x 1759-8486 |7 nnns |
773 | 1 | 8 | |g volume:14 |g year:2022 |g number:8 |g day:20 |g month:08 |g pages:794-798 |
856 | 4 | 0 | |u http://dx.doi.org/10.1136/neurintsurg-2021-017842 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 14 |j 2022 |e 8 |b 20 |c 08 |h 794-798 |