-
Something wrong with this record ?
Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients
J. Kral, M. Cabal, L. Kasickova, J. Havelka, T. Jonszta, O. Volny, M. Bar
Language English Country Germany
Document type Journal Article, Observational Study
Grant support
FNOs/2018
Ministerstvo Zdravotnictví Ceské Republiky
NLK
ProQuest Central
from 2002-01-01 to 1 year ago
CINAHL Plus with Full Text (EBSCOhost)
from 2008-01-01 to 1 year ago
Medline Complete (EBSCOhost)
from 2003-01-01 to 1 year ago
Nursing & Allied Health Database (ProQuest)
from 2002-01-01 to 1 year ago
Health & Medicine (ProQuest)
from 2002-01-01 to 1 year ago
- MeSH
- Computed Tomography Angiography methods MeSH
- Diffusion Magnetic Resonance Imaging MeSH
- Ischemic Stroke diagnostic imaging surgery MeSH
- Humans MeSH
- Cerebral Angiography methods MeSH
- Prospective Studies MeSH
- Radiographic Image Interpretation, Computer-Assisted methods MeSH
- Aged MeSH
- Sensitivity and Specificity MeSH
- Software MeSH
- Machine Learning * MeSH
- Thrombectomy * MeSH
- Check Tag
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Observational Study MeSH
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.
Department of Neuroradiology Faculty Hospital Ostrava Ostrava Czech Republic
Faculty of Medicine Masaryk University Brno Czech Republic
Faculty of Medicine Ostrava University Ostrava Czech Republic
References provided by Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc21020076
- 003
- CZ-PrNML
- 005
- 20210830101702.0
- 007
- ta
- 008
- 210728s2020 gw f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1007/s00234-020-02419-7 $2 doi
- 035 __
- $a (PubMed)32318775
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a gw
- 100 1_
- $a Kral, Jiri $u Department of Neurology, Faculty Hospital Ostrava, 17. Listopadu 1790/5, 708 52, Ostrava-Poruba, Czech Republic $u Faculty of Medicine, Masaryk University, Brno, Czech Republic
- 245 10
- $a Machine learning volumetry of ischemic brain lesions on CT after thrombectomy-prospective diagnostic accuracy study in ischemic stroke patients / $c J. Kral, M. Cabal, L. Kasickova, J. Havelka, T. Jonszta, O. Volny, M. Bar
- 520 9_
- $a 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.
- 650 _2
- $a senioři $7 D000368
- 650 _2
- $a mozková angiografie $x metody $7 D002533
- 650 _2
- $a CT angiografie $x metody $7 D000072226
- 650 _2
- $a difuzní magnetická rezonance $7 D038524
- 650 _2
- $a ženské pohlaví $7 D005260
- 650 _2
- $a lidé $7 D006801
- 650 _2
- $a ischemická cévní mozková příhoda $x diagnostické zobrazování $x chirurgie $7 D000083242
- 650 12
- $a strojové učení $7 D000069550
- 650 _2
- $a mužské pohlaví $7 D008297
- 650 _2
- $a prospektivní studie $7 D011446
- 650 _2
- $a rentgenový obraz - interpretace počítačová $x metody $7 D011857
- 650 _2
- $a senzitivita a specificita $7 D012680
- 650 _2
- $a software $7 D012984
- 650 12
- $a trombektomie $7 D017131
- 655 _2
- $a časopisecké články $7 D016428
- 655 _2
- $a pozorovací studie $7 D064888
- 700 1_
- $a Cabal, Martin $u Department of Neurology, Faculty Hospital Ostrava, 17. Listopadu 1790/5, 708 52, Ostrava-Poruba, Czech Republic
- 700 1_
- $a Kasickova, Linda $u Department of Neurology, Faculty Hospital Ostrava, 17. Listopadu 1790/5, 708 52, Ostrava-Poruba, Czech Republic $u Faculty of Medicine, Ostrava University, Ostrava, Czech Republic
- 700 1_
- $a Havelka, Jaroslav $u Department of Neuroradiology, Faculty Hospital Ostrava, Ostrava, Czech Republic
- 700 1_
- $a Jonszta, Tomas $u Department of Neuroradiology, Faculty Hospital Ostrava, Ostrava, Czech Republic
- 700 1_
- $a Volny, Ondrej $u International Clinical Research Centre, Stroke Research Program, St. Anne's University Hospital, Brno, Czech Republic $u Department of Neurology, St. Anne's University Hospital and Faculty of Medicine, Masaryk University, Brno, Czech Republic
- 700 1_
- $a Bar, Michal $u Department of Neurology, Faculty Hospital Ostrava, 17. Listopadu 1790/5, 708 52, Ostrava-Poruba, Czech Republic. michal.bar@fno.cz $u Faculty of Medicine, Ostrava University, Ostrava, Czech Republic. michal.bar@fno.cz
- 773 0_
- $w MED00003503 $t Neuroradiology $x 1432-1920 $g Roč. 62, č. 10 (2020), s. 1239-1245
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/32318775 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y p $z 0
- 990 __
- $a 20210728 $b ABA008
- 991 __
- $a 20210830101702 $b ABA008
- 999 __
- $a ok $b bmc $g 1690796 $s 1140522
- BAS __
- $a 3
- BAS __
- $a PreBMC
- BMC __
- $a 2020 $b 62 $c 10 $d 1239-1245 $e 20200422 $i 1432-1920 $m Neuroradiology $n Neuroradiology $x MED00003503
- GRA __
- $a FNOs/2018 $p Ministerstvo Zdravotnictví Ceské Republiky
- LZP __
- $a Pubmed-20210728
