View in EDS HTML Full Text PDF Full Text

Deep learning-based white matter lesion volume on CT is associated with outcome after acute ischemic stroke.

Saved in:
Bibliographic Details
Title: Deep learning-based white matter lesion volume on CT is associated with outcome after acute ischemic stroke.
Authors: van Voorst, Henk1,2 (AUTHOR) h.vanvoorst@amsterdamumc.nl, Pitkänen, Johanna3 (AUTHOR), van Poppel, Laura1,2 (AUTHOR), de Vries, Lucas1,2,4 (AUTHOR), Mojtahedi, Mahsa1,2 (AUTHOR), Martou, Laura5 (AUTHOR), Emmer, Bart J.1 (AUTHOR), Roos, Yvo B. W. E. M.6 (AUTHOR), van Oostenbrugge, Robert7 (AUTHOR), Postma, Alida A.8 (AUTHOR), Marquering, Henk A.1,2 (AUTHOR), Majoie, Charles B. L. M.1 (AUTHOR), Curtze, Sami3 (AUTHOR), Melkas, Susanna3 (AUTHOR), Bentley, Paul5 (AUTHOR), Caan, Matthan W. A.2 (AUTHOR), Dippel, Diederik (AUTHOR), Majoie, Charles (AUTHOR), van der Lugt, Aad (AUTHOR), van Es, Adriaan (AUTHOR)
Source: European Radiology. Aug2024, Vol. 34 Issue 8, p5080-5093. 14p.
Subjects: Ischemic stroke, White matter (Nerve tissue), Intracerebral hematoma, Stroke patients, Intracranial hemorrhage, Deep learning
Abstract: Background: Intravenous thrombolysis (IVT) before endovascular treatment (EVT) for acute ischemic stroke might induce intracerebral hemorrhages which could negatively affect patient outcomes. Measuring white matter lesions size using deep learning (DL-WML) might help safely guide IVT administration. We aimed to develop, validate, and evaluate a DL-WML volume on CT compared to the Fazekas scale (WML-Faz) as a risk factor and IVT effect modifier in patients receiving EVT directly after IVT. Methods: We developed a deep-learning model for WML segmentation on CT and validated with internal and external test sets. In a post hoc analysis of the MR CLEAN No-IV trial, we associated DL-WML volume and WML-Faz with symptomatic-intracerebral hemorrhage (sICH) and 90-day functional outcome according to the modified Rankin Scale (mRS). We used multiplicative interaction terms between WML measures and IVT administration to evaluate IVT treatment effect modification. Regression models were used to report unadjusted and adjusted common odds ratios (cOR/acOR). Results: In total, 516 patients from the MR CLEAN No-IV trial (male/female, 291/225; age median, 71 [IQR, 62–79]) were analyzed. Both DL-WML volume and WML-Faz are associated with sICH (DL-WML volume acOR, 1.78 [95%CI, 1.17; 2.70]; WML-Faz acOR, 1.53 95%CI [1.02; 2.31]) and mRS (DL-WML volume acOR, 0.70 [95%CI, 0.55; 0.87], WML-Faz acOR, 0.73 [95%CI 0.60; 0.88]). Only in the unadjusted IVT effect modification analysis WML-Faz was associated with more sICH if IVT was given (p = 0.046). Neither WML measure was associated with worse mRS if IVT was given. Conclusion: DL-WML volume and WML-Faz had a similar relationship with functional outcome and sICH. Although more sICH might occur in patients with more severe WML-Faz receiving IVT, no worse functional outcome was observed. Clinical relevance statement: White matter lesion severity on baseline CT in acute ischemic stroke patients has a similar predictive value if measured with deep learning or the Fazekas scale. Safe administration of intravenous thrombolysis using white matter lesion severity should be further studied. Key Points: White matter damage is a predisposing risk factor for intracranial hemorrhage in patients with acute ischemic stroke but remains difficult to measure on CT. White matter lesion volume on CT measured with deep learning had a similar association with symptomatic intracerebral hemorrhages and worse functional outcome as the Fazekas scale. A patient-level meta-analysis is required to study the benefit of white matter lesion severity-based selection for intravenous thrombolysis before endovascular treatment. [ABSTRACT FROM AUTHOR]
Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 178483283
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep learning-based white matter lesion volume on CT is associated with outcome after acute ischemic stroke.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22van+Voorst%2C+Henk%22">van Voorst, Henk</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> h.vanvoorst@amsterdamumc.nl</i><br /><searchLink fieldCode="AR" term="%22Pitkänen%2C+Johanna%22">Pitkänen, Johanna</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22van+Poppel%2C+Laura%22">van Poppel, Laura</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22de+Vries%2C+Lucas%22">de Vries, Lucas</searchLink><relatesTo>1,2,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mojtahedi%2C+Mahsa%22">Mojtahedi, Mahsa</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Martou%2C+Laura%22">Martou, Laura</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Emmer%2C+Bart+J%2E%22">Emmer, Bart J.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Roos%2C+Yvo+B%2E+W%2E+E%2E+M%2E%22">Roos, Yvo B. W. E. M.</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22van+Oostenbrugge%2C+Robert%22">van Oostenbrugge, Robert</searchLink><relatesTo>7</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Postma%2C+Alida+A%2E%22">Postma, Alida A.</searchLink><relatesTo>8</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Marquering%2C+Henk+A%2E%22">Marquering, Henk A.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Majoie%2C+Charles+B%2E+L%2E+M%2E%22">Majoie, Charles B. L. M.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Curtze%2C+Sami%22">Curtze, Sami</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Melkas%2C+Susanna%22">Melkas, Susanna</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bentley%2C+Paul%22">Bentley, Paul</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Caan%2C+Matthan+W%2E+A%2E%22">Caan, Matthan W. A.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dippel%2C+Diederik%22">Dippel, Diederik</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Majoie%2C+Charles%22">Majoie, Charles</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22van+der+Lugt%2C+Aad%22">van der Lugt, Aad</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22van+Es%2C+Adriaan%22">van Es, Adriaan</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Radiology%22">European Radiology</searchLink>. Aug2024, Vol. 34 Issue 8, p5080-5093. 14p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Ischemic+stroke%22">Ischemic stroke</searchLink><br /><searchLink fieldCode="DE" term="%22White+matter+%28Nerve+tissue%29%22">White matter (Nerve tissue)</searchLink><br /><searchLink fieldCode="DE" term="%22Intracerebral+hematoma%22">Intracerebral hematoma</searchLink><br /><searchLink fieldCode="DE" term="%22Stroke+patients%22">Stroke patients</searchLink><br /><searchLink fieldCode="DE" term="%22Intracranial+hemorrhage%22">Intracranial hemorrhage</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Intravenous thrombolysis (IVT) before endovascular treatment (EVT) for acute ischemic stroke might induce intracerebral hemorrhages which could negatively affect patient outcomes. Measuring white matter lesions size using deep learning (DL-WML) might help safely guide IVT administration. We aimed to develop, validate, and evaluate a DL-WML volume on CT compared to the Fazekas scale (WML-Faz) as a risk factor and IVT effect modifier in patients receiving EVT directly after IVT. Methods: We developed a deep-learning model for WML segmentation on CT and validated with internal and external test sets. In a post hoc analysis of the MR CLEAN No-IV trial, we associated DL-WML volume and WML-Faz with symptomatic-intracerebral hemorrhage (sICH) and 90-day functional outcome according to the modified Rankin Scale (mRS). We used multiplicative interaction terms between WML measures and IVT administration to evaluate IVT treatment effect modification. Regression models were used to report unadjusted and adjusted common odds ratios (cOR/acOR). Results: In total, 516 patients from the MR CLEAN No-IV trial (male/female, 291/225; age median, 71 [IQR, 62–79]) were analyzed. Both DL-WML volume and WML-Faz are associated with sICH (DL-WML volume acOR, 1.78 [95%CI, 1.17; 2.70]; WML-Faz acOR, 1.53 95%CI [1.02; 2.31]) and mRS (DL-WML volume acOR, 0.70 [95%CI, 0.55; 0.87], WML-Faz acOR, 0.73 [95%CI 0.60; 0.88]). Only in the unadjusted IVT effect modification analysis WML-Faz was associated with more sICH if IVT was given (p = 0.046). Neither WML measure was associated with worse mRS if IVT was given. Conclusion: DL-WML volume and WML-Faz had a similar relationship with functional outcome and sICH. Although more sICH might occur in patients with more severe WML-Faz receiving IVT, no worse functional outcome was observed. Clinical relevance statement: White matter lesion severity on baseline CT in acute ischemic stroke patients has a similar predictive value if measured with deep learning or the Fazekas scale. Safe administration of intravenous thrombolysis using white matter lesion severity should be further studied. Key Points: White matter damage is a predisposing risk factor for intracranial hemorrhage in patients with acute ischemic stroke but remains difficult to measure on CT. White matter lesion volume on CT measured with deep learning had a similar association with symptomatic intracerebral hemorrhages and worse functional outcome as the Fazekas scale. A patient-level meta-analysis is required to study the benefit of white matter lesion severity-based selection for intravenous thrombolysis before endovascular treatment. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=178483283
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00330-024-10584-z
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 5080
    Subjects:
      – SubjectFull: Ischemic stroke
        Type: general
      – SubjectFull: White matter (Nerve tissue)
        Type: general
      – SubjectFull: Intracerebral hematoma
        Type: general
      – SubjectFull: Stroke patients
        Type: general
      – SubjectFull: Intracranial hemorrhage
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Deep learning-based white matter lesion volume on CT is associated with outcome after acute ischemic stroke.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: van Voorst, Henk
      – PersonEntity:
          Name:
            NameFull: Pitkänen, Johanna
      – PersonEntity:
          Name:
            NameFull: van Poppel, Laura
      – PersonEntity:
          Name:
            NameFull: de Vries, Lucas
      – PersonEntity:
          Name:
            NameFull: Mojtahedi, Mahsa
      – PersonEntity:
          Name:
            NameFull: Martou, Laura
      – PersonEntity:
          Name:
            NameFull: Emmer, Bart J.
      – PersonEntity:
          Name:
            NameFull: Roos, Yvo B. W. E. M.
      – PersonEntity:
          Name:
            NameFull: van Oostenbrugge, Robert
      – PersonEntity:
          Name:
            NameFull: Postma, Alida A.
      – PersonEntity:
          Name:
            NameFull: Marquering, Henk A.
      – PersonEntity:
          Name:
            NameFull: Majoie, Charles B. L. M.
      – PersonEntity:
          Name:
            NameFull: Curtze, Sami
      – PersonEntity:
          Name:
            NameFull: Melkas, Susanna
      – PersonEntity:
          Name:
            NameFull: Bentley, Paul
      – PersonEntity:
          Name:
            NameFull: Caan, Matthan W. A.
      – PersonEntity:
          Name:
            NameFull: Dippel, Diederik
      – PersonEntity:
          Name:
            NameFull: Majoie, Charles
      – PersonEntity:
          Name:
            NameFull: van der Lugt, Aad
      – PersonEntity:
          Name:
            NameFull: van Es, Adriaan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 09387994
          Numbering:
            – Type: volume
              Value: 34
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: European Radiology
              Type: main
ResultId 1