Aarhus University Seal / Aarhus Universitets segl

Comparison of classification methods for tissue outcome after ischaemic stroke

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

DOI

  • Ceren Tozlu, Université Lyon, Claude Bernard University Lyon 1, Hospices Civils de Lyon, CNRS, UMR5558, Laboratoire de Biométrie et de Biologie Évolutive, Équipe Biostatistique-Santé
  • ,
  • Brice Ozenne, Rigshospitalet
  • ,
  • Tae Hee Cho, Université Lyon 1
  • ,
  • Norbert Nighoghossian, Université Lyon 1
  • ,
  • Irene Klærke Mikkelsen
  • Laurent Derex, Université Lyon 1
  • ,
  • Marc Hermier, Université Lyon 1
  • ,
  • Salvador Pedraza, Hospital Universitari de Girona Dr. Josep Trueta
  • ,
  • Jens Fiehler, University Medical Center Hamburg-Eppendorf
  • ,
  • Leif Østergaard
  • Yves Berthezène, Univ of Arhus, Université Lyon 1
  • ,
  • Jean Claude Baron, University of Cambridge, Université Paris Descartes
  • ,
  • Delphine Maucort-Boulch, Université Lyon, Université Lyon 1, Hospices Civils de Lyon, CNRS, UMR5558, Laboratoire de Biométrie et de Biologie Évolutive, Équipe Biostatistique-Santé

In acute ischaemic stroke, identifying brain tissue at high risk of infarction is important for clinical decision-making. This tissue may be identified with suitable classification methods from magnetic resonance imaging data. The aim of the present study was to assess and compare the performance of five popular classification methods (adaptive boosting, logistic regression, artificial neural networks, random forest and support vector machine) in identifying tissue at high risk of infarction on human voxel-based brain imaging data. The classification methods were used with eight MRI parameters, including diffusion-weighted imaging and perfusion-weighted imaging obtained in 55 patients. The five criteria used to assess the performance of the methods were the area under the receiver operating curve (AUCroc), the area under the precision–recall curve (AUCpr), sensitivity, specificity and the Dice coefficient. The methods performed equally in terms of sensitivity and specificity, while the results of AUCroc and the Dice coefficient were significantly better for adaptive boosting, logistic regression, artificial neural networks and random forest. However, there was no statistically significant difference between the performances of these five classification methods regarding AUCpr, which was the main comparison metric. Machine learning methods can provide valuable prognostic information using multimodal imaging data in acute ischaemic stroke, which in turn can assist in developing personalized treatment decision for clinicians after a thorough validation of methods with an independent data set.

Original languageEnglish
JournalEuropean Journal of Neuroscience
Volume50
Issue10
Pages (from-to)3590-3598
Number of pages9
ISSN0953-816X
DOIs
Publication statusPublished - Nov 2019

    Research areas

  • brain ischaemia, classification, diffusion-weighted imaging, machine learning, magnetic resonance imaging, perfusion-weighted imaging

See relations at Aarhus University Citationformats

ID: 172548087