Tissue Outcome Prediction in Patients with Proximal Vessel Occlusion and Mechanical Thrombectomy Using Logistic Models

Research output: Contribution to journalResearch articleContributedpeer-review


  • Florian Welle - , Leipzig University (Author)
  • Kristin Stoll - , Leipzig University (Author)
  • Christina Gillmann - , Leipzig University (Author)
  • Jeanette Henkelmann - , Leipzig University (Author)
  • Gordian Prasse - , Leipzig University (Author)
  • Daniel P.O. Kaiser - , Institute and Polyclinic of Diagnostic and Interventional Neuroradiology, TUD Dresden University of Technology (Author)
  • Elias Kellner - , University of Freiburg (Author)
  • Marco Reisert - , University of Freiburg (Author)
  • Hans R. Schneider - , Leipzig University (Author)
  • Julian Klingbeil - , Leipzig University (Author)
  • Anika Stockert - , Leipzig University (Author)
  • Donald Lobsien - , Leipzig University, Fresenius AG (Author)
  • Karl Titus Hoffmann - , Leipzig University (Author)
  • Dorothee Saur - , Leipzig University (Author)
  • Max Wawrzyniak - , Leipzig University (Author)


Perfusion CT is established to aid selection of patients with proximal intracranial vessel occlusion for thrombectomy in the extended time window. Selection is mostly based on simple thresholding of perfusion parameter maps, which, however, does not exploit the full information hidden in the high-dimensional perfusion data. We implemented a multiparametric mass-univariate logistic model to predict tissue outcome based on data from 405 stroke patients with acute proximal vessel occlusion in the anterior circulation who underwent mechanical thrombectomy. Input parameters were acute multimodal CT imaging (perfusion, angiography, and non-contrast) as well as basic demographic and clinical parameters. The model was trained with the knowledge of recanalization status and final infarct localization. We found that perfusion parameter maps (CBF, CBV, and Tmax) were sufficient for tissue outcome prediction. Compared with single-parameter thresholding-based models, our logistic model had comparable volumetric accuracy, but was superior with respect to topographical accuracy (AUC of receiver operating characteristic). We also found higher spatial accuracy (Dice index) in an independent internal but not external cross-validation. Our results highlight the value of perfusion data compared with non-contrast CT, CT angiography and clinical information for tissue outcome-prediction. Multiparametric logistic prediction has high potential to outperform the single-parameter thresholding-based approach. In the future, the combination of tissue and functional outcome prediction might provide an individual biomarker for the benefit from mechanical thrombectomy in acute stroke care.


Original languageEnglish
JournalTranslational stroke research
Publication statusPublished - 2023

External IDs

PubMed 37249761
Mendeley 797ef3b6-966a-3b59-b167-173add1b20e1
ORCID /0000-0001-5258-0025/work/150330305



  • Computed tomography, Perfusion, Prediction, Stroke, Tissue outcome