Predicting stroke lesion and clinical outcome with random forests

Oskar Maier*, Heinz Handels

*Corresponding author for this work


The treatment of ischemic stroke requires fast decisions for which the potentially fatal risks of an intervention have to be weighted against the presumed benefits. Ideally, the treating physician could predict the outcome under different circumstances beforehand and thus make an informed treatment decision. To this end, this article presents two new methods: one for lesion outcome and one for clinical outcome prediction from multispectral magnetic resonance sequences. After extracting tailored image features, a random forest classifier respectively regressor is trained. Both approaches were submitted to the Ischemic Stroke Lesion Segmentation (ISLES) 2017 challenge and obtained a first and third place. The outcome underlines the robustness of our designed features and stresses the approach’s resilience against overfitting when faced with small training datasets.

Original languageEnglish
Title of host publicationBrainLes 2016: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
EditorsAlessandro Crimi, Bjoern Menze, Oskar Maier, Mauricio Reyes, Stefan Winzeck, Heinz Handels
Number of pages12
Volume10154 LNCS
PublisherSpringer, Cham
Publication date12.04.2016
ISBN (Print)978-3-319-55523-2
ISBN (Electronic)978-3-319-55524-9
Publication statusPublished - 12.04.2016
Event19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2016
- Athens, Greece
Duration: 17.10.201621.10.2016


Dive into the research topics of 'Predicting stroke lesion and clinical outcome with random forests'. Together they form a unique fingerprint.

Cite this