Improved multi-parametric prediction of tissue outcome in acute ischemic stroke patients using spatial features

TY - JOUR

T1 - Improved multi-parametric prediction of tissue outcome in acute ischemic stroke patients using spatial features

AU - Grosser, Malte

AU - Gellißen, Susanne

AU - Borchert, Patrick

AU - Sedlacik, Jan

AU - Nawabi, Jawed

AU - Fiehler, Jens

AU - Forkert, Nils Daniel

PY - 2020

Y1 - 2020

N2 - INTRODUCTION: In recent years, numerous methods have been proposed to predict tissue outcome in acute stroke patients using machine learning methods incorporating multiparametric imaging data. Most methods include diffusion and perfusion parameters as image-based parameters but do not include any spatial information although these parameters are spatially dependent, e.g. different perfusion properties in white and gray brain matter. This study aims to investigate if including spatial features improves the accuracy of multi-parametric tissue outcome prediction.MATERIALS AND METHODS: Acute and follow-up multi-center MRI datasets of 99 patients were available for this study. Logistic regression, random forest, and XGBoost machine learning models were trained and tested using acute MR diffusion and perfusion features and known follow-up lesions. Different combinations of atlas coordinates and lesion probability maps were included as spatial information. The stroke lesion predictions were compared to the true tissue outcomes using the area under the receiver operating characteristic curve (ROC AUC) and the Dice metric.RESULTS: The statistical analysis revealed that including spatial features significantly improves the tissue outcome prediction. Overall, the XGBoost and random forest models performed best in every setting and achieved state-of-the-art results regarding both metrics with similar improvements achieved including Montreal Neurological Institute (MNI) reference space coordinates or voxel-wise lesion probabilities.CONCLUSION: Spatial features should be integrated to improve lesion outcome prediction using machine learning models.

AB - INTRODUCTION: In recent years, numerous methods have been proposed to predict tissue outcome in acute stroke patients using machine learning methods incorporating multiparametric imaging data. Most methods include diffusion and perfusion parameters as image-based parameters but do not include any spatial information although these parameters are spatially dependent, e.g. different perfusion properties in white and gray brain matter. This study aims to investigate if including spatial features improves the accuracy of multi-parametric tissue outcome prediction.MATERIALS AND METHODS: Acute and follow-up multi-center MRI datasets of 99 patients were available for this study. Logistic regression, random forest, and XGBoost machine learning models were trained and tested using acute MR diffusion and perfusion features and known follow-up lesions. Different combinations of atlas coordinates and lesion probability maps were included as spatial information. The stroke lesion predictions were compared to the true tissue outcomes using the area under the receiver operating characteristic curve (ROC AUC) and the Dice metric.RESULTS: The statistical analysis revealed that including spatial features significantly improves the tissue outcome prediction. Overall, the XGBoost and random forest models performed best in every setting and achieved state-of-the-art results regarding both metrics with similar improvements achieved including Montreal Neurological Institute (MNI) reference space coordinates or voxel-wise lesion probabilities.CONCLUSION: Spatial features should be integrated to improve lesion outcome prediction using machine learning models.

KW - Acute Disease

KW - Aged

KW - Algorithms

KW - Area Under Curve

KW - Brain Infarction/diagnosis

KW - Female

KW - Humans

KW - Magnetic Resonance Imaging

KW - Male

KW - Middle Aged

KW - Models, Theoretical

KW - ROC Curve

KW - Stroke/diagnosis

U2 - 10.1371/journal.pone.0228113

DO - 10.1371/journal.pone.0228113

M3 - SCORING: Journal article

C2 - 31978179

VL - 15

SP - e0228113

JO - PLOS ONE

JF - PLOS ONE

SN - 1932-6203

IS - 1

ER -