From Brain Tissue Infarction at 24 Hours to Patient Functional Outcome at 90 Days Using Deep Learning

Abstract

Accurate functional outcome prediction shortly after the onset of stroke would enable more effective personalized care of stroke patients. A deep learning approach was developed that utilizes follow-up images at 24 h to predict the functional outcome 90 days after stroke onset. The method involves the use of a conventional U-net segmentation model that was trained to delineate the stroke lesion on CT images, with an additional branch integrated into the U-net’s bottom layer to extract features for a separately trained network that classifies cases into favorable (modified Rankin Score (mRS) = 0–2) or unfavorable outcomes (mRS = 3–6). The method was trained and validated using 3-fold cross-validation on a set of 240 images (training: 170; validation: 90). The lesion segmentation yielded an average Dice score of 0.458 and an average absolute volume error of 10.71 ml, while the binary mRS prediction obtained an overall accuracy of 88.6% on the training set and 58.0% on the validation set. Although there is much room for improvement, these results demonstrate the potential of deep learning approaches toward a promising decision-support tool for stroke outcome prediction.