Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder

TL;DR

This paper introduces a novel spatiotemporal diffusion autoencoder that generates meaningful stroke representations from CT images, improving prediction of stroke outcomes and evolution over time.

Contribution

It applies diffusion probabilistic models to create a self-supervised, semantically rich stroke representation and extends it for longitudinal data, enhancing outcome prediction accuracy.

Findings

Achieves top performance in next-day severity prediction

Outperforms existing methods in functional outcome prediction

Effective on multi-center, minimally labeled dataset

Abstract

Stroke is a major cause of death and disability worldwide. Accurate outcome and evolution prediction has the potential to revolutionize stroke care by individualizing clinical decision-making leading to better outcomes. However, despite a plethora of attempts and the rich data provided by neuroimaging, modelling the ultimate fate of brain tissue remains a challenging task. In this work, we apply recent ideas in the field of diffusion probabilistic models to generate a self-supervised semantically meaningful stroke representation from Computed Tomography (CT) images. We then improve this representation by extending the method to accommodate longitudinal images and the time from stroke onset. The effectiveness of our approach is evaluated on a dataset consisting of 5,824 CT images from 3,573 patients across two medical centers with minimal labels. Comparative experiments show that our method achieves the best performance for predicting next-day severity and functional outcome at discharge.