ISLES'24 -- A Real-World Longitudinal Multimodal Stroke Dataset

TL;DR

This paper introduces ISLES'24, a comprehensive longitudinal multimodal stroke dataset with imaging and clinical data over multiple time points, enabling improved machine learning models for stroke diagnosis and prognosis.

Contribution

It provides the first large-scale, multi-time-point stroke dataset with multimodal imaging and clinical data, facilitating advanced machine learning research.

Findings

Dataset includes 245 cases with multimodal imaging and clinical data.

Enables development of models for lesion identification and prognosis prediction.

Supports longitudinal analysis of stroke evolution and outcomes.

Abstract

Stroke remains a leading cause of global morbidity and mortality, imposing a heavy socioeconomic burden. Advances in endovascular reperfusion therapy and CT and MR imaging for treatment guidance have significantly improved patient outcomes. Developing machine learning algorithms that can create accurate models of brain function from stroke images for tasks like lesion identification and tissue survival prediction requires large, diverse, and well annotated public datasets. While several high-quality image datasets in stroke exist, they include only single time point data. Data over different time points are essential to accurately identify lesions and predict prognosis. Here, we provide comprehensive longitudinal stroke data, including (sub-)acute CT imaging with angiography and perfusion, follow-up MRI after 2-9 days, and acute and longitudinal clinical data up to a three-month outcome. The dataset also includes vessel occlusion masks from acute CT angiography and delineated infarction masks in follow-up MRI. This multicenter dataset consists of 245 cases and is a solid basis for developing powerful machine-learning algorithms to facilitate clinical decision-making.