StrokeTimer: Robust Representation Learning for Ischemic Stroke Onset-Time Estimation from Non-contrast CT
2026-06-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed StrokeTimer, a computer program that looks at brain scans to help estimate how long ago a stroke started, which is important for deciding treatment. Because the initial signs of a stroke on standard CT scans are often very subtle, and there is a lot of variation in data from different hospitals and scanners, the authors used special learning techniques to improve detection. They tested StrokeTimer on large collections of stroke images and found it performed much better than previous methods. Their work shows promise for aiding doctors in making faster and better treatment decisions for stroke patients.
Ischemic strokeReperfusion therapyNon-contrast CT (NCCT)Onset time estimationSelf-supervised learningContrastive learningMacro AUCBrain imagingRadiological biomarkersStroke treatment
Authors
Weiru Wang, Susanne G. H. Olthuis, Elizaveta Lavrova, Robert J. van Oostenbrugge, Charles B. L. M. Majoie, Wim H. van Zwam, Ruisheng Su
Abstract
Ischemic stroke is a major global disease. Treatment decisions are highly time-sensitive, as eligibility for reperfusion therapies relies on the interval between stroke onset and intervention. However, the true onset time is often uncertain in clinical practice, necessitating imaging-based assessment of tissue age as a surrogate marker. Early ischemic changes on routinely acquired non-contrast CT (NCCT) are often subtle, and real-world clinical datasets exhibit pronounced onset-time class imbalance and center-scanner-related heterogeneity. In this work, we propose StrokeTimer, a fully automated framework for onset-time estimation in acute ischemic stroke. StrokeTimer integrates self-supervised disentanglement learning with energy-guided contrastive learning to capture subtle ischemic patterns while addressing long-tailed data distributions under acquisition variability. Onset time is categorized into three clinically relevant windows: <4.5 h, 4.5-6 h, and >6 h. Experimental results on a large multi-center NCCT dataset from two national cohorts, MR CLEAN Registry and MR CLEAN LATE, show that StrokeTimer achieves a macro AUC of 0.69 and a macro F1-score of 0.57, improving the strongest baseline by nearly 50% (p < 0.005). In this realistic, challenging setting, representative baseline approaches exhibit near-chance macro performance. Model explanations further highlight subtle gray-white matter blurring and hypodense regions consistent with established radiological biomarkers. These findings demonstrate the potential of StrokeTimer to support treatment decision-making in acute ischemic stroke. Code is available at https://github.com/BrainVas/StrokeTimer.