Intra-Domain Task-Adaptive Transfer Learning to Determine Acute Ischemic Stroke Onset Time

TL;DR

This paper introduces a deep learning approach using intra-domain transfer learning on MRI data to classify stroke onset time, improving accuracy and inclusivity over previous models, with potential to aid treatment decisions.

Contribution

The study presents a novel intra-domain task-adaptive transfer learning method for classifying stroke onset time from MRI, outperforming models trained from scratch and previous approaches.

Findings

Achieved ROC-AUC of 0.74 for TSS < 4.5 hours classification

Pretrained models outperform models trained from scratch

Overall accuracy of 75.78% on broad patient cohort

Abstract

Treatment of acute ischemic strokes (AIS) is largely contingent upon the time since stroke onset (TSS). However, TSS may not be readily available in up to 25% of patients with unwitnessed AIS. Current clinical guidelines for patients with unknown TSS recommend the use of MRI to determine eligibility for thrombolysis, but radiology assessments have high inter-reader variability. In this work, we present deep learning models that leverage MRI diffusion series to classify TSS based on clinically validated thresholds. We propose an intra-domain task-adaptive transfer learning method, which involves training a model on an easier clinical task (stroke detection) and then refining the model with different binary thresholds of TSS. We apply this approach to both 2D and 3D CNN architectures with our top model achieving an ROC-AUC value of 0.74, with a sensitivity of 0.70 and a specificity of 0.81 for classifying TSS < 4.5 hours. Our pretrained models achieve better classification metrics than the models trained from scratch, and these metrics exceed those of previously published models applied to our dataset. Furthermore, our pipeline accommodates a more inclusive patient cohort than previous work, as we did not exclude imaging studies based on clinical, demographic, or image processing criteria. When applied to this broad spectrum of patients, our deep learning model achieves an overall accuracy of 75.78% when classifying TSS < 4.5 hours, carrying potential therapeutic implications for patients with unknown TSS.