Data Science of Stroke Imaging and Enlightenment of the Penumbra

Abstract

Imaging protocols of acute ischemic stroke continue to hold significant uncertainties regarding patient selection for reperfusion therapy with thrombolysis and mechanical thrombectomy. Given that patient inclusion criteria can easily introduce biases that may be unaccounted for, the reproducibility and reliability of the patient screening method is of utmost importance in clinical trial design. The optimal imaging screening protocol for selection in targeted populations remains uncertain. Acute neuroimaging provides a snapshot in time of the brain parenchyma and vasculature. By identifying the at-risk but still viable penumbral tissue, imaging can help estimate the potential benefit of a reperfusion therapy in these patients. This paper provides a perspective about the assessment of the penumbral tissue in the context of acute stroke and reviews several neuroimaging models that have recently been developed to assess the penumbra in a more reliable fashion. The complexity and variability of imaging features and techniques used in stroke will ultimately require advanced data driven software tools to provide quantitative measures of risk/benefit of recanalization therapy and help aid in making the most favorable clinical decisions.

Preserved Collateral Blood Flow in the Endovascular M2CAO Model Allows for Clinically Relevant Profiling of Injury Progression in Acute Ischemic Stroke

“…Previous studies describe a highly variable degree of ischemic lesion growth in early human AIS [1–3], with DWI lesion expansion occurring in around 70% of AIS cases and predominantly in patients with large perfusion mismatches in the acute phase [13, 32–33]. We report a longitudinal DWI/PWI mismatch profile of 11 percentage points of ADC lesion expansion relative to the size of the initially hypoperfused cortical tissue supplied by the MCA, with the volume fraction approximately 27% at 600 min MC2CAO (Fig 7B).…”

“…It is now understood that the rate of infarction progression is heterogeneous between AIS patients, and that slow infarction growth rates are associated with a higher potential to form a significant penumbra, and with improved clinical outcomes following recanalization treatment [1–3]. In cases of rapidly expanding malignant infarction [4–5], however, acute intervention is not appropriate, due to the unwarranted risk of adverse complications [6].…”

Clinical-Radiological Parameters Improve the Prediction of the Thrombolysis Time Window by Both MRI Signal Intensities and DWI-FLAIR Mismatch

“…A general problem of imaging biomarkers in acute stroke is the heterogeneity of stroke [14] . Stroke MRI can only provide a snapshot of each individual stroke progression.…”

“…These patients are to date excluded from thrombolytic treatment [11,12] . Several strategies to identify patients eligible for thrombolysis by MRI have been investigated [13,14] . One promising approach is to use quantitative relative signal intensities of DWI and FLAIR imaging.…”

Deep learning guided stroke management: a review of clinical applications

“…Several studies have shown that some patients may benefit from thrombolysis and/or recanalization if carried out within 3–4.5 hours after a stroke 2. Not all patients benefit from rapid intervention, however, and determining which patients would benefit is one of the major challenges for interventional stroke management 7. Without clear clinical features for guidance or a solid biological rationale for which neurons may regain functional capacity after ischemic injury, a significant amount of attention has been paid to using neuroimaging to assess potential benefit by identifying areas of ischemia that have not yet experienced cellular death 8…”