Using Data-Driven Methods to Improve Brain Blood Flow Measurements in Cerebrovascular Disease with Dynamic Imaging

Cerebrovascular reactivity (CVR) is a widely studied biomarker of cerebral hemodynamics, commonly used in risk stratification and treatment planning in patients with steno-occlusive disease (SOD). Conventional use relies on normalization of estimates to contralateral hemisphere reference values, which is unsuitable for bilateral or indeterminate distributions of disease. We report upon a custom data-driven approach leveraging random forest classifiers (RFc) to identify candidate voxels for normalization to facilitate interrogation outside conditions of known unilateral SOD.

We retrospectively analyzed 16 patients with unilateral SOD who underwent acetazolamide-augmented blood oxygen level- dependent-MRI and DSC perfusion. Three RFc models were trained by using leave-one-out cross-validation (LOOCV) to identify candidate voxels brain-wide whose CVR was within 10% of the normal hemispheric median: 1) all voxels; 2) gray matter only; and 3) white matter only. Model input features included time-to-maximum, mean transit time, CBF, and CBV from contemporaneous DSC. The median model-predicted reference cerebrovascular reactivity (CVRref) was compared with ground-truth medians in LOOCV, and its impact on threshold-based volumetric classification of CVR reduction assessed.

RFc models effectively predicted ground-truth CVR voxels, achieving median absolute percent differences of 12.8% (interquartile range [IQR]: 5.0%-18.9%) by using all voxels, 11.3% (IQR: 9.3%-16.1%) for gray matter, and 9.8% (IQR: 4.4%-16.9%) for white matter. Volumetric estimates of CVR reduction across thresholds for the models revealed excellent agreement between ground-truth and model estimates without statistically significant differences (P > .01), excepting lowest white matter CVR thresholds. Model use in a small pilot deployment of bilateral SOD cases demonstrated the potential utility, enabling voxelwise CVR assessment without reliance on contralateral reference.

We present a novel data-driven approach for normalizing CVR maps in patients with bilateral or indeterminate SOD. Using an RFc, our method provides an individualized, brain-wide reference CVR, expanding the utility of CVR estimates beyond the typical constraints of unilateral disease, and with potential application to other, similarly constrained scenarios such as for SPECT or PET hemodynamic studies.