4D flow MRI for intracranial hemodynamics assessment in Alzheimer's disease

Abstract

Cerebral blood flow, arterial pulsation, and vasomotion play important roles in the transport of waste metabolites out of the brain. Impaired vasomotion results in reduced driving force for the perivascular/glymphatic clearance of beta-amyloid. Noninvasive cerebrovascular characteristic features that potentially assess these transport mechanisms are mean blood flow (MBF) and pulsatility index (PI). In this study, 4D flow MRI was used to measure intra-cranial flow features, particularly MBF, PI, resistive index (RI) and cross-sectional area in patients with Alzheimer's disease (AD), mild cognitive impairment and in age matched and younger cognitively healthy controls. Three-hundred fourteen subjects participated in this study. Volumetric, time-resolved phase contrast (PC) MRI data were used to quantify hemodynamic parameters from 11 vessel segments. Anatomical variants of the Circle of Willis were also cataloged. The AD population reported a statistically significant decrease in MBF and cross-sectional area, and also an increase in PI and RI compared to age matched cognitively healthy control subjects. The 4D flow MRI technique used in this study provides quantitative measurements of intracranial vessel geometry and the velocity of flow. Cerebrovascular characteristics features of vascular health such as pulsatility index can be extracted from the 4D flow MRI data.

Keywords: 4D flow MRI; Alzheimer’s disease; circle of Willis; mean blood flow; pulsatility index.

Figure 1.

PC VIPR data shown as (a) coronal, (b) axial, (c) sagittal MIP image of the PC angiogram and corresponding view of the segmented arteries with eleven flow analysis planes placed perpendicular to the vessel path (d, e, f). (g) Carotid terminus segmented with blood flow velocity vectors and distribution on the MCA. (h) Pulsatile flow waveform through the cardiac cycle recovered from the PC VIPR data.

Figure 2.

Pulsatility index throughout the intra cranial arterial tree shown as coronal, axial and sagittal color maps for an AD subject (a, b, c), an MCI subject (d, e, f,) and an age matched cognitively healthy control (g, h, i).

Figure 3.

Mean blood flow (mL/min) for 314 subjects including patients with AD, MCI, the normal age matched (old) control group, and a middle age control group. Left and right branches are reported together. The four populations were compared with each vessel segment using ANOVA followed by Tukey’s Honestly Significant Difference Procedure. For example: for the ICA inferior segment there are six comparisons which are outlined by the brackets. For each vessel segment, the mean flow is statistically different among all cohorts, with exception of 10 pairs. These pairs that were not found to be statistically significantly different are indicated by the symbol “°”.

Figure 4.

Pulsatility index for the 160 subjects in all four groups that had ECG information recorded. Out of the 36 pairwise comparisons all but the 12 pairs indicated by the “°” symbol showed statistical significance.

Figure 5.

Resistive index. Out of the 36 pairwise comparisons all but the 13 pairs indicated by the “°” symbol showed statistical significance.

Figure 6.

Cross-sectional area (mm²). Out of the 36 pairwise comparisons 18 pairs indicated by the “°” symbol did not showed statistical significance.