Cerebral perfusion in insulin resistance and type 2 diabetes

Abstract

Cerebral perfusion was evaluated in 87 subjects prospectively enrolled in three study groups-healthy controls (HC), patients with insulin resistance (IR) but not with diabetes, and type 2 diabetes mellitus (T2DM). Participants received a comprehensive 8-hour clinical evaluation and arterial spin labeling magnetic resonance imaging (MRI). In order of decreasing significance, an association was found between cerebral blood flow (CBF) and sex, waist circumference, diastolic blood pressure (BP), end tidal CO2, and verbal fluency score (R(2)=0.27, F=5.89, P<0.001). Mean gray-matter CBF in IR was 4.4 mL/100 g per minute lower than in control subjects (P=0.005), with no hypoperfusion in T2DM (P=0.312). Subjects with IR also showed no CO2 relationship (slope=-0.012) in the normocapnic range, in contrast to a strong relationship in healthy brains (slope=0.800) and intermediate response (slope=0.445) in diabetic patients. Since the majority of T2DM but few IR subjects were aggressively treated with blood glucose, cholesterol, and BP lowering medications, our finding could be attributed to the beneficial effect of these drugs.

Figure 1

The arterial spin labeling (ASL) signal was acquired at two 8-mm-thick axial locations. Left: upper slice at the level of the cingulate gyrus. Right: lower slice at the level of the middle temporal gyrus. bSSFP images show good gray-/white-matter tissue contrast that aids in segmentation. Note the availability of ample white matter to use as a reference region in the perfusion analysis.

Figure 2

Steps to generate white-matter (WM) and gray-matter (GM) regions of interest (ROIs). (A) A control image (left) and labeled image (right) acquired using the flow-sensitive alternating inversion recovery-based arterial spin labeling (ASL) sequence with bSSFP readout. (B) Two WM seeds placed by the user. (C) Ten small GM seeds are placed on the cortex. (D) The initial WM ROI in blue is constructed from voxels whose signal is within 10% of the seed, and restricted to the largest connected component. (E) The final WM ROI in green is obtained by removal of outliers from CBF histogram of the initial ROI. The aim is to eliminate voxels contaminated with WM lesions and partial volume of GM. (F) The initial GM ROI is obtained by selecting voxels whose signal is less than a threshold equal to the average of WM ROIs and GM seeds. (G) The final GM ROI in red is obtained by automatic boundary erosion to reduce partial volume effect followed by interactive removal of nonbrain areas (using an ‘electronic eraser'). Similar processing steps are applied to the temporal slice.

Figure 3

The relationship between cerebral blood flow (CBF) in mL/100 g per minute and variables: end tidal CO₂, waist circumference, verbal fluency test score, sex (mean and standard deviations for women 59.9±6.7 and for men 56.2±5.1), and diastolic blood pressure. Also plotted is the relationship between waist circumference and diastolic blood pressure.

Figure 4

The distribution of cerebral blood flow (CBF) in study groups: healthy control (HC), insulin resistance (IR), and type 2 diabetes mellitus (T2DM). The symbol *denotes significant difference in mean CBF according to Tukey's post hoc test, ANOVA. The dark lines in the middle of the boxes are the median values. The bottom (top) of the box indicates the 25th (75th) percentile, 95% of the data lie between the whiskers.

Figure 5

Gray-matter perfusion versus end-tidal CO₂ in study groups: healthy control (HC) (top), insulin resistance (IR) (middle), and type 2 diabetes mellitus (T2DM) (bottom).