Effects of Ginkgo biloba on cerebral blood flow assessed by quantitative MR perfusion imaging: a pilot study

Abstract

Introduction: Extract of Ginkgo biloba (EGb), a dietary supplement used for a number of conditions including dementia, has been suggested to increase cerebral bloodflow (CBF). The purpose of this study was to determine if changes in CBF could be detected by dynamic susceptibility contrast-enhanced magnetic resonance imaging (DSC-MRI)in elderly human subjects taking EGb.

Methods: DSC-MRI was performed in nine healthy men(mean age 61±10 years) before and after 4 weeks of 60 mg EGb taken twice daily. One subject underwent six consecutive scans to evaluate intrasubject reproducibility. CBF values were computed before and after EGb, and analyzed at three different levels of spatial resolution, using voxel-based statistical parametric mapping (SPM), and regions of interest in different lobes, and all regions combined.

Results: Normalized intrasubject CBF (nCBF) measurements had a standard deviation of 7% and 4% in gray and white matter (WM) regions, respectively. SPM using an uncorrected, voxel-level threshold of P≤0.001 showed a small CBF increase in the left parietal-occipital region.CBF in individual lobar regions did not show any significant change post-EGb, but all regions combined showed a significant increase of non-normalized CBF after EGb (15% in white and 13% in gray matter, respectively, P≤0.0001).

Conclusion: nCBF measured by DSC-MRI has good intrasubject reproducibility. In this small cohort of normal elderly individuals, a mild increase in CBF is found in the left parietal-occipital WM after EGb, as well as a small but statistically significant increase in global CBF.

Fig. 1

A sample CBF map (without normalization) generated using the Penguin software in a 69-year-old man

Fig. 2

Box plots showing intrasubject variation of measurements of CBF in various lobar regions of each cerebral hemisphere after registration using the Talairach atlas, a without and b with normalization against mean CBF of the cerebellar WM. Each box encompasses the first to third quartiles, with error bars marking the full range of values, horizontal bar representing the median and x denoting the mean. GM is depicted in gray, and WM in white. From all regions, the absolute mean CBF of the cortical GM is 57.67±18.68 and of the WM 21.24±5.95. Average nCBF of the GM is 2.54±0.18 and of the WM 0.94±0.04

Fig. 3

Statistical parametric map of regional increased perfusion after Ginkgo administration (uncorrected P≤0.005). The red region representing hyperperfusion is localized to the left parietal–occipital WM. This result was demonstrated only in the “pre≤post” design matrix based on paired t test. The intensities of color-coding in the 3D rendering are weighted sum of t values, where the weights are proportional to the depth within the brain; that is, deeper regions will be shown with less intensities

Fig. 4

Box plots showing CBF values in various segmented lobar WM regions before and after Ginkgo administration: (a) non-normalized CBF values, (b) CBF values normalized to cerebellar WM CBF (nCBF). In all lobar regions (including cerebellum), there is a general trend of higher mean and median absolute CBF values after Ginkgo administration; however, this is not statistically significant when corrections for multiple comparisons are performed. This trend is not consistently observed after normalization, but still holds in more than 50% of the regions. If correction for multiple comparisons is not performed, a single ROI of the left occipital and parietal WM region shows significantly increased CBF and nCBF post-Ginkgo (see text)