Intracranial hemodynamic changes during adult moyamoya disease progression

Abstract

Background and purpose: This study evaluated the changes in blood flow velocity in the anterior and posterior intracranial circulations according to the progression of moyamoya disease in adult patients.

Methods: We evaluated Suzuki's angiographic stage and mean blood flow velocity (MBFV) changes in intracranial vessels from both sides in 19 adult moyamoya patients. We then analyzed the linearity of MBFV changes from early to late moyamoya stages in each intracranial vessel using piecewise linear regression models.

Results: The MBFV in the middle cerebral artery, terminal internal carotid artery, and anterior cerebral artery increased non linearly until stage III, and then decreased progressively up to stage VI. The ophthalmic artery also showed nonlinear velocity changes, with an increase in MBFV up to stage IV, followed by a decrease in MBFV up to stage VI. The MBFV of the basilar artery increased linearly from a normal velocity at an early moyamoya stage to a stenotic velocity at a late stage. There was no statistically significant regression model for the relationship between the MBFV in the posterior cerebral artery and moyamoya stage.

Conclusions: The nonlinear and/or linear MBFV changes associated with variable intracranial vessels might be useful in initial and follow-up evaluations of different stages of moyamoya disease.

Keywords: Cerebral blood flow; Moyamoya disease; Transcranial Doppler.

Figure 1

Best-fit piecewise linear regression models for hemodynamic changes in the anterior intracranial circulation at the carotid fork region. There were significant piecewise linear models for the relationship of the middle cerebral artery (MCA) (p<0.0001, R²=63%) (A), anterior cerebral artery (ACA) (p<0.0001, R²=52.60%) (B), and terminal intracranial artery (p=0.0001, R²=42.70%) (C) with the knot point at stage III.

Figure 2

Best-fit piecewise linear regression models for hemodynamic changes in the (ophthalmic artery) OA and the siphon region of the internal carotid artery (ICA-siphon). There were significant piecewise regression models for the OA (p=0.0002, R²=40.20%) (A) with the knot point at stage IV, and for the ICA-siphon (p=0.0163, R²=15.10%) (B) with no knot point in any moyamoya stage.

Figure 3

Best-fit piecewise linear regression models for hemodynamic changes in the posterior intracranial circulation. There was no significant piecewise linear model for the PCA in advanced moyamoya stages (A), and there was a continuously increasing linear regression model for the basilar artery (BA) (p=0.0009, R²=48.90%) (B) with no knot point in any moyamoya stage.

Figure 4

Combined non linear and linear hemodynamic changes in the intracranial circulation during moyamoya disease progression. The linear or nonlinear changes in the mean blood flow velocity (MBFV) observed in each vessel were adjusted according to the criteria for stenotic and markedly decreased MBFV for each examined vessel. 'Stenosis' means an MBFV exceeding the upper limit of the normal range for each examined vessel. 'Marked decrease' means an MBFV of lower than the lower normal limit for each examined vessel.