Reproducibility of quantitative CT brain perfusion measurements in patients with symptomatic unilateral carotid artery stenosis

Abstract

Background and purpose: To establish intraobserver and interobserver variability for regional measurement of CT brain perfusion (CTP) and to determine whether reproducibility can be improved by calculating perfusion ratios.

Materials and methods: CTP images were acquired in 20 patients with unilateral symptomatic carotid artery stenosis (CAS). We manually drew regions of interest (ROIs) in the cortical flow territories of the anterior (ACA), middle (MCA), and posterior (PCA) cerebral arteries and the basal ganglia in each hemisphere; recorded cerebral blood volume (CBV), cerebral blood flow (CBF), and mean transit time (MTT); and calculated ratios of perfusion values between symptomatic and asymptomatic hemisphere. We assessed intraobserver and interobserver variability by performing a Bland-Altman analysis of the relative differences between 2 observations and calculated SDs of relative differences (SDD(rel)) as a measure of reproducibility. We used an F test to assess significance of differences between SDD(rel) of absolute CTP values and CTP ratios, and the Levine test to compare the 4 perfusion territories.

Results: MTT was the most reproducible parameter (SDD(rel) <or= 10%). Intraobserver and interobserver variability were higher for absolute CTP values compared with CTP ratios for CBV (16%-17% versus 11%-16%) and CBF (18% versus 10%-13%) but not for MTT (5%-9%). Reproducibility was best in the MCA territory: SDD(rel) was <or=11% for perfusion ratios of all 3 parameters.

Conclusion: MTT is the most reproducible CTP parameter in patients with unilateral symptomatic CAS. Measurement variability in CBV and CBF can be improved if CTP ratios instead of CTP values are used. The MCA territory shows the least measurement variability.

Fig 1.

Analysis of manual outlined ROIs according to territorial division of Damasio. 1, ACA territory; 2, MCA territory; 3, basal ganglia; 4, PCA territory.

Fig 2.

Bland-Altman plots of the relative differences (interobserver variability, pooled data) against the mean absolute value for CBF (milliliters per 100 g per minute) (A), CBV (milliliters per 100 g) (B), and MTT (seconds) (C). The relative ΔCBV, ΔCBF, and ΔMTT indicate the difference between 2 observations divided by the mean of those 2 observations, given as a percentage. The thick line represents the mean bias, and the dotted lines indicate the upper and lower limits of agreement. These upper and lower limits of agreement for the relative differences were 37% and −37% for CBV, 38% and −43% for CBF, and 21% and −16% for MTT, respectively.