Feasibility and measurement precision of 3D quantitative blood flow mapping of the prostate using dynamic contrast-enhanced multi-slice CT

Abstract

We have developed a 3D dynamic contrast-enhanced (DCE) multislice CT protocol that covers the complete prostate. The DCE-CT data are subsequently analysed using the adiabatic approximation of the tissue homogeneity model resulting in five 3D quantitative maps of blood flow, mean transit time, extraction fraction, extracellular extravascular space and delay time. The purpose of this study was to establish the feasibility of determining these parameters in the prostate with a spatial resolution as high as approximately 0.1 cc as well as a good measurement precision. The precision of the parameter estimation as a function of noise level is determined by a Monte Carlo-based method that simulates the effect of noise present in the data. We find that the precision depends on the value of the flow and transit time, where a higher value is favourable. At a noise level of 4 HU in combination with a peak enhancement in the iliac arteries of approximately 300 HU the 95% confidence intervals are sufficiently small to discriminate whether a parameter value is above or below a given threshold. We have collected and analysed the noise level in the DCE-data of five patients. A noise level of 3.8 HU on average can be obtained by averaging to a voxel volume of 4.5 x 4.5 x 5 mm(3) = 0.1 cc. Analysis of the parameter maps shows that it is feasible to detect both small and large lesions, as well as irregularly shaped lesions.