Accuracy and precision of quantitative DCE-MRI parameters: How should one estimate contrast concentration?

Introduction: Pharmacokinetic parameters derived from dynamic contrast-enhanced MRI (DCE-MRI) data are sensitive to acquisition and post-processing techniques, which makes it difficult to compare results obtained using different methods. In particular, one of the most important factors affecting estimation of model parameters is how to convert MRI signal intensities to contrast agent concentration. The purpose of our study was to quantitatively compare a linear signal-to-concentration conversion (LC) as an approximation and a non-linear conversion (NLC) based on the MRI signal equation, in terms of the accuracy and precision of the pharmacokinetic parameters in T-weighted DCE-MRI.

Materials And Methods: Numerical simulation studies were conducted to compare LC and NLC in terms of the accuracy and precision in contrast kinetic parameter estimation, and to evaluate their dependency on flip angle (FA), pre-contrast T (T) and arterial input function (AIF). In addition, the effect of the conversion method on the diagnostic accuracy was evaluated with 36 breast lesions (19 benign and 17 malignant).

Results: The transfer rate (K) estimated using LC and measured AIF (mAIF) were up to 38% higher than the true K values, while the LC K estimates with the presumed AIF (pAIF) were up to 7% lower than the true K values, when FA = 45°. When using a small FA, such as 12°, the LC K with pAIF had least sensitivity to the error in T compared to the K estimated using LC with mAIF, and NLC with pAIF or mAIF. The breast DCE-MRI study showed that both LC and NLC K were significantly different (p < 0.05) between the malignant and benign lesions. The effect size between benign and malignant values as measured by Cohen's d was 1.06 for LC K and 1.02 for NLC K.

Conclusion: The present study results show that, when precontrast T measurement is not available and a low FA is used for DCE-MRI, the uncertainty in the contrast kinetic parameter estimation can be reduced by using the LC method with pAIF, without compromising the diagnostic accuracy.