Liver DCE-MRI registration based on sparse recovery de-enhanced curves

The challenge of dynamic contrast-enhanced MRI (DCE-MRI) registration is the huge intensity changes caused by contrast agent injections. These changes may lead to the unrealistic deformation of contrast enhancement regions by traditional intensity-based registration algorithms. In this study, we construct and register the de-enhanced time-series, which are consisted of a series of “non-contrast” curves (only including motion) by sparse representation with a specially constructed dictionary. Furthermore, we combine an intensity-invariant similarity, residual complexity, into the cost function of our registration algorithm and apply iterative de-enhancing and registration strategy to improve the robustness and accuracy. Our registration algorithm is conducted on the clinical data of liver DCE-MRI. Experiment results demonstrate that our proposed method has an imporved registration performance.