A methodology for generating four-dimensional arterial spin labeling MR angiography virtual phantoms

Abstract Four-dimensional arterial spin labeling magnetic resonance angiography (4D ASL MRA) is a non-invasive medical imaging modality that can be used for anatomical and hemodynamic analysis of the cerebrovascular system. However, it generates a considerable amount of data, which is tedious to analyze visually. As an alternative, medical image processing methods can be used to process the data and present measurements of the geometry and blood flow in the cerebrovascular system to the user, such as vessel radius, tortuosity, blood flow volume, and transit time. Nevertheless, evaluating medical image processing methods developed for this modality requires annotated data, which can be time-consuming and expensive to obtain. Alternatively, virtual simulations are a faster and less expensive option that can be used for initial evaluation of image processing methods. The present work proposes a methodology for generating annotated 4D ASL MRA virtual phantoms, in different scenarios with different acquisition parameter settings. In each scenario, the phantoms are generated using real cerebrovascular geometries of healthy volunteers, where blood flow is simulated according to a mathematical model specifically designed to describe the signal observed in 4D ASL MRA images. Realistic noise is added using an homomorphic approach, designed to replicate noise characteristic of multi-coil acquisitions. In order to exemplify the utility of the phantoms, they are used to evaluate the accuracy of a method to estimate blood flow parameter values, such as relative blood volume and transit time, in different scenarios. The estimated values are then compared to its corresponding virtual ground-truth values. The accuracy of the results is ranked according to the average absolute error. The results of the experiments show that blood flow parameters can be more accurately estimated when blood is magnetically labeled for longer periods of time and when the datasets are acquired with higher temporal resolution. In summary, the present work describes a methodology to create annotated virtual phantoms, which represent a useful alternative for initial evaluation of medical image processing methods for 4D ASL MRA images.