Removing Large Vessels is Essential for the Accurate Estimation of Tissue Flow

Motivation: To investigate the contribution of large vessels to the accuracy of tissue flow in kinetic parameter mapping. Goal(s): Compare the accuracy of quantitative transport mapping (QTM) deep learning method (QTMnet) with and without large vessel augmentations in its training data. Approach: The simulated tissue data for QTMnet training is further augmented by adding simulated large vessels. We then evaluated model performance on ex vivo liver flow data with the ground truth total tissue flow. Results: Augmented QTMnet performs the best over the whole liver ROI (4.16% ± 44.33%) when compared to QTMnet (299.6% ± 91.6%) and conventional tracer kinetics estimations (211.3%±126.3%) respectively. Impact: We show that large vessel flow must be removed from tissue perfusion maps. In QTMnet, which trains a deep learning model on synthetic data to obtain blood flow, this can be achieved with large vessel augmentations of the training data.