Keywords: AI/ML Software, Flow, Perfusion; Augmentation; Modeling
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.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords