Synthetic Perfusion Maps: Imaging Perfusion Deficits in DSC-MRI with Deep Learning
This work addresses the need for efficient and reliable perfusion imaging in acute ischemic stroke diagnosis, representing an incremental improvement over existing methods.
The authors tackled the problem of generating perfusion maps from raw dynamic susceptibility contrast-enhanced perfusion imaging data for acute ischemic stroke cases, achieving results comparable to clinical target maps with a model-free, fast, and less noisy approach.
In this work, we present a novel convolutional neural net- work based method for perfusion map generation in dynamic suscepti- bility contrast-enhanced perfusion imaging. The proposed architecture is trained end-to-end and solely relies on raw perfusion data for inference. We used a dataset of 151 acute ischemic stroke cases for evaluation. Our method generates perfusion maps that are comparable to the target maps used for clinical routine, while being model-free, fast, and less noisy.