WSSNet: aortic 4D Flow MRI wall shear stress estimation neural network

We developed WSSNet, a deep learning method to estimate aortic wall shear stress based on geometry and velocity from 4D Flow MRI.<div>The network was trained on synthetic data, generated from CFD simulations. </div><div><br></div><div>The input and output of the network consists of flattened representation of the aortic vessel surface, translated into velocity sheets and coordinate flatmaps. </div><div><br></div><div>Training dataset and pre-trained weights are provided here.</div><div>The network was trained using Tensorflow 2.3 with Keras backend.</div><div><br></div><div>Files:</div><div>1, wssnet: contains the network weights and optimisation parameters to restore/continue training</div><div>2. wssnet_dataset: contains the dataset files used for training the network</div><div><br></div><div>Please follow the instruction in our github page to use the files.</div><div><br></div><div><div><b>GitHub:</b></div><div>https://github.com/EdwardFerdian/WSSNet</div></div>