Image2Flow: A proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data

• Tina Yao,

  Roles Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Visualization, Writing – original draft

  Affiliation Institute of Cardiovascular Science, University College London, London, United Kingdom

  https://orcid.org/0000-0003-0470-311X

  ⨯
• Endrit Pajaziti,

  Roles Methodology, Writing – review & editing

  Affiliation Institute of Cardiovascular Science, University College London, London, United Kingdom

  ⨯
• Michael Quail,

  Roles Data curation, Writing – review & editing

  Affiliation Institute of Cardiovascular Science, University College London, London, United Kingdom

  ⨯
• Silvia Schievano,

  Roles Writing – review & editing

  Affiliation Institute of Cardiovascular Science, University College London, London, United Kingdom

  ⨯
• Jennifer Steeden ,

  Contributed equally to this work with: Jennifer Steeden, Vivek Muthurangu

  Roles Supervision, Writing – review & editing

  Affiliation Institute of Cardiovascular Science, University College London, London, United Kingdom

  https://orcid.org/0000-0002-9792-2022

  ⨯
• Vivek Muthurangu

  Contributed equally to this work with: Jennifer Steeden, Vivek Muthurangu

  Roles Conceptualization, Data curation, Methodology, Supervision, Writing – original draft, Writing – review & editing

  * E-mail: v.muthurangu@ucl.ac.uk

  Affiliation Institute of Cardiovascular Science, University College London, London, United Kingdom

  https://orcid.org/0000-0002-4292-6456

  ⨯