Physics-Informed Graph Neural Networks to solve 1-D equations of blood flow
This study showcased the ability to calculate lumen area and blood flow rate in blood vessels within a given topology by seamlessly integrating 1-D blood flow with PIGNNs, using only blood flow velocity measurements. Moreover, this study is the first to compare the PIGNNs method with other classic Physics-Informed Neural Network (PINNs) approaches for blood flow simulation. Our findings highlight the potential to use this cost-effective and proficient tool to estimate real-time arterial pulse waves.
Authors
- Elnaz Ghajar-Rahimi
- Craig J. Goergen (ORCID: https://orcid.org/0000-0001-8883-7953)
- Miquel Aguirre (ORCID: https://orcid.org/0000-0003-1798-7908)
- Ahmet Şen (ORCID: https://orcid.org/0000-0003-1865-681X)
- Stéphane Avril (ORCID: https://orcid.org/0000-0002-8604-7736)
- Laurent Navarro (ORCID: https://orcid.org/0000-0002-8788-8027)
Institutions
- Inserm (FR)
- Purdue University West Lafayette (US)
- Mines Saint-Étienne (FR)
- Biologie, ingénierie et imagerie pour l'Ophtalmologie (FR)
- Université Jean Monnet (FR)
- Universitat Politècnica de Catalunya (ES)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2024-09-20
- DOI
- https://doi.org/10.1016/j.cmpb.2024.108427
- Citations
- 7
- Primary Topic
- Cardiovascular Health and Disease Prevention
- Type
- article
- Field-Weighted Citation Impact
- 2.81