arXiv:2509.15900v2 Announce Type: replace-cross Abstract: This work aims to predict blood flow with non-Newtonian viscosity in stenosed arteries using convolutional neural network (CNN) surrogate models. An alternating Schwarz domain decomposition method is proposed which uses CNN-based subdomain solvers. A universal subdomain solver (USDS) is trained on a single, fixed geometry and then applied for each subdomain solve in the Schwarz method. Results for two-dimensional stenotic arteries of varying shape and length for different inflow conditions are presented and statistically evaluated. One
The rapid advancement in AI, particularly CNNs and domain decomposition methods, allows for more sophisticated and efficient biomedical simulations previously infeasible or computationally expensive.
This development can significantly accelerate medical research, drug discovery, and treatment planning by providing highly accurate and fast simulation tools for complex biological systems like blood flow in arteries.
The ability to simulate non-Newtonian blood flow in stenosed arteries with high efficiency using CNN-based methods changes the landscape of computational fluid dynamics in medicine, reducing reliance on traditional, slower simulation techniques.
- · Medical Researchers
- · Pharmaceutical Industry
- · Biomedical Engineering
- · AI/ML in Healthcare
- · Traditional Computational Fluid Dynamics Software
- · Simulation Hardware reliant on brute-force computation
Improved diagnosis and personalized treatment strategies for cardiovascular diseases due to better predictive models.
Reduced need for animal testing and human trials for certain medical device or drug iterations.
Potential for real-time surgical guidance systems leveraging on-the-fly, high-fidelity blood flow simulations.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG