Predictive stress analysis in simplified spinal disc model using physics-informed neural networks

被引：0

作者：

Kim, Kwang Hyeon ^{[1
]}

Koo, Hae-Won ^{[2
]}

Lee, Byung-Jou ^{[2
]}

机构：

[1] Inje Univ, Ilsan Paik Hosp, Clin Res Support Ctr, Goyang, South Korea

[2] Inje Univ, Coll Med, Ilsan Paik Hosp, Dept Neurosurg, Goyang, South Korea

来源：

COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING | 2025年

基金：

新加坡国家研究基金会;

关键词：

Physics-informed neural networks; spinal disc modeling; stress prediction; biomechanics; NUCLEUS PULPOSUS; BIOMECHANICS; BEHAVIOR;

D O I：

10.1080/10255842.2025.2471504

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This study develops a physics-informed neural network (PINN) model to predict stress distribution in a simplified spinal disc structure. The model incorporates 3D spatial inputs and enforces equilibrium conditions through a custom loss function. Trained on synthetic elasticity-based data, it achieves an MAE of 0.026 and an R-2 of 74.6%. Stress patterns under various loading conditions were visualized, with peak stress occurring at z = 1 under top compression. Results demonstrate PINNs' potential for biomechanical modeling, improving predictive accuracy in spinal biomechanics and informing clinical interventions.

引用

页数：13

共 31 条

[1] Arzani A., Wang J.-X., D'Souza R.M., Uncovering near-wall blood flow from sparse data with physics-informed neural networks, Phys Fluids, 33, 7, (2021)
[2] Bolandi H., Sreekumar G., Li X., Lajnef N., Boddeti V.N., Physics informed neural network for dynamic stress prediction, Appl Intell, 53, 22, pp. 26313-26328, (2023)
[3] Cuomo S., Di Cola V.S., Giampaolo F., Rozza G., Raissi M., Piccialli F., Scientific machine learning through physics–informed neural networks: where we are and what’s next, J Sci Comput, 92, 3, (2022)
[4] Desmoulin G.T., Pradhan V., Milner T.E., Mechanical aspects of intervertebral disc injury and implications on biomechanics, Spine (Phila Pa 1976), 45, 8, pp. E457-E464, (2020)
[5] Du Toit J.F., Laubscher R., Evaluation of physics-informed neural network solution accuracy and efficiency for modeling aortic transvalvular blood flow, MCA, 28, 2, (2023)
[6] Galbusera F., Casaroli G., Bassani T., Artificial intelligence and machine learning in spine research, JOR Spine, 2, 1, (2019)
[7] Ghezelbash F., Hossein Eskandari A., Robert-Lachaine X., Cao S., Pesteie M., Qiao Z., Shirazi-Adl A., Lariviere C., Machine learning applications in spine biomechanics, J Biomech, 166, (2024)
[8] Grossmann T.G., Komorowska U.J., Latz J., Schonlieb C.-B., Can physics-informed neural networks beat the finite element method?, IMA J Appl Math, 89, 1, pp. hxae011-hxae174, (2024)
[9] Iatridis J.C., Setton L.A., Weidenbaum M., Mow V.C., The viscoelastic behavior of the non-degenerate human lumbar nucleus pulposus in shear, J Biomech, 30, 10, pp. 1005-1013, (1997)
[10] Iatridis J.C., Weidenbaum M., Setton L.A., Mow V.C., Is the nucleus pulposus a solid or a fluid? Mechanical behaviors of the nucleus pulposus of the human intervertebral disc, Spine (Phila Pa 1976), 21, 10, pp. 1174-1184, (1996)

← 1 2 3 4 →