EUVIMEDEUVIMED entdecken
Crossref

Neural Network Approximation Aided Kinetic Parameter Inference of Compartment Models in Dynamic PET

Wenrui Shao, Yixin Chen, Ourui Fu, Tian Li, Zhi Yang, Nan Li, Hongbin Han, Xiangxi Meng, Zhaoheng Xie

IEEE Transactions on Radiation and Plasma Medical Sciences · 2026-11 · 10 (8) · 1219-1229

DOI: 10.1109/trpms.2026.3660465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Radiation and Plasma Medical Sciences, 2026-11. Verfasst von Wenrui Shao und 8 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: Natural Science Foundation of China, Start-Up Funds of Peking University Health Science Center and in part by 2024 China Industrial Technology Infrastructure Public Service Platform Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inferring kinetic parameters in dynamic positron emission tomography (PET) imaging is challenging due to the significant noise, the complexity of compartment models, the high spatio-temporal resolution of the data, and the variability in framing protocols. This study proposes a robust neural network-based method that directly solves the ordinary differential equations (ODEs) derived from kinetic models. By discretizing the derivative term using finite difference methods, ODEs are parameterized as a four-layer neural network. The network is optimized by minimizing a specialized loss function that incorporates physiological constraints. The delay correction and parallel network processing are also incorporated for voxel-level parametric PET imaging. Both simulations and real patient studies confirm the method’s effectiveness and practical applicability. Compared with the reference methods, our method excels in accuracy, robustness and physiological interpretability, particularly in high-noise conditions. Overall, our proposed approach offers enhanced diagnostic capabilities and a deeper understanding of physiological processes, showing great potential for medical imaging and personalized treatment strategies. The code has been made publicly available at https://github.com/PKU-MIPET/NNAKPI.git.

Förderung

  • Natural Science Foundation of China
  • Start-Up Funds of Peking University Health Science Center and in part by 2024 China Industrial Technology Infrastructure Public Service Platform Project

Zitieren

APA

Shao, W., Chen, Y., Fu, O., Li, T., Yang, Z., Li, N., Han, H., Meng, X., & Xie, Z. (2026). Neural Network Approximation Aided Kinetic Parameter Inference of Compartment Models in Dynamic PET. IEEE Transactions on Radiation and Plasma Medical Sciences, 10(8), 1219-1229. https://doi.org/10.1109/trpms.2026.3660465

Vancouver

Shao W, Chen Y, Fu O, Li T, Yang Z, Li N, et al. Neural Network Approximation Aided Kinetic Parameter Inference of Compartment Models in Dynamic PET. IEEE Transactions on Radiation and Plasma Medical Sciences. 2026;10(8):1219-1229. doi:10.1109/trpms.2026.3660465

BibTeX
@article{Shao2026,
  author = {Shao, Wenrui and Chen, Yixin and Fu, Ourui and Li, Tian and Yang, Zhi and Li, Nan and Han, Hongbin and Meng, Xiangxi and Xie, Zhaoheng},
  title = {Neural Network Approximation Aided Kinetic Parameter Inference of Compartment Models in Dynamic PET},
  journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
  year = {2026},
  volume = {10},
  number = {8},
  pages = {1219--1229},
  doi = {10.1109/trpms.2026.3660465}
}
Kostenlos starten →