EUVIMEDEUVIMED entdecken
Crossref

Improved deep learning‐based IVIM parameter estimation via the use of more “realistic” simulated brain data

Lu Wang, Jiechao Wang, Qinqin Yang, Congbo Cai, Zhen Xing, Zhong Chen, Dairong Cao, Shuhui Cai

Medical Physics · 2025

DOI: 10.1002/mp.17583 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Lu Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University, Xiamen, Fujian, China. Hauptthemen laut MEDLINE: Deep Learning, Brain, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Key R & D Program of China, National Natural Science Foundation of China, Science and Technology Project of Fujian Province of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Due to the low signal‐to‐noise ratio (SNR) and the limited number of b ‐values, precise parameter estimation of intravoxel incoherent motion (IVIM) imaging remains an open issue to date, especially for brain imaging where the relatively small difference between D and D * easily leads to outliers and obvious graininess in estimated results.

Purpose

To propose a synthetic data driven supervised learning method (SDD‐IVIM) for improving precision and noise robustness in IVIM parameter estimation without relying on real‐world data for neural network training.

Methods

On account of the absence of standard IVIM parametric maps from real‐world data, a novel model‐based method for generating synthetic human brain IVIM data was introduced. Initially, the parameter values of synthetic IVIM parametric maps were sampled from the complex distributions composed of a series of simple and uniform distributions. Subsequently, these parametric maps were modulated with human brain texture to imitate brain tissue structure. Finally, they were used to generate synthetic human brain multi‐ b ‐value diffusion‐weighted (DW) images based on the IVIM bi‐exponential model. With the proposed data synthesis method, an ordinary U‐Net with spatial smoothness was employed for IVIM parameter mapping within a supervised learning framework. The performance of SDD‐IVIM was evaluated on both numerical phantom and 20 glioma patients. The estimated IVIM parametric maps were compared to those derived from five state‐of‐the‐art methods.

Results

In numerical phantom experiments, SDD‐IVIM method produces IVIM parametric maps with lower mean absolute error, lower mean bias, and higher structural similarity compared to the other five methods, especially when the SNR of DW images is low. In glioma patient experiments, SDD‐IVIM method offers lower coefficient of variation and more reasonable contrast‐to‐noise ratio between tumor and contralateral normal appearing white matter than the other five methods.

Conclusion

Our method owns superior performance in parametric map quality, parameter estimation precision, and lesion characterization in IVIM parameter estimation, with strong resistance to noise.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBrainImage Processing, Computer-AssistedHumansSignal-To-Noise RatioDiffusion Magnetic Resonance ImagingMotion

Stichwörter der Autor:innen

intravoxel incoherent motionmagnetic resonance imagingnoise resistancesupervised learningsynthetic data driven

Autor:innen und Institutionen

  • Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University, Xiamen, Fujian, China.
  • Department of Radiology, First Affiliated Hospital of Fujian Medical University, Fuzhou, Fujian, China.

Förderung

  • National Key R & D Program of China
  • National Natural Science Foundation of China
  • Science and Technology Project of Fujian Province of China

Zitieren

APA

Wang, L., Wang, J., Yang, Q., Cai, C., Xing, Z., Chen, Z., Cao, D., & Cai, S. (2025). Improved deep learning‐based IVIM parameter estimation via the use of more “realistic” simulated brain data. Medical Physics. https://doi.org/10.1002/mp.17583

Vancouver

Wang L, Wang J, Yang Q, Cai C, Xing Z, Chen Z, et al. Improved deep learning‐based IVIM parameter estimation via the use of more “realistic” simulated brain data. Medical Physics. 2025. doi:10.1002/mp.17583

BibTeX
@article{Wang2025,
  author = {Wang, Lu and Wang, Jiechao and Yang, Qinqin and Cai, Congbo and Xing, Zhen and Chen, Zhong and Cao, Dairong and Cai, Shuhui},
  title = {Improved deep learning‐based IVIM parameter estimation via the use of more “realistic” simulated brain data},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.17583}
}
Kostenlos starten →