EUVIMEDEUVIMED entdecken
Crossref

Highly robust reconstruction framework for three-dimensional optical imaging based on physical model constrained neural networks

Xueli Chen, Yu Meng, Lin Wang, Wangting Zhou, Duofang Chen, Hui Xie, Shenghan Ren

Physics in Medicine & Biology · 2024

DOI: 10.1088/1361-6560/ad2ca3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics in Medicine & Biology, 2024. Verfasst von Xueli Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Center for Biomedical-photonics and Molecular Imaging, Advanced Diagnostic-Therapy Technology and Equipment Key Laboratory of Higher Education Instit…. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Deep Learning. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, National Young Talent Program, the Shaanxi Young Top-notch Talent Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . The reconstruction of three-dimensional optical imaging that can quantitatively acquire the target distribution from surface measurements is a serious ill-posed problem. Traditional regularization-based reconstruction can solve such ill-posed problem to a certain extent, but its accuracy is highly dependent on a prior information, resulting in a less stable and adaptable method. Data-driven deep learning-based reconstruction avoids the errors of light propagation models and the reliance on experience and a prior by learning the mapping relationship between the surface light distribution and the target directly from the dataset. However, the acquisition of the training dataset and the training of the network itself are time consuming, and the high dependence of the network performance on the training dataset results in a low generalization ability. The objective of this work is to develop a highly robust reconstruction framework to solve the existing problems. Approach . This paper proposes a physical model constrained neural networks-based reconstruction framework. In the framework, the neural networks are to generate a target distribution from surface measurements, while the physical model is used to calculate the surface light distribution based on this target distribution. The mean square error between the calculated surface light distribution and the surface measurements is then used as a loss function to optimize the neural network. To further reduce the dependence on a priori information, a movable region is randomly selected and then traverses the entire solution interval. We reconstruct the target distribution in this movable region and the results are used as the basis for its next movement. Main Results . The performance of the proposed framework is evaluated with a series of simulations and in vivo experiment, including accuracy robustness of different target distributions, noise immunity, depth robustness, and spatial resolution. The results collectively demonstrate that the framework can reconstruct targets with a high accuracy, stability and versatility. Significance . The proposed framework has high accuracy and robustness, as well as good generalizability. Compared with traditional regularization-based reconstruction methods, it eliminates the need to manually delineate feasible regions and adjust regularization parameters. Compared with emerging deep learning assisted methods, it does not require any training dataset, thus saving a lot of time and resources and solving the problem of poor generalization and robustness of deep learning methods. Thus, the framework opens up a new perspective for the reconstruction of three-dimension optical imaging.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedDeep LearningNeural Networks, ComputerImaging, Three-DimensionalOptical ImagingAlgorithms

Stichwörter der Autor:innen

deep learningphysical modelrobust reconstructionthree-dimensional optical imagingtomography

Autor:innen und Institutionen

  • Center for Biomedical-photonics and Molecular Imaging, Advanced Diagnostic-Therapy Technology and Equipment Key Laboratory of Higher Education Institutions in Shaanxi Province, School of Life Science and Technology, Xid…
  • Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidi…
  • Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong 510555, People's Republic of China.
  • School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, Shaanxi 710048, People's Republic of China.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • National Young Talent Program, the Shaanxi Young Top-notch Talent Program
  • Key Research and Development Program of Shaanxi
  • National Young Talent Program; Shaanxi Young Top-notch Talent Protram
  • Key Research and Development of Shaanxi

Zitieren

APA

Chen, X., Meng, Y., Wang, L., Zhou, W., Chen, D., Xie, H., & Ren, S. (2024). Highly robust reconstruction framework for three-dimensional optical imaging based on physical model constrained neural networks. Physics in Medicine & Biology. https://doi.org/10.1088/1361-6560/ad2ca3

Vancouver

Chen X, Meng Y, Wang L, Zhou W, Chen D, Xie H, et al. Highly robust reconstruction framework for three-dimensional optical imaging based on physical model constrained neural networks. Physics in Medicine & Biology. 2024. doi:10.1088/1361-6560/ad2ca3

BibTeX
@article{Chen2024,
  author = {Chen, Xueli and Meng, Yu and Wang, Lin and Zhou, Wangting and Chen, Duofang and Xie, Hui and Ren, Shenghan},
  title = {Highly robust reconstruction framework for three-dimensional optical imaging based on physical model constrained neural networks},
  journal = {Physics in Medicine & Biology},
  year = {2024},
  doi = {10.1088/1361-6560/ad2ca3}
}
Kostenlos starten →