EUVIMEDEUVIMED entdecken
Crossref

Deep Equilibrium Unfolding Learning for Noise Estimation and Removal in Optical Molecular Imaging

Lidan Fu, Lingbing Li, Binchun Lu, Xiaoyong Guo, Xiaojing Shi, Jie Tian, Zhenhua Hu

Computerized Medical Imaging and Graphics · 2025

DOI: 10.1016/j.compmedimag.2025.102492 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2025. Verfasst von Lidan Fu und 6 weiteren Autor:innen. Beteiligte Einrichtung: CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligen…. Hauptthemen laut MEDLINE: Deep Learning, Microscopy, Fluorescence, Image Processing, Computer-Assisted, Spectroscopy, Near-Infrared. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In clinical optical molecular imaging, the need for real-time high frame rates and low excitation doses to ensure patient safety inherently increases susceptibility to detection noise. Faced with the challenge of image degradation caused by severe noise, image denoising is essential for mitigating the trade-off between acquisition cost and image quality. However, prevailing deep learning methods exhibit uncontrollable and suboptimal performance with limited interpretability, primarily due to neglecting underlying physical model and frequency information. In this work, we introduce an end-to-end model-driven Deep Equilibrium Unfolding Mamba (DEQ-UMamba) that integrates proximal gradient descent technique and learnt spatial-frequency characteristics to decouple complex noise structures into statistical distributions, enabling effective noise estimation and suppression in fluorescent images. Moreover, to address the computational limitations of unfolding networks, DEQ-UMamba trains an implicit mapping by directly differentiating the equilibrium point of the convergent solution, thereby ensuring stability and avoiding non-convergent behavior. With each network module aligned to a corresponding operation in the iterative optimization process, the proposed method achieves clear structural interpretability and strong performance. Comprehensive experiments conducted on both clinical and in vivo datasets demonstrate that DEQ-UMamba outperforms current state-of-the-art alternatives while utilizing fewer parameters, facilitating the advancement of cost-effective and high-quality clinical molecular imaging.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMicroscopy, FluorescenceImage Processing, Computer-AssistedSpectroscopy, Near-InfraredSignal-To-Noise RatioRecurrent Neural NetworksComputer Simulation

Stichwörter der Autor:innen

Deep equilibrium learningFluorescence microscopy imagingMamba-based modelMedical image denoisingNIR-II molecular imaging

Autor:innen und Institutionen

  • CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China.
  • Interventional Radiology Department, Chinese PLA General Hospital, Beijing 100039, China.
  • Department of Precision Instrument, Tsinghua University, Beijing 100084, China.
  • Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Gastrointestinal Cancer Center, Ward I, Peking University Cancer Hospital & Institute, Beijing 100142, China.
  • CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China;…

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Fu, L., Li, L., Lu, B., Guo, X., Shi, X., Tian, J., & Hu, Z. (2025). Deep Equilibrium Unfolding Learning for Noise Estimation and Removal in Optical Molecular Imaging. Computerized Medical Imaging and Graphics. https://doi.org/10.1016/j.compmedimag.2025.102492

Vancouver

Fu L, Li L, Lu B, Guo X, Shi X, Tian J, et al. Deep Equilibrium Unfolding Learning for Noise Estimation and Removal in Optical Molecular Imaging. Computerized Medical Imaging and Graphics. 2025. doi:10.1016/j.compmedimag.2025.102492

BibTeX
@article{Fu2025,
  author = {Fu, Lidan and Li, Lingbing and Lu, Binchun and Guo, Xiaoyong and Shi, Xiaojing and Tian, Jie and Hu, Zhenhua},
  title = {Deep Equilibrium Unfolding Learning for Noise Estimation and Removal in Optical Molecular Imaging},
  journal = {Computerized Medical Imaging and Graphics},
  year = {2025},
  doi = {10.1016/j.compmedimag.2025.102492}
}
Kostenlos starten →