EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

3D registration-guided deformable residual inpainting for ssEM restoration

Zhenbang Zhang, Jingtong Feng, Hongjia Li iD, Haythem El-Messiry, Zhiqiang Xu, Renmin Han iD

Bioinformatics · 01.06.2026 · 42 (6)

DOI: 10.1093/bioinformatics/btag329 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 22.05.2026. Verfasst von Zhenbang Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shenzhen Research Institute of Shandong University, Shenzhen, 518000, China. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Microscopy, Electron. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Natural Science Foundation of Guangdong Province, Dubai Future Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Serial section electron microscopy (ssEM) is essential for studying biological cell structures at nanometer resolution. However, supporting film folding (SFF) degradation frequently occurs during sample preparation, causing structural distortions and information loss that severely impair downstream analyses such as 3D reconstruction and neuron segmentation. Results We propose RegInpaint, a novel recovery framework that jointly addresses deformation correction and missing-information restoration caused by SFF degradation. RegInpaint formulates SFF recovery as a joint problem of 3D elastic registration and image inpainting, providing a generalizable solution for ssEM restoration. Experiments on four EM datasets show that RegInpaint consistently outperforms existing methods in image restoration quality and significantly improves neuron segmentation accuracy. Availability and implementation Source code is freely available at https://github.com/zhangzhenbang2021/RegInpaint.git.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalMicroscopy, ElectronAlgorithmsNeuronsSoftware

Autor:innen und Institutionen

  • Shenzhen Research Institute of Shandong University, Shenzhen, 518000, China.
  • Research Center for Mathematics and Interdisciplinary Sciences, Frontiers Science Center for Nonlinear Expectations (Ministry of Education), Shandong University, Qingdao, 266237, China.
  • Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, 7909, United Arab Emirates.
  • College of Medical Information and Engineering, Ningxia Medical University, Ningxia, 750004, China.
  • School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China.
  • Canadian University Dubai, Dubai, 117781, United Arab Emirates.

ORCID-Profile: Hongjia Li, Renmin Han

Förderung

  • National Key Research and Development Program of China
  • Natural Science Foundation of Guangdong Province
  • Dubai Future Foundation
  • Fundamental Research Funds for the Central Universities, and the Natural Science Foundation of Ningxia Province

Zitieren

APA

Zhang, Z., Feng, J., Li, H., El-Messiry, H., Xu, Z., & Han, R. (2026). 3D registration-guided deformable residual inpainting for ssEM restoration. Bioinformatics, 42(6). https://doi.org/10.1093/bioinformatics/btag329

Vancouver

Zhang Z, Feng J, Li H, El-Messiry H, Xu Z, Han R. 3D registration-guided deformable residual inpainting for ssEM restoration. Bioinformatics. 2026;42(6). doi:10.1093/bioinformatics/btag329

BibTeX
@article{Zhang2026,
  author = {Zhang, Zhenbang and Feng, Jingtong and Li, Hongjia and El-Messiry, Haythem and Xu, Zhiqiang and Han, Renmin},
  title = {3D registration-guided deformable residual inpainting for ssEM restoration},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {6},
  doi = {10.1093/bioinformatics/btag329}
}
Kostenlos starten →