EUVIMEDEUVIMED entdecken
Crossref

Three-Dimensional Reconstruction of Serial Block-Face Scanning Electron Microscopy Using Semantic Segmentation based on Semi-Supervised Deep Learning

Dal-Jae Yun, Junhyeong Park iD, Youngkwon Haam, Hee-Seok Kweon, Hwan Hur, Jisoo Kim, In-Yong Park, Ha Rim Lee, Haewon Jung iD

Microscopy and Microanalysis · 09.05.2025 · 31 (3)

DOI: 10.1093/mam/ozaf047 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Microscopy and Microanalysis, online erschienen am 11.06.2025. Verfasst von Dal-Jae Yun und 8 weiteren Autor:innen. Beteiligte Einrichtung: Emerging Research Instruments Group, Strategic Technology Research Institute, Korea Research Institute of Standards and Science (KRISS), 267 Gajeong-…. Hauptthemen laut MEDLINE: Deep Learning, Microscopy, Electron, Scanning, Imaging, Three-Dimensional, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Development of core technologies for advanced measuring instruments, Korea Research Institute of Standards and Science, Ministry of Science and ICT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Serial block-face scanning electron microscopy (SBF-SEM) is employed to achieve high-resolution volume reconstructions and detailed ultrastructural analyses of complex organelles. The performance of SBF-SEM is evaluated according to the accuracy of segmentation. Our study introduces a semi-supervised learning approach using a segment interpolation method to mitigate the costs of manual segmentation. The shapes and locations of individual segments between sparsely annotated label images are estimated using the proposed method. The proposed method is particularly well suited for SBF-SEM, where alignment and fine cutting of samples allow for accurate predictions with a minimal amount of labelled data. To validate the deep neural networks trained using the proposed method, the F-1 score metric and the K-fold technique were utilized. The results achieved an F-1 score of 0.89 for mouse brain cells and 0.84 for inverted images during the validation process for semi-supervised learning. Testing on an independently separated test dataset yielded scores of 0.84 for mouse brain cells and 0.80 for inverted cases. The automatically segmented results were then reconstructed in volume images using the marching cube algorithm. This allows for a three-dimensional (3-D) analysis of complex organelles, with potential applications in the fields of biology and medicine.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMicroscopy, Electron, ScanningImaging, Three-DimensionalImage Processing, Computer-AssistedAnimalsMiceBrainNeural Networks, ComputerVolume Electron Microscopy

Stichwörter der Autor:innen

3-D reconstructionDNNSBF-SEMsemantic segmentationsemi-supervised learning

Autor:innen und Institutionen

  • Emerging Research Instruments Group, Strategic Technology Research Institute, Korea Research Institute of Standards and Science (KRISS), 267 Gajeong-ro, Yuseong-gu, Daejeon 34113, Republic of Korea.
  • Major in Nanoconvergence Measurement, University of Science and Technology, 217 Gajeong-ro, Yuseong-gu, Daejeon 34113, Republic of Korea.
  • Graduate School of Analytical Science and Technology, Chungnam National University, 99 Daehak-ro, Yuseong-gu, Daejeon 34134, Rebublic of Korea.
  • Center for Research Equipment, Korea Basic Science Institute, 162 Yeongudanji-ro, Ochang-eup, Cheongwon-gu, Cheongju 28119, Republic of Korea.
  • Center for Scientific Instrumentation, Korea Basic Science Institute, 169-148 Gwahak-ro, Yuseong-gu, Daejeon 34133, Republic of Korea.

ORCID-Profile: Junhyeong Park, Haewon Jung

Förderung

  • Development of core technologies for advanced measuring instruments
  • Korea Research Institute of Standards and Science
  • Ministry of Science and ICT
  • Commercializations Promotion Agency for R and D Outcomes

Zitieren

APA

Yun, D. J., Park, J., Haam, Y., Kweon, H. S., Hur, H., Kim, J., Park, I. Y., Lee, H. R., & Jung, H. (2025). Three-Dimensional Reconstruction of Serial Block-Face Scanning Electron Microscopy Using Semantic Segmentation based on Semi-Supervised Deep Learning. Microscopy and Microanalysis, 31(3). https://doi.org/10.1093/mam/ozaf047

Vancouver

Yun DJ, Park J, Haam Y, Kweon HS, Hur H, Kim J, et al. Three-Dimensional Reconstruction of Serial Block-Face Scanning Electron Microscopy Using Semantic Segmentation based on Semi-Supervised Deep Learning. Microscopy and Microanalysis. 2025;31(3). doi:10.1093/mam/ozaf047

BibTeX
@article{Yun2025,
  author = {Yun, Dal-Jae and Park, Junhyeong and Haam, Youngkwon and Kweon, Hee-Seok and Hur, Hwan and Kim, Jisoo and Park, In-Yong and Lee, Ha Rim and Jung, Haewon},
  title = {Three-Dimensional Reconstruction of Serial Block-Face Scanning Electron Microscopy Using Semantic Segmentation based on Semi-Supervised Deep Learning},
  journal = {Microscopy and Microanalysis},
  year = {2025},
  volume = {31},
  number = {3},
  doi = {10.1093/mam/ozaf047}
}
Kostenlos starten →