EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A noise-robust classification method for cryo-ET subtomograms with out-of-distribution detection

Wenjia Meng iD, Xueshi Yu iD, Tingting Zhang iD, Renmin Han iD

Bioinformatics · 06.05.2025 · 41 (5)

DOI: 10.1093/bioinformatics/btaf274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 13.05.2025. Verfasst von Wenjia Meng und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Shandong University, Jinan 250101, China. Hauptthemen laut MEDLINE: Cryoelectron Microscopy, Electron Microscope Tomography, Imaging, Three-Dimensional, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Cryogenic electron tomography (cryo-ET) enables high-resolution 3D reconstruction of biological samples, with accurate subtomogram classification critical for structural analysis. However, current subtomogram classification methods often struggle with out-of-distribution (OOD) data issue, causing misclassification and mismatched structures. Results To solve this problem, we propose a unified subtomogram classification framework that incorporates OOD detection to distinguish unknown (OOD) from known (in-distribution, ID) classes and predict labels for ID data, thereby enhancing existing subtomogram classification methods. Within this framework, we develop a noise-robust classification method that integrates a 3D discrete wavelet transform-based encoder to reduce high-frequency noise and extract robust features. Additionally, we incorporate a Mahalanobis distance-based OOD detector with a reliable metric for 3D subtomograms and introduce an adaptive classifier that adjusts to accommodate datasets of varying scales. The experimental and visualization results demonstrate that our noise-robust method improves subtomogram classification accuracy and effectively models features while enhancing OOD detection. Availability and implementation Our code is available at https://github.com/yxs1137/Subtomo-Classification-with-OOD.git. The real data used in this study can be accessed through CryoET Data Portal.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cryoelectron MicroscopyElectron Microscope TomographyImaging, Three-DimensionalImage Processing, Computer-AssistedAlgorithmsWavelet Analysis

Autor:innen und Institutionen

  • School of Software, Shandong University, Jinan 250101, China.
  • College of Medical Information and Engineering, Ningxia Medical University, Yinchuan 750004, China.
  • Research Center for Mathematics and Interdisciplinary Sciences (Ministry of Education Frontiers Science Center for Nonlinear Expectations), Shandong University, Qingdao 266237, China.

ORCID-Profile: Wenjia Meng, Xueshi Yu, Tingting Zhang, Renmin Han

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Meng, W., Yu, X., Zhang, T., & Han, R. (2025). A noise-robust classification method for cryo-ET subtomograms with out-of-distribution detection. Bioinformatics, 41(5). https://doi.org/10.1093/bioinformatics/btaf274

Vancouver

Meng W, Yu X, Zhang T, Han R. A noise-robust classification method for cryo-ET subtomograms with out-of-distribution detection. Bioinformatics. 2025;41(5). doi:10.1093/bioinformatics/btaf274

BibTeX
@article{Meng2025,
  author = {Meng, Wenjia and Yu, Xueshi and Zhang, Tingting and Han, Renmin},
  title = {A noise-robust classification method for cryo-ET subtomograms with out-of-distribution detection},
  journal = {Bioinformatics},
  year = {2025},
  volume = {41},
  number = {5},
  doi = {10.1093/bioinformatics/btaf274}
}
Kostenlos starten →