EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FMCerNet: frequency-aware multi-label learning for fine-grained cervical cytology screening

Linyun Zhou iD, Qiuyu Cai, Xiaoling Wang, Weihan Li, Jian Yang, Mingli Song, Jing Zhang, Feng Zhou, Qihan You, Yudong Wang, Zunlei Feng, Xiuming Zhang

Bioinformatics · 02.10.2026 · 42 (10)

DOI: 10.1093/bioinformatics/btag759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 19.10.2026. Verfasst von Linyun Zhou und 11 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science, Zhejiang University, Hangzhou, Zhejiang 310058, China. Hauptthemen laut MEDLINE: Uterine Cervical Neoplasms, Machine Learning, Cervix Uteri. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Central Universities, Zhejiang Provincial Natural Science Foundation of China, Zhejiang Province Health Major Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Automated cytology screening is essential for early cervical cancer prevention, where gigapixel whole-slide images (WSIs) are typically partitioned into tiles for tile-level feature extraction and subsequent WSI-level diagnosis aggregation. However, existing tile-level methods remain constrained by limited input sizes, which frequently obscures sparse and morphologically subtle abnormal cells. Furthermore, these methods commonly formulate tile-level representation learning as a coarse single-label classification task, thereby failing to capture the complex co-occurrence patterns and morphological heterogeneity of cervical cytological abnormalities. Results We propose the Frequency-Aware Multi-Label Learning Network (FMCerNet), a tile-level feature extractor equipped with a Large-Field Frequency-Enhanced ViT backbone and a Coarse-to-Fine multi-label classification head. The former incorporates a Dual-Tree Complex Wavelet Transform module to efficiently extract frequency-domain features from large-scale tiles, whereas the latter enhances fine-grained tile representation decoding through hierarchical supervision. Experiments on both public and private datasets demonstrate that FMCerNet improves the accuracy of positive screening and fine-grained subtype classification while maintaining high inference speed. Availability and implementation Code at https://github.com/imAzhou/FMCerNet and archived on Zenodo (doi: 10.5281/zenodo.22886105).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Uterine Cervical NeoplasmsMachine LearningCervix UteriHumansFemaleAlgorithms

Autor:innen und Institutionen

  • College of Computer Science, Zhejiang University, Hangzhou, Zhejiang 310058, China.
  • Department of Pathology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310003, China.
  • School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315100, China.
  • International Peace Maternal and Child Health Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200030, China.

ORCID-Profile: Linyun Zhou

Förderung

  • Central Universities
  • Zhejiang Provincial Natural Science Foundation of China
  • Zhejiang Province Health Major Science and Technology Program

Zitieren

APA

Zhou, L., Cai, Q., Wang, X., Li, W., Yang, J., Song, M., Zhang, J., Zhou, F., You, Q., Wang, Y., Feng, Z., & Zhang, X. (2026). FMCerNet: frequency-aware multi-label learning for fine-grained cervical cytology screening. Bioinformatics, 42(10). https://doi.org/10.1093/bioinformatics/btag759

Vancouver

Zhou L, Cai Q, Wang X, Li W, Yang J, Song M, et al. FMCerNet: frequency-aware multi-label learning for fine-grained cervical cytology screening. Bioinformatics. 2026;42(10). doi:10.1093/bioinformatics/btag759

BibTeX
@article{Zhou2026,
  author = {Zhou, Linyun and Cai, Qiuyu and Wang, Xiaoling and Li, Weihan and Yang, Jian and Song, Mingli and Zhang, Jing and Zhou, Feng and You, Qihan and Wang, Yudong and Feng, Zunlei and Zhang, Xiuming},
  title = {FMCerNet: frequency-aware multi-label learning for fine-grained cervical cytology screening},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {10},
  doi = {10.1093/bioinformatics/btag759}
}
Kostenlos starten →