EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-supervised learning for colposcopic image classification using generative adversarial networks

Feng Liang, Yun Feng, Jin Ding, Chuanyi Zhang, Junyao Sun, Shue Wang, Cheng Peng, Gangming Zhao, Liping Li

Frontiers in Medicine · 23.07.2026 · 13

DOI: 10.3389/fmed.2026.1828859 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Medicine, online erschienen am 23.07.2026. Verfasst von Feng Liang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Intelligent Computing and Signal Processing, MOE, Anhui University, Hefei, China. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Traditional colposcopy screening faces several challenges, including heavy reliance on physician expertise, relatively high misdiagnosis rates, and uneven distribution of primary healthcare resources. To address these limitations, this study aimed to develop an artificial intelligence-assisted framework for colposcopic image generation and interpretation.

Methods

We proposed a Feature-pyramid and Squeeze-excitation Generative Adversarial Network (FSGAN) to generate realistic colposcopic images and a region-focused recognition model named CenSwin Transformer for image classification. FSGAN-generated images were incorporated into model training, and a dynamic pseudo-label semi-supervised learning strategy was applied to improve recognition performance. The proposed model was evaluated through 12 repeated experiments and further validated on an additional independent dataset.

Results

Across 12 repeated experiments, CenSwin Transformer achieved an accuracy of 90.39 ± 0.67%, recall of 86.10 ± 4.33%, and F1-score of 0.8645 ± 0.0111. Compared with Swin Transformer, CenSwin Transformer showed statistically significant improvements in accuracy and F1-score. On the independent validation dataset, the model achieved an accuracy of 85.26% and recall of 71.11%.

Discussion

The proposed FSGAN-assisted semi-supervised learning framework and CenSwin Transformer model improved colposcopic image recognition performance, particularly in accuracy and F1-score. These findings suggest that the model may serve as an auxiliary second-opinion tool for colposcopic image interpretation, especially in primary healthcare settings or regions with limited access to experienced colposcopists.

Schlagwörter

Stichwörter der Autor:innen

classification of cervical lesionscolposcopic imagedeep learninggenerative adversarial networkssemi-supervised learning

Autor:innen und Institutionen

  • Key Laboratory of Intelligent Computing and Signal Processing, MOE, Anhui University, Hefei, China.
  • Department of Obstetrics and Gynecology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, Jiangsu, China.
  • The People's Hospital of Fanchang District, Wuhu, Anhui, China.
  • The Traditional Chinese Medicine Hospital of Taihe, Taihe, Anhui, China.
  • Department of Obstetrics and Gynecology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.

Zitieren

APA

Liang, F., Feng, Y., Ding, J., Zhang, C., Sun, J., Wang, S., Peng, C., Zhao, G., & Li, L. (2026). Semi-supervised learning for colposcopic image classification using generative adversarial networks. Frontiers in Medicine, 13. https://doi.org/10.3389/fmed.2026.1828859

Vancouver

Liang F, Feng Y, Ding J, Zhang C, Sun J, Wang S, et al. Semi-supervised learning for colposcopic image classification using generative adversarial networks. Frontiers in Medicine. 2026;13. doi:10.3389/fmed.2026.1828859

BibTeX
@article{Liang2026,
  author = {Liang, Feng and Feng, Yun and Ding, Jin and Zhang, Chuanyi and Sun, Junyao and Wang, Shue and Peng, Cheng and Zhao, Gangming and Li, Liping},
  title = {Semi-supervised learning for colposcopic image classification using generative adversarial networks},
  journal = {Frontiers in Medicine},
  year = {2026},
  volume = {13},
  doi = {10.3389/fmed.2026.1828859}
}
Kostenlos starten →