HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification
IEEE Transactions on Medical Imaging · 2024-12 · 43 (12) · 4344-4355
DOI: 10.1109/tmi.2024.3419697 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2024-12. Verfasst von De Cai und 15 weiteren Autor:innen. Hauptthemen laut MEDLINE: Uterine Cervical Neoplasms, Cervix Uteri, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Sanming Project of Medicine in Shenzhen, Postdoctoral Joint Training Program of Sichuan University.
Abstract (Originalsprache)
Cervical cytology is a critical screening strategy for early detection of pre-cancerous and cancerous cervical lesions. The challenge lies in accurately classifying various cervical cytology cell types. Existing automated cervical cytology methods are primarily trained on databases covering a narrow range of coarse-grained cell types, which fail to provide a comprehensive and detailed performance analysis that accurately represents real-world cytopathology conditions. To overcome these limitations, we introduce HiCervix, the most extensive, multi-center cervical cytology dataset currently available to the public. HiCervix includes 40,229 cervical cells from 4,496 whole slide images, categorized into 29 annotated classes. These classes are organized within a three-level hierarchical tree to capture fine-grained subtype information. To exploit the semantic correlation inherent in this hierarchical tree, we propose HierSwin, a hierarchical vision transformer-based classification network. HierSwin serves as a benchmark for detailed feature learning in both coarse-level and fine-level cervical cancer classification tasks. In our comprehensive experiments, HierSwin demonstrated remarkable performance, achieving 92.08% accuracy for coarse-level classification and 82.93% accuracy averaged across all three levels. When compared to board-certified cytopathologists, HierSwin achieved high classification performance (0.8293 versus 0.7359 averaged accuracy), highlighting its potential for clinical applications. This newly released HiCervix dataset, along with our benchmark HierSwin method, is poised to make a substantial impact on the advancement of deep learning algorithms for rapid cervical cancer screening and greatly improve cancer prevention and patient outcomes in real-world clinical settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Sanming Project of Medicine in Shenzhen
- Postdoctoral Joint Training Program of Sichuan University
Zitieren
APA
Cai, Chen, J., Zhao, J., Xue, Y., Yang, S., Yuan, W., Feng, M., Weng, H., Liu, S., Peng, Y., Zhu, J., Wang, K., Jackson, C., Tang, H., Huang, J., & Wang, X. (2024). HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification. IEEE Transactions on Medical Imaging, 43(12), 4344-4355. https://doi.org/10.1109/tmi.2024.3419697
Vancouver
Cai, Chen J, Zhao J, Xue Y, Yang S, Yuan W, et al. HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification. IEEE Transactions on Medical Imaging. 2024;43(12):4344-4355. doi:10.1109/tmi.2024.3419697
BibTeX
@article{Cai2024,
author = {Cai, De and Chen, Jie and Zhao, Junhan and Xue, Yuan and Yang, Sen and Yuan, Wei and Feng, Min and Weng, Haiyan and Liu, Shuguang and Peng, Yulong and Zhu, Junyou and Wang, Kanran and Jackson, Christopher and Tang, Hongping and Huang, Junzhou and Wang, Xiyue},
title = {HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification},
journal = {IEEE Transactions on Medical Imaging},
year = {2024},
volume = {43},
number = {12},
pages = {4344--4355},
doi = {10.1109/tmi.2024.3419697}
}
EUVIMED