EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Fei Kong, Xiyue Wang, Jinxi Xiang, Sen Yang, Xinran Wang, Meng Yue, Jun Zhang, Junhan Zhao, Xiao Han, Yuhan Dong, Biyue Zhu, Fang Wang und 1 weitere

Computational and Structural Biotechnology Journal · 2024-12 · 23 · 1439-1449

DOI: 10.1016/j.csbj.2024.03.028 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 10.04.2024. Verfasst von Fei Kong und 12 weiteren Autor:innen. Beteiligte Einrichtung: Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

Schlagwörter

Stichwörter der Autor:innen

Attention mechanismCancer detectionConsistent learningFederated learningHistopathology

Autor:innen und Institutionen

  • Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China.
  • College of Biomedical Engineering, Sichuan University, Chengdu, 610065, China.
  • AI Lab, Tencent, Shenzhen, 518057, China.
  • Department of Pathology, The Fourth Hospital of Hebei Medical University, Shijiazhuang, 050035, China.
  • Massachusetts General Hospital, Boston, MA, 02114, United States.
  • Harvard T.H. Chan School of Public Health, Boston, MA, 02115, United States.

Zitieren

APA

Kong, F., Wang, X., Xiang, J., Yang, S., Wang, X., Yue, M., Zhang, J., Zhao, J., Han, X., Dong, Y., Zhu, B., Wang, F., & Liu, Y. (2024). Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading. Computational and Structural Biotechnology Journal, 23, 1439-1449. https://doi.org/10.1016/j.csbj.2024.03.028

Vancouver

Kong F, Wang X, Xiang J, Yang S, Wang X, Yue M, et al. Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading. Computational and Structural Biotechnology Journal. 2024;23:1439-1449. doi:10.1016/j.csbj.2024.03.028

BibTeX
@article{Kong2024,
  author = {Kong, Fei and Wang, Xiyue and Xiang, Jinxi and Yang, Sen and Wang, Xinran and Yue, Meng and Zhang, Jun and Zhao, Junhan and Han, Xiao and Dong, Yuhan and Zhu, Biyue and Wang, Fang and Liu, Yueping},
  title = {Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading},
  journal = {Computational and Structural Biotechnology Journal},
  year = {2024},
  volume = {23},
  pages = {1439--1449},
  doi = {10.1016/j.csbj.2024.03.028}
}
Kostenlos starten →