| Jiang Jiewei (蒋杰伟)*,Cui Yiwei*,Yao Qihai*,Wang Ning*,Li Kuan*,Li Zhongwen**.[J].高技术通讯(英文),2026,32(1):1~10 |
|
| A similarity-guided dynamic adjustment federated learning framework for multicenter keratitis diagnosis |
| |
| DOI：10. 3772 / j. issn. 1006-6748. 2026. 01. 001 |
| 中文关键词: |
| 英文关键词: federated learning, keratitis diagnosis, deep learning, data heterogeneity, dynamic aggregation |
| 基金项目: |
| Author Name | Affiliation | | Jiang Jiewei (蒋杰伟)* | (* School of Electronic Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, P. R. China)
(** Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, P. R. China) | | Cui Yiwei* | | | Yao Qihai* | | | Wang Ning* | | | Li Kuan* | | | Li Zhongwen** | |
|
| Hits: 26 |
| Download times: 28 |
| 中文摘要: |
| |
| 英文摘要: |
| Keratitis is a common ophthalmic disease associated with a high risk of blindness. Although deep learning (DL) based on slit-lamp images has shown great promise for automatic keratitis diagnosis,data heterogeneity and privacy constraints hinder data sharing, limiting model generalization across multiple medical centers. To address these challenges, we propose a similarity-guided dynamic adjustment federated learning algorithm for automated keratitis diagnosis (SDAFL_AKD). SDAFL_AKD introduces a similarity-based regularization term during local model updates to alleviate catastrophic forgetting and employs a performance-driven dynamic aggregation mechanism on the server-side to adaptively weight client contributions, thereby enhancing global model robustness under non-independent and identically distributed (Non-IID) conditions. The framework is evaluated on slit-lamp images collected from four independent data sources encompassing keratitis, normal cornea, and other cornea abnormalities, and compared with FedAvg, model-contrastive federated learning (MOON),stochastic controlled averaging for federated learning (SCAFFOLD) and single-center baseline models. Experimental results demonstrate that SDAFL_AKD consistently outperforms conventional methods, achieving average accuracies of 97. 95% on a balanced dataset and 86. 05% on an imbalanced smart phone-acquired dataset. Ablation studies further confirm the synergistic benefits of the similarity (SIM) and dynamic aggregation (DA) modules in improving multi-category recognition and generalization. These findings indicate the effectiveness of SDAFL_AKD for keratitis diagnosis under data heterogeneous and privacy-constrained conditions, providing a scalable solution for collaborative ophthalmic image analysis across institutions. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
