Adaptive Multimodal Fusion in Vertical Federated Learning for Decentralized Glaucoma Screening
Brain Sciences · 14.09.2025 · 15 (9) · 990
DOI: 10.3390/brainsci15090990 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 14.09.2025. Verfasst von Ayesha Jabbar und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Science and Technology Program, Guangdong Provincial Key Laboratory.
Abstract (Originalsprache)
Background/Objectives: Early and accurate detection of glaucoma is vital for preventing irreversible vision loss, yet traditional diagnostic approaches relying solely on unimodal retinal imaging are limited by data sparsity and constrained context. Furthermore, real-world clinical data are often fragmented across institutions under strict privacy regulations, posing significant challenges for centralized machine learning methods.
Methods
To address these barriers, this study proposes a novel Quality Aware Vertical Federated Learning (QAVFL) framework for decentralized multimodal glaucoma detection. The proposed system dynamically integrates clinical text, retinal fundus images, and biomedical signal data through modality-specific encoders, followed by a Fusion Attention Module (FAM) that adaptively weighs the reliability and contribution of each modality. Unlike conventional early fusion or horizontal federated learning methods, QAVFL operates in vertically partitioned environments and employs secure aggregation mechanisms incorporating homomorphic encryption and differential privacy to preserve patient confidentiality.
Results
Extensive experiments conducted under heterogeneous non-IID settings demonstrate that QAVFL achieves an accuracy of 98.6%, a recall of 98.6%, an F1-score of 97.0%, and an AUC of 0.992, outperforming unimodal and early fusion baselines with statistically significant improvements (p < 0.01).
Conclusions
The findings validate the effectiveness of dynamic multimodal fusion under privacy-preserving decentralized learning and highlight the scalability and clinical applicability of QAVFL for robust glaucoma screening across fragmented healthcare environments.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China.
- Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China.
ORCID-Profile: Jianjun Huang
Förderung
- Shenzhen Science and Technology Program
- Guangdong Provincial Key Laboratory
Zitieren
APA
Jabbar, A., Huang, J., Jabbar, M. K., & Ali, A. (2025). Adaptive Multimodal Fusion in Vertical Federated Learning for Decentralized Glaucoma Screening. Brain Sciences, 15(9), 990. https://doi.org/10.3390/brainsci15090990
Vancouver
Jabbar A, Huang J, Jabbar MK, Ali A. Adaptive Multimodal Fusion in Vertical Federated Learning for Decentralized Glaucoma Screening. Brain Sciences. 2025;15(9):990. doi:10.3390/brainsci15090990
BibTeX
@article{Jabbar2025,
author = {Jabbar, Ayesha and Huang, Jianjun and Jabbar, Muhammad Kashif and Ali, Asad},
title = {Adaptive Multimodal Fusion in Vertical Federated Learning for Decentralized Glaucoma Screening},
journal = {Brain Sciences},
year = {2025},
volume = {15},
number = {9},
pages = {990},
doi = {10.3390/brainsci15090990}
}
EUVIMED