Scholarlink

<p>This paper proposes a robust Federated Learning (FL) framework, FedVC-ADDiM for the efficient diagnosis of Alzheimer’s disease using decentralized MRI brain scans. The framework integrates a multi-objective optimization technique, Pareto Front Selection for Multi-Objective Optimization (PFSMOO), to select the most suitable global-local model from a diverse set of pre-trained architectures, with the VGG19 model identified as the optimal choice. To enhance the model FL capabilities, we introduce an attention-augmented Convolutional Block Attention Module (CBAM) within the VGG19 architecture, enabling the model to focus on critical neuroimaging features. Existing models often suffer from issues such as overfitting due to deep architectures, which can lead to poor generalization on unseen data, and the inability to effectively prioritize efficient features, resulting in reduced accuracy in complex medical diagnoses. The FedVC-ADDiM framework addresses these challenges by leveraging federated knowledge sharing, ensuring data privacy while maintaining model accuracy across diverse, decentralized datasets. Experimental results show that the model with CBAM achieved a notable increase in overall accuracy (95.68% vs. 94.81%) for Alzheimer disease detection. In terms of precision and recall, the model with CBAM demonstrated higher precision for the Dementia class (0.9579 vs. 0.9422) and improved recall for the non-Demented class (0.9585 vs. 0.9412). The integration of CBAM also improved the model F1-Score for both classes, showing better detection capabilities and robustness. The results highlight the model robustness, making it suitable for large-scale, collaborative health diagnosis in real-world medical environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

FedVC-ADDiM: a federated learning framework for diagnosis of alzheimer disease using deep learning

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Inzamam Shahzad ,
  • Jianquan Ouyang,
  • Saif Ur Rehman Khan

摘要

This paper proposes a robust Federated Learning (FL) framework, FedVC-ADDiM for the efficient diagnosis of Alzheimer’s disease using decentralized MRI brain scans. The framework integrates a multi-objective optimization technique, Pareto Front Selection for Multi-Objective Optimization (PFSMOO), to select the most suitable global-local model from a diverse set of pre-trained architectures, with the VGG19 model identified as the optimal choice. To enhance the model FL capabilities, we introduce an attention-augmented Convolutional Block Attention Module (CBAM) within the VGG19 architecture, enabling the model to focus on critical neuroimaging features. Existing models often suffer from issues such as overfitting due to deep architectures, which can lead to poor generalization on unseen data, and the inability to effectively prioritize efficient features, resulting in reduced accuracy in complex medical diagnoses. The FedVC-ADDiM framework addresses these challenges by leveraging federated knowledge sharing, ensuring data privacy while maintaining model accuracy across diverse, decentralized datasets. Experimental results show that the model with CBAM achieved a notable increase in overall accuracy (95.68% vs. 94.81%) for Alzheimer disease detection. In terms of precision and recall, the model with CBAM demonstrated higher precision for the Dementia class (0.9579 vs. 0.9422) and improved recall for the non-Demented class (0.9585 vs. 0.9412). The integration of CBAM also improved the model F1-Score for both classes, showing better detection capabilities and robustness. The results highlight the model robustness, making it suitable for large-scale, collaborative health diagnosis in real-world medical environments.