FOLC-Net: A Federated-Optimized Lightweight Architecture for Enhanced MRI Disease Diagnosis across Axial, Coronal, and Sagittal Views

2025-07-09

AI Summary

Existing MRI disease diagnosis models suffer performance degradation on single- or multi-view anatomical images (e.g., sagittal planes), limiting clinical utility in resource-constrained edge settings. Method: We propose a federated lightweight network optimized via Manta-Ray Foraging Optimization (MRFO) for automated architecture search, integrated with global model cloning and ConvNeXt modules to enable cross-view adaptive modeling and decentralized training. Contribution/Results: The resulting model contains only 1.217M parameters and occupies just 0.9 MB, drastically reducing deployment overhead. It achieves 92.44% accuracy on sagittal-plane diagnosis—surpassing state-of-the-art methods (88.37%–88.95%)—and demonstrates superior robustness and generalization across both single- and multi-view scenarios. This work establishes a scalable, high-accuracy federated MRI analysis paradigm tailored for medical edge environments with limited computational resources.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Multi-modal Vision
• Search and Optimization: Non-convex Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The framework is designed to improve performance in the analysis of combined as well as single anatomical perspectives for MRI disease diagnosis. It specifically addresses the performance degradation observed in state-of-the-art (SOTA) models, particularly when processing axial, coronal, and sagittal anatomical planes. The paper introduces the FOLC-Net framework, which incorporates a novel federated-optimized lightweight architecture with approximately 1.217 million parameters and a storage requirement of only 0.9 MB. FOLC-Net integrates Manta-ray foraging optimization (MRFO) mechanisms for efficient model structure generation, global model cloning for scalable training, and ConvNeXt for enhanced client adaptability. The model was evaluated on combined multi-view data as well as individual views, such as axial, coronal, and sagittal, to assess its robustness in various medical imaging scenarios. Moreover, FOLC-Net tests a ShallowFed model on different data to evaluate its ability to generalize beyond the training dataset. The results show that FOLC-Net outperforms existing models, particularly in the challenging sagittal view. For instance, FOLC-Net achieved an accuracy of 92.44% on the sagittal view, significantly higher than the 88.37% accuracy of study method (DL + Residual Learning) and 88.95% of DL models. Additionally, FOLC-Net demonstrated improved accuracy across all individual views, providing a more reliable and robust solution for medical image analysis in decentralized environments. FOLC-Net addresses the limitations of existing SOTA models by providing a framework that ensures better adaptability to individual views while maintaining strong performance in multi-view settings. The incorporation of MRFO, global model cloning, and ConvNeXt ensures that FOLC-Net performs better in real-world medical applications.

Problem

• Improves MRI disease diagnosis across axial, coronal, sagittal views
• Addresses performance degradation in SOTA models for anatomical planes
• Enhances adaptability and robustness in decentralized medical imaging

Innovation

• Federated-optimized lightweight architecture for MRI
• Manta-ray foraging optimization for model generation
• Global model cloning and ConvNeXt for adaptability