ScholarWorks@숙명여자대학교

초록

The integration of artificial intelligence in wireless edge healthcare networks has revolutionized medical imaging, particularly in ultrasound diagnostics, where real-time processing and privacy preservation are paramount. Traditional centralized AI approaches face substantial obstacles in healthcare applications, including communication bottlenecks, privacy violations, and inadequate resource allocation among heterogeneous medical devices. This paper introduces a novel hierarchical Stackelberg game-based collaborative learning framework for ultrasound intelligence in wireless edge healthcare networks (HSGUL), which innovatively applies Stackelberg game mechanisms to ultrasound image analysis tasks. Based on the computational heterogeneity of medical edge devices, our framework establishes dynamic gaming relationships among cloud healthcare platforms, edge medical clusters, and ultrasound diagnostic nodes through a dual-pricing fair incentive process. This creates personalized hierarchical resource allocation strategies that obtain optimal Nash equilibrium solutions for ultrasound model training, effectively guiding edge-based medical AI models toward positive acceleration. The framework operates through a three-phase Stackelberg game mechanism coordinating resource allocation and incentive distribution across the healthcare network hierarchy. Experimental validation on cardiac, abdominal, and thyroid ultrasound datasets demonstrates superior performance compared to established baseline methods. HSGUL achieves 94.73 % accuracy on cardiac ultrasound classification while reducing communication overhead by 47 % compared to centralized approaches, maintaining patient data privacy through localized edge processing and enabling scalable deployment across diverse healthcare institutions with varying computational capabilities. © 2025 Elsevier B.V.

키워드