Predicting Muscle Thickness Deformation from Muscle Activation Patterns: A Dual-Attention Framework

Abstract-- Understanding the relationship between muscle activation and thickness deformation is critical for diagnosing muscle-related diseases and monitoring muscle health. Although ultrasound technique can measure muscle thickness change during muscle movement, its application in portable devices is limited by wiring and data collection challenges. Experimental results with six healthy subjects showed that the approach could accurately predict muscle excursion with an average precision of 0.923 0.900mm, which shows that this method can facilitate real-time portable muscle health monitoring, Our proposed method employs a novel dual-attention framework to correlate muscle activation with thickness I. INTRODUCTION This framework included hierarchical selfattention Quantifying the relationship between muscle activation [12] and cross-attention [13] mechanisms. Selfattention and thickness deformation is essential for understanding captured long-range signal dependencies and dynamically muscle dynamics and health [1], [2], particularly in conditions adjusted the importance of different signal components such as Facioscapulohumeral Dystrophy [3]. Traditional [14], while cross-attention merged and synthesized ultrasound imaging can visualize muscle thickness these features to provide comprehensive MTD information.