Ultrasound Assessment of Muscle Atrophy During Short- and Medium-Term Head-Down Bed Rest.

OBJECTIVE

This study aims to investigate the feasibility of ultrasound technology for assessing muscle atrophy progression in a head-down bed rest model, providing a reference for monitoring muscle functional status in a microgravity environment.

METHODS

A 40-day head-down bed rest model using rhesus monkeys was established to simulate the microgravity environment in space. A dual-encoder parallel deep learning model was developed to extract features from B-mode ultrasound images and radiofrequency signals separately. Additionally, an up-sampling module incorporating the Coordinate Attention mechanism and the Pixel-attention-guided fusion module was designed to enhance direction and position awareness, as well as improve the recognition of target boundaries and detailed features. The evaluation efficacy of single ultrasound signals and fused signals was compared.

RESULTS

The assessment accuracy reached approximately 87% through inter-individual cross-validation in 6 rhesus monkeys. The fusion of ultrasound signals significantly enhanced classification performance compared to using single modalities, such as B-mode images or radiofrequency signals.

CONCLUSION

This study demonstrates that ultrasound technology combined with deep learning algorithms can effectively assess disuse muscle atrophy. The proposed approach offers a promising reference for diagnosing muscle atrophy under long-term immobilization, with significant application value and potential for widespread adoption.