Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

E114232 - MAS - Muscle Analyzer System

Reference number
Coordinator Hytton Technologies AB
Funding from Vinnova SEK 4 745 668
Project duration September 2020 - September 2024
Status Completed
Venture Eurostars

Important results from the project

The MAS project developed a portable device to accurately assess muscle quality, specifically tailored for sarcopenia. By integrating microwave sensors, Raspberry Pi, NanoVNA, cloud services, and a user interface for real-time data, the project´s goal was realized. Phantom experiments validated the device´s accuracy, and a three-step AI algorithm estimated the thickness of skin, fat, and muscle layers. Secure communication via BACE+ and Hytton Cloud ensures safe data handling for clinical applications.

Expected long term effects

The MAS project developed a reliable, portable device for assessing muscle quality, validated through phantom experiments and clinical trials. Integrating a Raspberry Pi, NanoVNA, and a three-stage machine learning algorithm, it predicts tissue thickness and detects muscle quality variations. Dual communication via BACE+ and Hytton Cloud ensures secure, real-time data handling. This cost-effective tool enhances the detection and monitoring of sarcopenia and other muscle conditions for clinicians.

Approach and implementation

The MAS project has developed a portable and precise muscle quality assessment system. This device combines a Raspberry Pi, NanoVNA, and a touchscreen, featuring dual communication through BACE+ and Hytton Cloud for secure data transfer. The system´s accuracy was confirmed using Artificial Tissue-Emulating (ATE) phantoms. It employs a three-stage machine learning algorithm to predict tissue thicknesses, which has been effective in both phantom studies and clinical trials. The system is designed for scalability, reliability, and user-friendliness in clinical environments.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 3 January 2025

Reference number 2020-03595