Robust quantification of spontaneous muscular activities by simultaneous interpretation of sEMG data

摘要

Robust quantification of spontaneous mechanical activities of resting musculature (SMAM1) by diffusionweighted imaging (DWI) is of high interest for the assessment of activity distribution and spontaneous muscle fiber imaging in healthy and non-healthy population. However, detection can be hampered due to varying signal intensity, noise, vessel pulsation and voluntary movement.~2 Strong correlation between simultaneously applied MRcompatible surface EMG (sEMG) and SMAM is utilized to overcome these limitations.~3 A deep learning approach consisting of sEMG classification and DWI activity detection is proposed to enable accurate quantification of SMAMs.