Epidemiological studies have shown a relationship between hand exertion and risk of developing distal upper extremity musculoskeletal disorders (DUEMSDs). Recently, fatigue-failure models were proposed for estimating the risk of DUEMSD development. However, models that incorporate tendon strain are primarily based on in-vitro data and may be better informed using in-vivo data. This methodological pilot study aimed to establish an approach for correlating grip force and spatiotemporal strains of the flexor digitorum superficialis (FDS) tendon using ultrasound imaging. Three image texture correlation techniques to measure in-vivo strains were explored and compared: digital image correlation, direct deformation estimation, and StrainNet, a novel deep learning neural network for strain prediction. StrainNet resulted in more accurate strain measurements than conventional image assessment tools, enabled continuous prediction of FDS tendon strain, and allowed for comparison of median bulk tissue strain during isometric contraction to grip force. Future work will study more participants and viscoelastic behavior.