Skip to main content
Visual Computing for Industry, Biomedicine, and Art
Fig. 5 | Visual Computing for Industry, Biomedicine, and Art

Fig. 5

From: Automated analysis of pectoralis major thickness in pec-fly exercises: evolving from manual measurement to deep learning techniques

Fig. 5

PMaj thickness change for the same load training intensity at two different biofeedback conditions (with and without RUSI biofeedback) (n = 25). In graphs, the curves represent the average values of the PMaj thickness change, while the envelope areas represent the standard deviation of the PMaj thickness change. (a) represents the PMaj thickness change with different biofeedback conditions at the low-moderate load training intensity (50% of 1-RM); (b) represents the PMaj thickness change with different biofeedback conditions at the high load training intensity (80% of 1-RM). For the assigned load training intensity with RUSI biofeedback (on), the PMaj thickness change was significantly increased for low-moderate training intensity as well as for high-intensity training compared to the corresponding load training intensity without RUSI biofeedback (off). This emphasizes the important role of RUSI visual biofeedback in the process of muscle thickness change

Back to article page