Comparison of decomposition algorithms for identification of single motor units in ultrafast ultrasound image sequences of low force voluntary skeletal muscle contractions

Abstract

Objective: In this study, the aim was to compare the performance of four spatiotemporal decomposition algorithms (stICA, stJADE, stSOBI, and sPCA) and parameters for identifying single motor units in human skeletal muscle under voluntary isometric contractions in ultrafast ultrasound image sequences as an extension of a previous study. The performance was quantified using two measures: (1) the similarity of components' temporal characteristics against gold standard needle electromyography recordings and (2) the agreement of detected sets of components between the different algorithms.

Results: We found that out of these four algorithms, no algorithm significantly improved the motor unit identification success compared to stICA using spatial information, which was the best together with stSOBI using either spatial or temporal information. Moreover, there was a strong agreement of detected sets of components between the different algorithms. However, stJADE (using temporal information) provided with complementary successful detections. These results suggest that the choice of decomposition algorithm is not critical, but there may be a methodological improvement potential to detect more motor units.

Keywords: Blind source separation; Concentric needle electromyography; Decomposition algorithms; Motor units; Ultrafast ultrasound.

Fig. 1

Framework for MU identification in ultrafast ultrasound (UUS) image sequences was composed of four stages. A The first stage; data acquisition. Collecting synchronized UUS and concentric needle electromyography (EMG) measurements on the biceps brachii under low force voluntary isometric contractions. B The second stage; calculating tissue velocities (based on the UUS radiofrequency signals). C The third stage; data decomposition. We inserted each region-of-interest (ROI, 25 in total) into four different decomposition algorithms (see Table 1) to extract 25 spatiotemporal components. D The fourth and final stage; post-processing. We selected one optimal component out of 625 (25 components in each of the 25 ROIs) based on its distance to the needle tip (< 10 mm) and maximal agreement to MU firing rate in terms of RoA. The selected components’ features are then compared between the different decomposition algorithms

Fig. 2

Performance evaluation of the decomposition algorithms (red points) with stICA08 (blue points) as the reference algorithm. The comparison between the algorithms’ performance is based on (1) firing pattern agreement between the components and the EMG reference (RoA), and (2) agreement between the different algorithms’ identified component sets (CIDR). The components’ RoA values were divided into groups; A high-success group (75% ≤ RoA ≤ 100%), and B semi-success group (50% ≤ RoA < 75%). Note that the number of components at the x-axis denotes each algorithm’s number of components within the pre-defined group (high-success or semi-success)