UltraTimTrack: a Kalman-filter-based algorithm to track muscle fascicles in ultrasound image sequences

Abstract

Background Brightness-mode (B-mode) ultrasound is a valuable tool to non-invasively image skeletal muscle architectural changes during movement, but automatically estimating architectural features such as fascicle length remains a major challenge. Existing fascicle tracking algorithms either require time-consuming drift corrections or yield noisy estimates that require post-processing. We therefore aimed to develop an algorithm that tracks fascicles without drift and noise across a range of experimental conditions and image acquisition settings. Methods We applied a Kalman filter to combine fascicle length and fascicle angle estimates from existing and openly available UltraTrack and TimTrack algorithms into a hybrid algorithm called UltraTimTrack. We applied the hybrid algorithm to ultrasound image sequences collected from the human medial gastrocnemius of healthy individuals (N=8, 4 women), who performed cyclical submaximal plantar flexion contractions or remained at rest during passive ankle joint rotations at given frequencies and amplitudes whilst seated in a dynamometer chair. We quantified the algorithm’s tracking accuracy, noise, and drift as the respective mean, cycle-to-cycle, and accumulated between-contraction variability in fascicle length and fascicle angle. We expected UltraTimTrack’s estimates to be less noisy and to drift less across experimental conditions and image acquisition settings, compared with estimates from its parent algorithms. Results The proposed algorithm had low-noise estimates like UltraTrack and was drift-free like TimTrack across the broad range of conditions we tested. Estimated fascicle length and fascicle angle deviations accumulated to 2.1 ± 1.3 mm (mean ± s.d.) and 0.8 ± 0.7 deg, respectively, over 120 cyclical contractions. Average cycle-to-cycle variability was 1.4 ± 0.4 mm and 0.6 ± 0.3 deg, respectively. In comparison, UltraTrack had similar cycle-to-cycle variability (1.1 ± 0.3 mm, 0.5 ± 0.1 deg) but greater cumulative deviation (67.0 ± 59.3 mm, 9.3 ± 8.6 deg), whereas TimTrack had similar cumulative deviation (1.9 ± 2.2 mm, 0.9 ± 1.0 deg) but greater variability (3.5 ± 1.0 mm, 1.4 ± 0.5 deg). UltraTimTrack was significantly less affected by experimental conditions and image acquisition settings than its parent algorithms. It also performed well on a previously published image sequence from the human tibialis anterior, yielding a smaller root-mean-square deviation from manual tracking (fascicle length: 2.7 mm, fascicle angle: 0.7 deg) than a recently proposed hybrid algorithm (fascicle length: 4.5 mm, fascicle angle: 0.8 deg) and a machine-learning (DL_Track) algorithm (fascicle length: 8.2 mm, fascicle angle: 4.8 deg). Conclusion We developed a Kalman-filter-based method to improve fascicle tracking from B-mode ultrasound image sequences. The proposed algorithm provides low-noise, drift-free estimates of muscle architectural changes that may better inform muscle function interpretations.