Automatic Extraction of Muscle Parameters with Attention UNet in Ultrasonography

Abstract

Automatically delineating the deep and superficial aponeurosis of the skeletal muscles from ultrasound images is important in many aspects of the clinical routine. In particular, finding muscle parameters, such as thickness, fascicle length or pennation angle, is a time-consuming clinical task requiring both human labour and specialised knowledge. In this study, a multi-step solution for automating these tasks is presented. A process to effortlessly extract the aponeurosis for automatically measuring the muscle thickness has been introduced as a first step. This process consists mainly of three parts. In the first part, the Attention UNet has been incorporated to automatically delineate the boundaries of the studied muscles. Afterwards, a specialised post-processing algorithm was utilised to improve (and correct) the segmentation results. Lastly, the calculation of the muscle thickness was performed. The proposed method has achieved similar to a human-level performance. In particular, the overall discrepancy between the automatic and the manual muscle thickness measurements was equal to 0.4 mm, a significant result that demonstrates the feasibility of automating this task. In the second step of the proposed methodology, the fascicle's length and pennation angle are extracted through an unsupervised pipeline. Initially, filtering is applied to the ultrasound images to further distinguish the tissues from the other muscle structures. Later, the well-known K-Means algorithm is used to isolate them successfully. As the last step, the dominant angle of the segmented muscle tissues is reported and compared with manual measurements. The proposed pipeline is showing very promising results in the evaluated dataset. Specifically, in the calculation of the pennation angle, the overall discrepancy between the automatic and the manual measurements was less than 2.22° (degrees), once more comparable with the human-level performance. Finally, regarding the fascicle length measurements, the results were divided based on the muscle properties. In the muscles where a large portion (or all) of the fascicles are located between the upper and lower aponeuroses, the proposed pipeline exhibits superb performance; otherwise, overall accuracy deteriorates due to errors caused by the trigonometric approximations needed for the length calculation.

Keywords: Attention-UNet; fascicles length; muscle thickness; pennation angle; segmentation; ultrasonography.

Figure 1

Sample ultrasound images along with their annotations. (a) Sample from the BB muscle, (b) from the GCM muscle, and (c) the TA muscle. The TA muscle comprises two compartments divided by the central fascia in the middle. These are depicted as 1 and 2.

Figure 2

Different image augmentations techniques were utilised during the training of the Attention-UNet.

Figure 3

In the case that the predicted mask is not optimal, the post-processing improved the result.

Figure 4

Centerline Distance: the red curves are the two boundaries; the white line is the centerline, and the yellow lines are the perpendicular chords to the centerline used for calculating the muscle thickness.

Figure 5

Flow chart of the muscle fascicles extraction pipeline.

Figure 6

Pennation angle is depicted with θ. The fascicle length is illustrated with yellow lines.

Figure 7

The Bland−Altman plots for the muscle thickness measurements for (a) biceps brachii, (b) gastrocnemius medialis, (c) tibialis anterior and (d) overall.

Figure 8

Qualitative results of the fascicles extraction in the validation set. The green lines are the algorithm’s output before the fascicles extended in the whole muscle and the yellow lines after.

Figure 9

Pennation angle’s Bland−Altman plots for (a) biceps brachii, (b) gastrocnemius medialis, (c) tibialis anterior, and (d) overall.

Figure 10

Fascicles Length’s Bland−Altman plots for (a) biceps brachii, (b) gastrocnemius medialis, (c) tibialis anterior, and (d) overall.