Background and objective

Direct measurement of muscle-tendon junction (MTJ) position is important for understanding dynamic tendon behavior and muscle-tendon interaction in healthy and pathological populations. Traditionally, obtaining MTJ position during functional activities is accomplished by manually tracking the position of the MTJ in cine B-mode ultrasound images – a laborious and time-consuming process. Recent advances in deep learning have facilitated the availability of user-friendly open-source software packages for automated tracking. However, these software packages were originally intended for animal pose estimation and have not been widely tested on ultrasound images. Therefore, the purpose of this paper was to evaluate the efficacy of deep neural networks to accurately track medial gastrocnemius MTJ positions in cine B-mode ultrasound images across tasks spanning controlled loading during isolated contractions to physiological loading during treadmill walking.

Methods

Cine B-mode ultrasound images of the medial gastrocnemius MTJ were collected from 15 subjects (6M/9F, 23 yr, 71.9 kg, 1.8 m) during treadmill walking at 1.25 m/s and during maximal voluntary isometric plantarflexor contractions (MVICs). Five deep neural networks were trained using 480 manually-labeled images collected during walking, defined as the ground truth, and were then used to predict MTJ position in images from novel subjects: 1) during walking (novel-subject) and 2) during MVICs (novel-condition).

Results

We found an average mean absolute error of 1.26±1.30 mm and 2.61±3.31 mm between the ground truth and predicted MTJ positions in the novel-subject and novel-condition evaluations, respectively.

Conclusions

Our results provide support for the use of open-source software for creating deep neural networks to reliably track MTJ positions in B-mode ultrasound images. We believe this approach to MTJ position tracking is an accessible and time-saving solution, with broad applications for many fields, such as rehabilitation or clinical diagnostics.

中文翻译：

---

使用深度神经网络自动分析健康年轻人在孤立收缩和行走期间腓肠肌内侧肌腱连接处位移

背景和目标

肌肉-肌腱连接 (MTJ) 位置的直接测量对于了解健康和病理人群中的动态肌腱行为和肌肉-肌腱相互作用非常重要。传统上，在功能活动期间获取 MTJ 位置是通过手动跟踪电影 B 模式超声图像中 MTJ 的位置来完成的——这是一个费力且耗时的过程。深度学习的最新进展促进了用于自动跟踪的用户友好的开源软件包的可用性。然而，这些软件包最初是为动物姿势估计而设计的，并没有在超声图像上得到广泛的测试。所以，

方法

在以 1.25 m/s 的跑步机行走和最大自主等长跖屈肌收缩 (MVIC) 期间，从 15 名受试者（6M/9F，23 岁，71.9 kg，1.8 m）收集了内侧腓肠肌 MTJ 的电影 B 模式超声图像。五个深度神经网络使用在行走期间收集的 480 张手动标记的图像进行训练，定义为基本事实，然后用于预测来自新主题的图像中的 MTJ 位置：1）在行走期间（新主题）和 2）在 MVIC 期间（新条件）。

结果

我们发现在新主题和新条件评估中，地面实况和预测的 MTJ 位置之间的平均平均绝对误差分别为 1.26±1.30 毫米和 2.61±3.31 毫米。

结论

我们的结果为使用开源软件创建深度神经网络以可靠地跟踪 B 型超声图像中的 MTJ 位置提供了支持。我们相信这种 MTJ 位置跟踪方法是一种可访问且省时的解决方案，在许多领域都有广泛的应用，例如康复或临床诊断。