School of Computing, SASTRA Deemed University, Thanjavur 613401, India.
Centre for Biomechanics and Rehabilitation Technologies, Staffordshire University, Stoke-on-Trent ST4 2DE, UK.
Sensors (Basel). 2022 Aug 29;22(17):6498. doi: 10.3390/s22176498.
Existing approaches for automated tracking of fascicle length (FL) and pennation angle (PA) rely on the presence of a single, user-defined fascicle (feature tracking) or on the presence of a specific intensity pattern (feature detection) across all the recorded ultrasound images. These prerequisites are seldom met during large dynamic muscle movements or for deeper muscles that are difficult to image. Deep-learning approaches are not affected by these issues, but their applicability is restricted by their need for large, manually analyzed training data sets. To address these limitations, the present study proposes a novel approach that tracks changes in FL and PA based on the distortion pattern within the fascicle band. The results indicated a satisfactory level of agreement between manual and automated measurements made with the proposed method. When compared against feature tracking and feature detection methods, the proposed method achieved the lowest average root mean squared error for FL and the second lowest for PA. The strength of the proposed approach is that the quantification process does not require a training data set and it can take place even when it is not possible to track a single fascicle or observe a specific intensity pattern on the ultrasound recording.
现有的自动跟踪束长 (FL) 和羽状角 (PA) 的方法依赖于单个用户定义的束 (特征跟踪) 或在所有记录的超声图像中存在特定的强度模式 (特征检测)。在大型动态肌肉运动或难以成像的深层肌肉中，这些前提条件很少得到满足。深度学习方法不受这些问题的影响，但它们的适用性受到需要大型、手动分析的训练数据集的限制。为了解决这些限制，本研究提出了一种新的方法，该方法基于束带内的失真模式来跟踪 FL 和 PA 的变化。结果表明，所提出的方法与手动和自动测量之间具有令人满意的一致性。与特征跟踪和特征检测方法相比，所提出的方法在 FL 方面实现了最低的平均均方根误差，在 PA 方面实现了第二低的平均均方根误差。该方法的优点在于，量化过程不需要训练数据集，即使在无法跟踪单个束或在超声记录上观察到特定强度模式的情况下，也可以进行。
