Automatic Identification of Ultrasound Images of the Tibial Nerve in Different Ankle Positions Using Deep Learning.

Peripheral nerve tension is known to be related to the pathophysiology of neuropathy; however, assessing this tension is difficult in a clinical setting. In this study, we aimed to develop a deep learning algorithm for the automatic assessment of tibial nerve tension using B-mode ultrasound imaging. To develop the algorithm, we used 204 ultrasound images of the tibial nerve in three positions: the maximum dorsiflexion position and -10° and -20° plantar flexion from maximum dorsiflexion. The images were taken of 68 healthy volunteers who did not have any abnormalities in the lower limbs at the time of testing. The tibial nerve was manually segmented in all images, and 163 cases were automatically extracted as the training dataset using U-Net. Additionally, convolutional neural network (CNN)-based classification was performed to determine each ankle position. The automatic classification was validated using five-fold cross-validation from the testing data composed of 41 data points. The highest mean accuracy (0.92) was achieved using manual segmentation. The mean accuracy of the full auto-classification of the tibial nerve at each ankle position was more than 0.77 using five-fold cross-validation. Thus, the tension of the tibial nerve can be accurately assessed with different dorsiflexion angles using an ultrasound imaging analysis with U-Net and a CNN.

Tibial nerve dynamics during ankle dorsiflexion: The relationship between stiffness and excursion of the tibial nerve.

Peripheral nerves extend with a gradual increase in stiffness and also with excursion, namely reduction of fiber bundle waviness, to adapt to joint movements. Although the close relationships between the tibial nerve (TN) excursion and stiffness during ankle dorsiflexion in cadaver studies, the precise in vivo their relationships remain unclear. We hypothesized that the excursion of the TN can be estimated from its stiffness in vivo using shear-wave elastography. This study aimed to analyze the relationships between the TN stiffness at the plantarflexion and dorsiflexion and TN excursion during dorsiflexion using ultrasonography. Twenty-one healthy adults participated in constant-velocity movements of the ankle joint with a 20° range from the maximum dorsiflexion, and the TN was imaged using an ultrasound imaging system. The maximum flow velocity value and the TN excursion distance per dorsiflexion were then calculated as indexes of excursion using the application software Flow PIV. The shear wave velocities of the TN at plantarflexion and dorsiflexion were also measured. Based on our single linear regression, the shear wave velocities of the TN at the plantarflexion had the strongest effect on the excursion indexes, followed by the those at dorsiflexion. Ultrasonographic shear wave velocity could predict the TN excursion if measured under mild plantarflexion of the ankle joint, and might have a close biomechanical relation to the total waviness of the TN.

Changes in tibial nerve stiffness during ankle dorsiflexion according to in-vivo analysis with shear wave elastography.

A more detailed assessment of pathological changes in the tibial nerve (TN) is needed to better assess how physical therapy influences TN pathologies. The cross-sectional nerve area can be used for TN assessment but may be influenced by individual differences in parameters, such as body height, body weight, and foot length. Therefore, there are no known reliable noninvasive quantitative methods for assessing TN neuropathy. Although recent ultrasonographic studies reported that TN stiffness changes could be used to assess TN neuropathies of the foot, these studies did not consider the joint position, and peripheral nerve tension can change with joint movement. Therefore, we considered that TN stiffness assessment could be improved by analyzing the relationship between ankle joint position and TN stiffness. This study aimed to investigate the relationship between TN stiffness and ankle angle changes using shear wave elastography. We hypothesized that the TN shear wave velocity significantly increases with ankle dorsiflexion and that the total ankle range or maximum dorsiflexion range correlates with the shear wave velocity. This cross-sectional study included 20 TNs of 20 healthy adults. Ultrasonography and shear wave elastography were used to evaluate the TN. TN stiffness was measured at 5 ankle positions as follows: maximum dorsiflexion (100% df), plantar flexion in the resting position (0% df), and 3 intermediate points (25% df, 50% df, and 75% df). TN shear wave velocity increased with an increase in ankle df angle. While total ankle range was significantly and negatively correlated with TN stiffness in all ankle positions, the maximum ankle df angle was significantly and negatively correlated only at 75% and 100% df. TN stiffness below 50% df may be affected by gliding or decreased nerve loosening, and TN stiffness above 75% df may be influenced by nerve tensioning. When measuring TN stiffness for diagnostic purposes, TN should be assessed at an ankle joint angle below 50% df.