Automatic Assessment of Upper Extremity Function and Mobile Application for Self-Administered Stroke Rehabilitation.

Rehabilitation training is essential for a successful recovery of upper extremity function after stroke. Training programs are typically conducted in hospitals or rehabilitation centers, supervised by specialized medical professionals. However, frequent visits to hospitals can be burdensome for stroke patients with limited mobility. We consider a self-administered rehabilitation system based on a mobile application in which patients can periodically upload videos of themselves performing reach-to-grasp tasks to receive recommendations for self-managed exercises or progress reports. Sensing equipment aside from cameras is typically unavailable in the home environment. A key contribution of our work is to propose a deep learning-based assessment model trained only with video data. As all patients carry out identical tasks, a fine-grained assessment of task execution is required. Our model addresses this difficulty by learning RGB and optical flow data in a complementary manner. The correlation between the RGB and optical flow data is captured by a novel module for modality fusion using cross-attention with Transformers. Experiments showed that our model achieved higher accuracy in movement assessment than existing methods for action recognition. Based on the assessment model, we developed a patient-centered, solution-based mobile application for upper extremity exercises for hemiplegia, which can recommend 57 exercises with three levels of difficulty. A prototype of our application was evaluated by potential end-users and achieved a good quality score on the Mobile Application Rating Scale (MARS).

Ultrasonographic examination of the safe zone for medial needle approach towards the median-innervated flexor digitorum profundus muscle: Effect of changes in position of the forearm.

The flexor digitorum profundus (FDP) is a forearm flexor muscle. Certain cases require the needle to be inserted accurately and safely into the deep, lateral portion of the FDP, which is innervated by the anterior interosseous nerve. In this study, we compared 2 techniques for approaching the median-innervated FDP (MFDP) medially, each according to the position of the forearm, supinated or pronated. The forearms of healthy volunteers without any musculoskeletal problems of the upper extremities were examined. Using high-resolution ultrasonography, the medial aspects of the forearms were scanned with elbows flexed at 90°. Using the images obtained, several parameters for distance and angle were measured in 2 different positions: forearm-supinated and forearm-pronated. Thirty-seven forearms from the volunteers were subject to examination. The angle α, which is the valid angle of insertion when approaching with the needle towards the deeply located MFDP, slightly increased from 22.89° to 23.41° when the forearm was pronated from the supinated position; however, this increase was not statistically significant. In contrast, the angle ß, which is the safe angle of insertion when approaching with the needle towards the MFDP without contacting the ulnar nerve, was significantly increased from 41.40° to 46.80° upon forearm pronation. Because the safe angle of insertion of the needle medially into the MFDP increases with forearm pronation, the forearm-pronated position is recommended, instead of the forearm-supinated position, when inserting a needle into the MFDP in the medial aspect of the forearm.

Ultrasonographic Assessment of the Safe Zone for Carpal Tunnel Intervention: A Comparison Between Healthy Individuals and Patients With Carpal Tunnel Syndrome.

OBJECTIVE: To compare transverse and longitudinal safe zones using ultrasonography between healthy individuals and patients with carpal tunnel syndrome (CTS). METHODS: This was a prospective observational case-control study. Forty wrists from 20 healthy individuals and 40 wrists from 24 patients with CTS were examined. Patients with CTS were classified into three groups (mild, moderate, and severe CTS) based on electrodiagnostic findings. Using ultrasonography, we measured the distance between the median nerve and ulnar vessels to identify the transverse safe zone, and between the distal flexor retinaculum and superficial palmar artery arch to identify the longitudinal safe zone. RESULTS: The transverse and longitudinal safe zones were significantly different between participants with CTS and those without CTS. The transverse safe zone significantly differed between the mild and severe CTS groups, while the longitudinal safe zone was not significantly different between the groups. The cross-sectional area of the median nerve negatively correlated with the transverse and longitudinal safe zones. CONCLUSION: Transverse and longitudinal safe zones were narrower in patients with CTS than in the healthy group. A significant difference was observed between patients with mild CTS and those with severe CTS. Furthermore, the cross-sectional area of the median nerve was directly proportional to the degree of narrowing of the transverse and longitudinal safe zones.

Ultrasonographic anatomy of posterior antebrachial cutaneous nerve in healthy subjects.

INTRODUCTION/AIMS: The posterior antebrachial cutaneous nerve (PACN) is one of the cutaneous branches of the radial nerve, and receives sensory input from the posterior arm and forearm. The aim of this study is to describe the ultrasonographic anatomy of the PACN. METHODS: PACN and its branches were scanned using ultrasonography in 30 healthy volunteers. The distances between the epicondylar line and the bifurcation site of each branch of PACN (A) point of separation of the radial nerve and the PACN, (B) point of separation of the anterior and posterior divisions, (C) point of bifurcation of the posterior division into the epicondylar and anconeus branches), cross-sectional areas and depths from the skin surface to each nerve at positions A, B, and C were measured. RESULTS: The mean distance from the epicondylar line to A, B, and C was 10.01 ± 0.82 cm, 7.46 ± 0.98 cm, and 4.02 ± 1.16 cm, respectively. The mean depth from the skin surface at A, B, and C was 1.00 ± 0.19 cm, 0.72 ± 0.19 cm, and 0.51 ± 0.12 cm, respectively. DISCUSSION: Ultrasonographic visualization of the PACN and its major branches was feasible. The reference values in this study may be helpful for more accurate sonographic assessment and electrophysiologic study, and contribute to safer interventions around the elbow region.

Is Abnormal Electrodiagnostic Finding Related to the Cross-Sectional Area of the Nerve Root in Cervical Radiculopathy?

OBJECTIVE: To assess the relevance of electrodiagnosis (EDX) in the cross-sectional area (CSA) of the nerve root of patients with cervical radiculopathy (CR) by using high-resolution ultrasonography (HRUS). METHODS: The CSAs of the cervical nerve roots at C5, C6, and C7 were measured bilaterally using HRUS in 29 patients with unilateral CR whose clinical symptoms, magnetic resonance imaging (MRI) findings, and EDX results corresponded with each other (CR-A group), and in 26 patients with unilateral CR whose clinical symptoms and MRI findings matched with each other but did not correspond with the EDX findings (CR-B group). RESULTS: The CSA of the affected side in each nerve root was significantly larger than that of the unaffected side in both the CR-A and CR-B groups. The side-to-side difference in the bilateral CSAs of the nerve root and the ratio of the CSAs between the unaffected and affected sides were statistically larger in the CR-A group than in the CR-B group. CONCLUSION: The increased CSAs in the CR-A group reflect the physiological changes of the cervical nerve root, which is supported by the EDX findings.