Assessment and Rating of Motor Cerebellar Ataxias With the Kinect v2 Depth Sensor: Extending Our Appraisal

Abstract

wide-based walking with large oscillation in the gait task), which is out of the scope of SARA. Our new system enables more accurate scoring of SARA and further provides additional information that is not currently evaluated with SARA. Therefore, it provides an easier, more accurate and more systematic description of CAs.

Quantitative evaluation of upper limb ataxia in spinocerebellar ataxias

“…Another study suggested that the gap between the Archimedean spiral template and the drawn spiral measured using the Image J software is related to the severity of ataxia and cerebellar volume 15 . Furthermore, a study that used a Kinect sensor demonstrated that compared with the fluctuation of the index finger, the average speed of the index finger in the nose–finger test was correlated more strongly with the SARA total score 17 …”

“…15 Furthermore, a study that used a Kinect sensor demonstrated that compared with the fluctuation of the index finger, the average speed of the index finger in the nose-finger test was correlated more strongly with the SARA total score. 17 The low sensitivity of velocity, yet high sensitivity of the distortion index B-spline may be attributed to the measurement methods used. Specifically, the pen-like tool we used may be more sensitive to the distance than to the velocity of hand movement; a previous study using a threedimensional movement analyzer suggested that the use of a pen detects disease-associated changes in distance more sensitively than those in velocity.…”

“…8,11 This is probably because of difficulties in visually evaluating how patients' upper limb movements deviate from the ideal trajectory. Several quantitative methods to evaluate ataxia have been developed [12][13][14][15][16][17] ; however, few studies have established an evaluation method of upper limb ataxia that is sensitive to disease progression.…”

Technological Evolution in the Instrumentation of Ataxia Severity Measurement

“…Clinical walking tasks used to evaluate ataxic gait include slow, preferred, and fast speed walking [154], SCAFI (8 meter/25-foot walk), Timed Up and Go (TUG) test [161], FARS (a timed walk of 50 feet) [19], SARA (sub-item one) [15], ICARS (gait disturbances sub-items one and two) [16], U-turning [162], walking in a circle [163], Tandem Walk test [146], Timed 25 Foot Walk Test [164], 10 metre Walk Test [165], Six Metre Walk Test [166], and Functional Ambulation Classification [167]. A review summarised the structure of typical motion capture techniques applied in neurological diseases across six categories of sensor systems including inertial kinematic, optical, magnetic, mechanical, acoustic, and computer vision [168].…”

Federated Deep Learning for the Diagnosis of Cerebellar Ataxia: Privacy Preservation and Auto-Crafted Feature Extractor

“…In the balance domain, a cloud-based ML implementation operating on data from IMU based wearable sensors were used to quantify the severity of truncal ataxia [1], [22]. Kinect c cameras [23], kinematic sensors [24]- [27], pressure-sensitive walkway [28], infrared camera [29], and S-band sensing [30] framework were employed to differentiate between the gait of individuals with and without ataxia. The systems described above modeled motor tasks assessed using ataxia clinical scales.…”