Motion Tracking in Diagnosis: Gait Disorders Classification with a Dual-Head Attentional Transformer-LSTM

Abstract

Gait and motion stability analysis in gait dysfunction problems is a very interesting research area. Usually, patients who undergo vestibular deafferentation are affected by changes in their dynamic balance. Therefore, it is important both patients and physicians are able to monitor the progress of the so-called vestibular compensation to observe the rehabilitation process objectively. Currently, the quantification of their progress is highly dependent on the physician’s opinion. In this article, we designed a novel methodology to classify the gait disorders associated with unilateral vestibular deafferentation in patients undergoing vestibular schwannoma surgery (model of complete vestibular loss associated with imbalance due to vestibular nerve section and eventual labyrinthectomy). We present a dual-head attentional transformer-LSTM (DHAT-LSTM) to evaluate the problem of rehabilitation from gait dysfunction, which is observed by a Kinect. A system consisting of a key-point-RCNN detector is used to compute body landmark measures and evaluate gait dysfunction based on a DHAT-LSTM network. This structure is used to quantitatively assess gait classification by tracking skeletal features based on the temporal variation of feature sequences. The proposed deep network analyses the features of the patient’s movement. These extracted high-level representations are then fed to the final evaluation of gait dysfunction. The result analytically demonstrates its effectiveness in classification evaluation when used in conjunction with state-of-the-art pose estimation and feature extraction techniques. An accuracy greater than 81% was achieved for given sets of individuals using velocity-based, angle-based, and position features for both the whole body and the symmetric features of the body.

A Computer Vision-Based System to Help Health Professionals to Apply Tests for Fall Risk Assessment

“…On the other hand, some investigations use Computer Vision techniques [ 56 , 57 , 58 , 59 , 60 ], while others have gone a step further and implement robots equipped with cameras and/or sensors. In the study described in [ 56 ], a person performs three types of exercises, and it is recorded by a camera located in a robot that follows a rectilinear trajectory, but the results are not correlated with any of the previously exposed tests, and many parameters of interest are not measured. In [ 61 ], a walker has been created for obtaining information during the TUG test, mainly through accelerometers.…”