A tool for home-based rehabilitation allowing for clinical evaluation in a visual markerless scenario

A review of computational approaches for evaluation of rehabilitation exercises

Recent advances in data analytics and computer-aided diagnostics stimulate the vision of patient-centric precision healthcare, where treatment plans are customized based on the health records and needs of every patient. In physical rehabilitation, the progress in machine learning and the advent of affordable and reliable motion capture sensors have been conducive to the development of approaches for automated assessment of patient performance and progress toward functional recovery. The presented study reviews computational approaches for evaluating patient performance in rehabilitation programs using motion capture systems. Such approaches will play an important role in supplementing traditional rehabilitation assessment performed by trained clinicians, and in assisting patients participating in home-based rehabilitation. The reviewed computational methods for exercise evaluation are grouped into three main categories: discrete movement score, rule-based, and template-based approaches. The review places an emphasis on the application of machine learning methods for movement evaluation in rehabilitation. Related work in the literature on data representation, feature engineering, movement segmentation, and scoring functions is presented. The study also reviews existing sensors for capturing rehabilitation movements and provides an informative listing of pertinent benchmark datasets. The significance of this paper is in being the first to provide a comprehensive review of computational methods for evaluation of patient performance in rehabilitation programs.

The KIMORE Dataset: KInematic Assessment of MOvement and Clinical Scores for Remote Monitoring of Physical REhabilitation

This paper proposes a free dataset, available at the following link,¹named KIMORE, regarding different rehabilitation exercises collected by a RGB-D sensor. Three data inputs including RGB, depth videos, and skeleton joint positions were recorded during five physical exercises, specific for low back pain and accurately selected by physicians. For each exercise, the dataset also provides a set of features, specifically defined by the physicians, and relevant to describe its scope. These features, validated with respect to a stereophotogrammetric system, can be analyzed to compute a score for the subject's performance. The dataset also contains an evaluation of the same performance provided by the clinicians, through a clinical questionnaire. The impact of KIMORE has been analyzed by comparing the output obtained by an example of rule and template-based approaches and the clinical score. The dataset presented is intended to be used as a benchmark for human movement assessment in a rehabilitation scenario in order to test the effectiveness and the reliability of different computational approaches. Unlike other existing datasets, the KIMORE merges a large heterogeneous population of 78 subjects, divided into 2 groups with 44 healthy subjects and 34 with motor dysfunctions. It provides the most clinically-relevant features and the clinical score for each exercise.¹https://univpm-my.sharepoint.com/:f:/g/personal/p008099_staff_univpm_it/EiwbKIzk6N9NoJQx4J8aubIBx0o7tIa1XwclWp1NmRkA-w?e=F3jtBk.

Validity of the total body centre of gravity during gait using a markerless motion capture system

PURPOSE

The purpose of this study was to examine the validity of total body centre of gravity (COG) measurement during gait with markerless motion capture system (MLS) on the basis of values acquired with a marker-based motion capture system (MBS).

MATERIALS AND METHODS

Thirty young healthy subjects walked on a flat surface as coordinate data from their bodies were acquired using the Kinect v2 (as a MLS) and Vicon systems (as a MBS). COG was calculated using coordinate data of the total body. Comparisons of COG ensemble curves in the mediolateral and vertical directions were performed between MLS and MBS throughout the gait cycle. The relative consistency between these systems was assessed using Pearson correlation coefficients.

RESULTS

The COG trajectory made by using MLS data followed the trend of the COG trajectory with MBS in the mediolateral direction. In the vertical direction, however, the COG trajectories did not match between two systems. High correlation coefficients (r  > 0.79) were observed from 30% to 80% of the gait cycle. The greatest difference of COG between MLS and MBS in the mediolateral direction was 1.1 mm. Differences in the vertical direction appeared to be proportional to the distance between the participant and the Kinect v2 sensor.

CONCLUSION

In the mediolateral direction, COG calculated with MLS data during gait was validated with COG calculated on the basis of a MBS. Further correction of systematic error is necessary to improve the validity of COG calculations in the vertical direction.

A Hidden Semi-Markov Model based approach for rehabilitation exercise assessment

In this paper, a Hidden Semi-Markov Model (HSMM) based approach is proposed to evaluate and monitor body motion during a rehabilitation training program. The approach extracts clinically relevant motion features from skeleton joint trajectories, acquired by the RGB-D camera, and provides a score for the subject's performance. The approach combines different aspects of rule and template based methods. The features have been defined by clinicians as exercise descriptors and are then assessed by a HSMM, trained upon an exemplar motion sequence. The reliability of the proposed approach is studied by evaluating its correlation with both a clinical assessment and a Dynamic Time Warping (DTW) algorithm, while healthy and neurological disabled people performed physical exercises. With respect to the discrimination between healthy and pathological conditions, the HSMM based method correlates better with the physician's score than DTW. The study supports the use of HSMMs to assess motor performance providing a quantitative feedback to physiotherapist and patients. This result is particularly appropriate and useful for a remote assessment in the home.

Accuracy evaluation of the Kinect v2 sensor during dynamic movements in a rehabilitation scenario

In this paper, the accuracy evaluation of the Kinect v2 sensor is investigated in a rehabilitation scenario. The accuracy analysis is provided in terms of joint positions and angles during dynamic postures used in low-back pain rehabilitation. Although other studies have focused on the validation of the accuracy in terms of joint angles and positions, they present results only considering static postures whereas the rehabilitation exercise monitoring involves to consider dynamic movements with a wide range of motion and issues related to the joints tracking. In this work, joint positions and angles represent clinical features, chosen by medical staff, used to evaluate the subject's movements. The spatial and temporal accuracy is investigated with respect to the gold standard, represented by a stereophotogrammetric system, characterized by 6 infrared cameras. The results provide salient information for evaluating the reliability of Kinect v2 sensor for dynamic postures.