Markerless gait analysis in stroke survivors based on computer vision and deep learning

Moro, Matteo; Marchesi, Giorgia; Odone, Francesca; Casadio, Maura

doi:10.1145/3341105.3373963

Cited by 32 publications

(28 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly in future investigations, our methodology can be used for a complete characterization of the modified functional reach test in an easy way. It could also be transposed or coupled with marker-less algorithms for movement analysis as performed in [ 57 , 58 , 59 , 60 , 61 ], which are taking place in research and in the clinical practice to facilitate the clinical assessments [ 58 ]. Currently, given the pandemic situation, those could be even more important, since they can facilitate clinical assessments from home and/or telerehabilitation, also it may be coupled with haptic feedback to improve its outcome [ 62 ].…”

Section: Discussionmentioning

confidence: 99%

Modified Functional Reach Test: Upper-Body Kinematics and Muscular Activity in Chronic Stroke Survivors

Marchesi

Ballardini

Barone

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Effective control of trunk muscles is fundamental to perform most daily activities. Stroke affects this ability also when sitting, and the Modified Functional Reach Test is a simple clinical method to evaluate sitting balance. We characterize the upper body kinematics and muscular activity during this test. Fifteen chronic stroke survivors performed twice, in separate sessions, three repetitions of the test in forward and lateral directions with their ipsilesional arm. We focused our analysis on muscles of the trunk and of the contralesional, not moving, arm. The bilateral activations of latissimi dorsi, trapezii transversalis and oblique externus abdominis were left/right asymmetric, for both test directions, except for the obliquus externus abdominis in the frontal reaching. Stroke survivors had difficulty deactivating the contralesional muscles at the end of each trial, especially the trapezii trasversalis in the lateral direction. The contralesional, non-moving arm had muscular activations modulated according to the movement phases of the moving arm. Repeating the task led to better performance in terms of reaching distance, supported by an increased activation of the trunk muscles. The reaching distance correlated negatively with the time-up-and-go test score.

show abstract

Section: Discussionmentioning

confidence: 99%

Modified Functional Reach Test: Upper-Body Kinematics and Muscular Activity in Chronic Stroke Survivors

Marchesi

Ballardini

Barone

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Three studies have examined 2D monocular applications (25–60 Hz) of DeepLabCut against manual labelling or marker-based methods for the leg closest to the camera (sagittal view), in underwater running ( Cronin et al, 2019 ), countermovement jumping ( Drazan et al, 2021 ) and walking in stroke survivors ( Moro et al, 2020 ). Markerless joint center differences were 10–20 mm greater than marker-based motion capture, but no significant differences were found between methods for temporospatial and joint angle outcome measures during walking and underwater running, and therefore this method may be a suitable alternative to 2D marker-based motion capture ( Cronin et al, 2019 ; Moro et al, 2020 ). Strong correlations were found for joint angles during countermovement jumping compared to marker-based methods, however this study had to perform a knee and hip correction based on marker-based results (5.6°).…”

Section: Performance Of Current Markerless Applicationsmentioning

confidence: 99%

“…While markerless systems may still be considered in their infancy, there have been several studies that demonstrate markerless potential for clinical applications. DeepLabCut was used to extract walking sagittal 2D joint angles in stroke survivors, showing significant differences between the affected and unaffected side ( Moro et al, 2020 ). Cunningham et al (2019) examined 2D monocular segment angles of a multi-segmented trunk and head in young children with cerebral palsy, enabling automation of clinical tests to examine spine and head posture.…”

Section: Practical Applicationsmentioning

confidence: 99%

Applications and limitations of current markerless motion capture methods for clinical gait biomechanics

Wade

Needham

McGuigan

et al. 2022

PeerJ

138

View full text Add to dashboard Cite

Background Markerless motion capture has the potential to perform movement analysis with reduced data collection and processing time compared to marker-based methods. This technology is now starting to be applied for clinical and rehabilitation applications and therefore it is crucial that users of these systems understand both their potential and limitations. This literature review aims to provide a comprehensive overview of the current state of markerless motion capture for both single camera and multi-camera systems. Additionally, this review explores how practical applications of markerless technology are being used in clinical and rehabilitation settings, and examines the future challenges and directions markerless research must explore to facilitate full integration of this technology within clinical biomechanics. Methodology A scoping review is needed to examine this emerging broad body of literature and determine where gaps in knowledge exist, this is key to developing motion capture methods that are cost effective and practically relevant to clinicians, coaches and researchers around the world. Literature searches were performed to examine studies that report accuracy of markerless motion capture methods, explore current practical applications of markerless motion capture methods in clinical biomechanics and identify gaps in our knowledge that are relevant to future developments in this area. Results Markerless methods increase motion capture data versatility, enabling datasets to be re-analyzed using updated pose estimation algorithms and may even provide clinicians with the capability to collect data while patients are wearing normal clothing. While markerless temporospatial measures generally appear to be equivalent to marker-based motion capture, joint center locations and joint angles are not yet sufficiently accurate for clinical applications. Pose estimation algorithms are approaching similar error rates of marker-based motion capture, however, without comparison to a gold standard, such as bi-planar videoradiography, the true accuracy of markerless systems remains unknown. Conclusions Current open-source pose estimation algorithms were never designed for biomechanical applications, therefore, datasets on which they have been trained are inconsistently and inaccurately labelled. Improvements to labelling of open-source training data, as well as assessment of markerless accuracy against gold standard methods will be vital next steps in the development of this technology.

show abstract

“…To fine tune the network on our data, we consider 45 subjects and we randomly select 15 frames for each viewpoint (45 frames for each subject), then we manually label the position in the image plane of the landmarks: 4 markers on the bow, 5 markers on the violin (the 6th one is excluded because almost always occluded), 3 anatomic landmarks on the body -see Figure 2. The parameters used to train the network are the ones suggested in other applications, see [14]. Once the network is trained, for each test frame it provides a set of 2D landmarks…”

Section: D Landmarks Detectionmentioning

confidence: 99%

On The Precision Of Markerless 3d Semantic Features: An Experimental Study On Violin Playing

Moro

Casadio²,

Mrotek

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Human motion analysis is an essential task in several domains and, depending on the application field, it requires different level of accuracy. In the motor control field it is commonly performed with motion capture systems and infrared markers that guarantee a high accuracy. However, these systems are expensive, cumbersome, and may induce bias. An alternative to marker-based technologies are image-based markerless systems, that are cheaper and do not affect the naturalness of the motion. Although their accuracy level seems to limit their use in motor control field, a thorough quantitative comparison with marker-based techniques does not appear to be available yet. We compare the estimates of a 3D image-based marker-less pipeline we propose, with a standard marker-based system; the analysis is carried out on a multi-sensor dataset acquired to study the motion of violin players. The results we obtain on the precision level are suggesting that marker-less systems may successfully track performances in real-world settings.

show abstract

Markerless gait analysis in stroke survivors based on computer vision and deep learning

Cited by 32 publications

References 18 publications

Modified Functional Reach Test: Upper-Body Kinematics and Muscular Activity in Chronic Stroke Survivors

Modified Functional Reach Test: Upper-Body Kinematics and Muscular Activity in Chronic Stroke Survivors

Applications and limitations of current markerless motion capture methods for clinical gait biomechanics

On The Precision Of Markerless 3d Semantic Features: An Experimental Study On Violin Playing

Contact Info

Product

Resources

About