4.6 Review

A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Neurosciences

Computer vision quantification of whole-body Parkinsonian bradykinesia using a large multi-site population

Gareth Morinan et al.

Summary: Parkinson's disease is a common neurological disorder characterized by bradykinesia. Using computer vision to objectively quantify bradykinesia could standardize decision-making for treatment and clinical trials, as well as facilitate remote assessment.

NPJ PARKINSONS DISEASE (2023)

Article Computer Science, Hardware & Architecture

A multimodal discrimination method for the response to name behavior of autistic children based on human pose tracking and head pose estimation

Chunyi Song et al.

Summary: The incidence rate of autism spectrum disorder (ASD) has been increasing and currently stands at around 1 to 2%. Clinical ASD screening is time-consuming, requires extensive training, and is costly. Therefore, there is an urgent need for an automated method that is objective and accurate for early screening of autistic children on a large scale.

DISPLAYS (2023)

Article Chemistry, Analytical

Beyond the Edge: Markerless Pose Estimation of Speech Articulators from Ultrasound and Camera Images Using DeepLabCut

Alan Wrench et al.

Summary: Automatic feature extraction using pose estimation deep neural nets with transfer learning has been applied for markerless estimation of speech articulator keypoints. Evaluation results show that the method achieves accurate estimation of tongue and lip keypoints compared to the hand-labeled data.

SENSORS (2022)

Article Computer Science, Artificial Intelligence

Human activity recognition using temporal convolutional neural network architecture

Yair A. Andrade-Ambriz et al.

Summary: A temporal convolutional neural network method is proposed for analyzing and recognizing human activities using spatio-temporal features, achieving improved accuracy in classification results through optimal use of computational resources, and providing real-time classification results.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Article Computer Science, Artificial Intelligence

FastNet: Fast high-resolution network for human pose estimation

Yanmin Luo et al.

Summary: This paper proposes an efficient high-resolution network, named FastNet, for human pose estimation under computation-limited resources. The network utilizes multiple subnetworks, asymmetric convolution, and waterfall module to achieve precise keypoint localization and rich spatial information retention. Comprehensive experiments demonstrate superior results of the proposed method on benchmark datasets.

IMAGE AND VISION COMPUTING (2022)

Article Clinical Neurology

Head tremor in cervical dystonia: Quantifying severity with computer vision

Jeanne P. Vu et al.

Summary: A study developed a computer vision-based software system, CMOR, to quantify the oscillatory and directional aspects of head tremor (HT) in cervical dystonia (CD) patients from video recordings. The method demonstrated convergence with clinical severity ratings.

JOURNAL OF THE NEUROLOGICAL SCIENCES (2022)

Review Multidisciplinary Sciences

Healthcare applications of single camera markerless motion capture: a scoping review

Bradley Scott et al.

Summary: This review analyzes the current healthcare applications of single camera markerless motion capture technology, highlighting its use cases for different patient populations. While the technology performs well in single plane measurements, it lacks accuracy in tracking detailed 3D kinematics, requiring further improvement for clinical decision making.
Article Computer Science, Information Systems

Vision-Based Finger Tapping Test in Patients With Parkinson's Disease via Spatial-Temporal 3D Hand Pose Estimation

Zhilin Guo et al.

Summary: This study proposes a novel computer-vision approach using depth camera and spatial-temporal 3D hand pose estimation to capture and evaluate hand movements of Parkinson's Disease patients, overcoming the subjectivity of manual evaluations and the interference of wearable sensors on patients' movement.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2022)

Article Pharmacology & Pharmacy

Patient-led development of digital endpoints and the use of computer vision analysis in assessment of motor function in rare diseases

Elisa Ferrer-Mallol et al.

Summary: Digital health technologies are revolutionizing the way health outcomes are assessed, providing more objective and continuous data collection and analysis. This technology allows for home-based disease assessments, reducing patient burden and offering a more comprehensive understanding of patient experiences in the real world. The development of tools utilizing digital biomarkers for measuring drug efficacy in disease-specific outcomes is crucial for the successful development of new treatments, especially for rare and chronic complex conditions.

FRONTIERS IN PHARMACOLOGY (2022)

Article Rehabilitation

Quantifying step length using two-dimensional video in individuals with Parkinson's disease

Margot Stricker et al.

Summary: Individuals with Parkinson's disease have shorter step lengths, and those with a history of falls have even shorter step lengths. Reliable measurement of step length from 2D video can be a useful tool for managing patients with Parkinson's disease.

PHYSIOTHERAPY THEORY AND PRACTICE (2021)

Article Orthopedics

Assessing the accuracy of measuring leg length discrepancy and genu varum/valgum using a markerless motion analysis system

Robert J. Hurley et al.

Summary: Discrepancies in leg length measurements and varus/valgus knee measurements were found when evaluated using clinical, radiological and MMA modalities. Therefore, it is currently recommended to use a combination of two or more evaluation modalities when assessing patients for TKR.

JOURNAL OF ORTHOPAEDICS (2021)

Article Rehabilitation

Automating the Clinical Assessment of Independent Wheelchair Sitting Pivot Transfer Techniques

Lin Wei et al.

Summary: The study used a low-cost markerless motion capture camera and machine learning methods to assess the quality of independent wheelchair sitting pivot transfers. The results showed that the algorithms were able to accurately distinguish proper and improper techniques, with high precision and model accuracy, demonstrating the potential for objective assessment of transfer techniques using this approach.

TOPICS IN SPINAL CORD INJURY REHABILITATION (2021)

Article Health Care Sciences & Services

Analysis of gait synchrony and balance in neurodevelopmental disorders using computer vision techniques

Adel Ardalan et al.

Summary: This study proposes a computational pipeline using computer vision techniques as an ecological and precise method to quantify gait in children with neurodevelopmental disorders. The research found that children with NDDs have poorer gait synchrony and balance compared to typically developing children. This cost-effective method preserves the validity of results and increases access to more diverse research cohorts.

HEALTH INFORMATICS JOURNAL (2021)

Article Multidisciplinary Sciences

Gait changes over time in hospitalized older adults with advanced dementia: Predictors of mobility change

Sina Mehdizadeh et al.

Summary: The study measured changes in quantitative gait measures over a 10-week psychogeriatric admission period in older adults with dementia, finding that gait stability, step time, and step length decreased while step time and length variability increased. Men showed a greater decrease in gait stability compared to women, and individuals with mild neuropsychiatric symptoms experienced a decrease in sacrum mediolateral range of motion over the 10-week period, whereas those with more severe symptoms saw an increase. This study provides evidence of worsening gait mechanics and control during hospitalization in older adults with dementia, suggesting that quantitative gait monitoring in hospitals could help prevent adverse events and monitor rehabilitation outcomes.

PLOS ONE (2021)

Article Computer Science, Artificial Intelligence

Automated assessment of Parkinsonian finger-tapping tests through a vision-based fine-grained classification model

Hao Li et al.

Summary: The study introduces a novel vision-based fine-grained action recognition model for the finger-tapping test in PD patients, utilizing a three-stream fine-grained classification network and spatial-temporal attention mechanism to enhance assessment effectiveness and mitigate the impact of imbalanced data on neural networks.

NEUROCOMPUTING (2021)

Article Computer Science, Artificial Intelligence

Vision-assisted recognition of stereotype behaviors for early diagnosis of Autism Spectrum Disorders

Farhood Negin et al.

Summary: Computer-assisted medical diagnosis is gaining popularity, and in this paper, a non-intrusive vision-assisted method based on human action recognition is proposed to aid in the diagnosis of Autism Spectrum Disorder (ASD). By collecting a comprehensive video dataset and developing various frameworks, it was demonstrated that an action-recognition-based system could potentially assist clinicians in providing reliable, accurate, and timely diagnosis of ASD.

NEUROCOMPUTING (2021)

Article Computer Science, Information Systems

A Spatio-Temporal Attention-Based Model for Infant Movement Assessment From Videos

Binh Nguyen-Thai et al.

Summary: Developing a method for assessing fidgety movements in infants from consumer-grade videos using human poses and spatio-temporal graph convolutional networks has shown significant improvement in cerebral palsy screening, outperforming existing methods with better interpretability on a real-life video dataset collected at an Australian hospital.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Article Health Care Sciences & Services

Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data

Jong Taek Lee et al.

Summary: This study developed a framework for classifying dependence in ambulation using a 3D convolutional neural network on video data recorded by smartphones during inpatient rehabilitation therapy for stroke patients. The proposed framework can alert clinicians or caregivers when stroke patients with dependent ambulation move alone without assistance, facilitating the design of individualized rehabilitation strategies.

JOURNAL OF PERSONALIZED MEDICINE (2021)

Article Chemistry, Analytical

A Clinically Interpretable Computer-Vision Based Method for Quantifying Gait in Parkinson's Disease

Samuel Rupprechter et al.

Summary: A novel computer vision-based approach for estimating the severity of gait impairment in Parkinson's disease was proposed and evaluated in this study. By analyzing videos of patients' gaits, an objective assessment can be provided to support clinical decision-making.

SENSORS (2021)

Article Multidisciplinary Sciences

Using 2D video-based pose estimation for automated prediction of autism spectrum disorders in young children

Nada Kojovic et al.

Summary: Recent clinical research in autism focuses on single feature extraction, utilizing deep neural networks to differentiate between ASD children and typically developing peers. The model achieved an 80.9% accuracy with prediction probability positively correlated to the overall level of symptoms of autism. The study suggests the potential of reliable machine-learning-based ASD screening in the near future.

SCIENTIFIC REPORTS (2021)

Article Computer Science, Information Systems

Identification of Abnormal Movements in Infants: A Deep Neural Network for Body Part-Based Prediction of Cerebral Palsy

Dimitrios Sakkos et al.

Summary: This paper explores new methods for automated early diagnosis of cerebral palsy, including using a deep learning framework and visualization techniques for infant body movement classification. Experimental results show that the proposed method outperforms previous pose-based techniques and other features from related works in terms of consistency and robustness, while the visualization framework enhances interpretability and adoption in the medical domain.

IEEE ACCESS (2021)

Article Engineering, Biomedical

Video Based Shuffling Step Detection for Parkinsonian Patients Using 3D Convolution

Xugang Cao et al.

Summary: This study proposes a purely video-based method for automatically detecting the shuffling step of Parkinson's Disease patients with an average accuracy of 90.8% and assessing the severity of walking abnormalities, leading to more frequent and accurate monitoring of the patients' condition at lower costs.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2021)

Article Clinical Neurology

Accuracy of Smartphone Video for Contactless Measurement of Hand Tremor Frequency

Stefan Williams et al.

Summary: The study demonstrates that using computer vision technology can accurately measure hand tremor frequency without the need for traditional accelerometry. This contactless method shows excellent agreement with the gold standard measure and could be a valuable tool in clinical settings and research studies for assessing tremor frequency.

MOVEMENT DISORDERS CLINICAL PRACTICE (2021)

Article Computer Science, Information Systems

Bradykinesia Recognition in Parkinson's Disease via Single RGB Video

Bo Lin et al.

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA (2020)

Article Computer Science, Information Systems

Vision-Based Freezing of Gait Detection With Anatomic Directed Graph Representation

Kun Hu et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Article Engineering, Biomedical

Assessment of Parkinsonian gait in older adults with dementia via human pose tracking in video data

Andrea Sabo et al.

JOURNAL OF NEUROENGINEERING AND REHABILITATION (2020)

Article Clinical Neurology

The discerning eye of computer vision: Can it measure Parkinson's finger tap bradykinesia?

Stefan Williams et al.

JOURNAL OF THE NEUROLOGICAL SCIENCES (2020)

Article Computer Science, Artificial Intelligence

Supervised classification of bradykinesia in Parkinson's disease from smartphone videos

Stefan Williams et al.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2020)

Article Engineering, Biomedical

Computer Vision to Automatically Assess Infant Neuromotor Risk

Claire Chambers et al.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2020)

Article Engineering, Biomedical

Vision-Based Method for Automatic Quantification of Parkinsonian Bradykinesia

Yu Liu et al.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2019)

Article Engineering, Biomedical

Objective and automatic classification of Parkinson disease with Leap Motion controller

A. H. Butt et al.

BIOMEDICAL ENGINEERING ONLINE (2018)

Article Biochemical Research Methods

Using Kinect to classify Parkinson's disease stages related to severity of gait impairment

Lacramioara Dranca et al.

BMC BIOINFORMATICS (2018)

Article Engineering, Biomedical

Automatic Timed Up-and-Go Sub-Task Segmentation for Parkinson's Disease Patients Using Video-Based Activity Classification

Tianpeng Li et al.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2018)

Article Engineering, Biomedical

Assessment of a markerless motion analysis system for manual wheelchair application

Jacob Rammer et al.

JOURNAL OF NEUROENGINEERING AND REHABILITATION (2018)

Article Engineering, Biomedical

Kinect-based assessment of proximal arm non-use after a stroke

K. K. A. Bakhti et al.

JOURNAL OF NEUROENGINEERING AND REHABILITATION (2018)

Article Engineering, Biomedical

Vision-based assessment of parkinsonism and levodopa-induced dyskinesia with pose estimation

Michael H. Li et al.

JOURNAL OF NEUROENGINEERING AND REHABILITATION (2018)

Article Clinical Neurology

Longitudinal evaluation of upper extremity reachable workspace in ALS by Kinect sensor

Evan De Bie et al.

AMYOTROPHIC LATERAL SCLEROSIS AND FRONTOTEMPORAL DEGENERATION (2017)

Article Medicine, General & Internal

Parkinson disease

Werner Poewe et al.

NATURE REVIEWS DISEASE PRIMERS (2017)

Article Orthopedics

Measurement of active shoulder motion using the Kinect, a commercially available infrared position detection system

Frederick A. Matsen et al.

JOURNAL OF SHOULDER AND ELBOW SURGERY (2016)

Article Engineering, Biomedical

Motion tracking and gait feature estimation for recognising Parkinson's disease using MS Kinect

Ondrej Tupa et al.

BIOMEDICAL ENGINEERING ONLINE (2015)

Review Biotechnology & Applied Microbiology

Mobile Phone-Based Joint Angle Measurement for Functional Assessment and Rehabilitation of Proprioception

Quentin Mourcou et al.

BIOMED RESEARCH INTERNATIONAL (2015)

Article Computer Science, Artificial Intelligence

A computer vision framework for finger-tapping evaluation in Parkinson's disease

Taha Khan et al.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2014)

Article Multidisciplinary Sciences

Automated Assessment of Upper Extremity Movement Impairment due to Stroke

Erienne V. Olesh et al.

PLOS ONE (2014)

Article Rehabilitation

The Effect of Neck Pain on Cervical Kinematics, as Assessed in a Virtual Environment

Hilla Sarig Bahat et al.

ARCHIVES OF PHYSICAL MEDICINE AND REHABILITATION (2010)

Article Clinical Neurology

Early prediction of cerebral palsy by computer-based video analysis of general movements: a feasibility study

Lars Adde et al.

DEVELOPMENTAL MEDICINE AND CHILD NEUROLOGY (2010)

Article Computer Science, Artificial Intelligence

Markerless Motion Capture through Visual Hull, Articulated ICP and Subject Specific Model Generation

Stefano Corazza et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2010)

Article Computer Science, Artificial Intelligence

A vision-based analysis system for gait recognition in patients with Parkinson's disease

Chien-Wen Cho et al.

EXPERT SYSTEMS WITH APPLICATIONS (2009)