Dataset Information

Quantifying normal and parkinsonian gait features from home movies: Practical application of a deep learning-based 2D pose estimator.

ABSTRACT: OBJECTIVE:Gait movies recorded in daily clinical practice are usually not filmed with specific devices, which prevents neurologists benefitting from leveraging gait analysis technologies. Here we propose a novel unsupervised approach to quantifying gait features and to extract cadence from normal and parkinsonian gait movies recorded with a home video camera by applying OpenPose, a deep learning-based 2D-pose estimator that can obtain joint coordinates from pictures or videos recorded with a monocular camera. METHODS:Our proposed method consisted of two distinct phases: obtaining sequential gait features from movies by extracting body joint coordinates with OpenPose; and estimating cadence of periodic gait steps from the sequential gait features using the short-time pitch detection approach. RESULTS:The cadence estimation of gait in its coronal plane (frontally viewed gait) as is frequently filmed in the daily clinical setting was successfully conducted in normal gait movies using the short-time autocorrelation function (ST-ACF). In cases of parkinsonian gait with prominent freezing of gait and involuntary oscillations, using ACF-based statistical distance metrics, we quantified the periodicity of each gait sequence; this metric clearly corresponded with the subjects' baseline disease statuses. CONCLUSION:The proposed method allows us to analyze gait movies that have been underutilized to date in a completely data-driven manner, and might broaden the range of movies for which gait analyses can be conducted.

SUBMITTER: Sato K

PROVIDER: S-EPMC6855634 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Quantifying normal and parkinsonian gait features from home movies: Practical application of a deep learning-based 2D pose estimator.

Sato Kenichiro K Nagashima Yu Y Mano Tatsuo T Iwata Atsushi A Toda Tatsushi T

PloS one 20191114 11

<h4>Objective</h4>Gait movies recorded in daily clinical practice are usually not filmed with specific devices, which prevents neurologists benefitting from leveraging gait analysis technologies. Here we propose a novel unsupervised approach to quantifying gait features and to extract cadence from normal and parkinsonian gait movies recorded with a home video camera by applying OpenPose, a deep learning-based 2D-pose estimator that can obtain joint coordinates from pictures or videos recorded wi ...[more]

PMID: 31725754

Similar Datasets

Project description:BackgroundThe step-by-step determination of the spatio-temporal parameters of gait is clinically relevant since it provides an estimation of the variability of specific gait patterns associated with frequent geriatric syndromes. In recent years, several methods, based on the use of magneto-inertial units (MIMUs), have been developed for the step-by-step estimation of the gait temporal parameters. However, most of them were applied to the gait of healthy subjects and/or of a single pathologic population. Moreover, spatial parameters in pathologic populations have been rarely estimated step-by-step using MIMUs. The validity of clinically suitable MIMU-based methods for the estimation of spatio-temporal parameters is therefore still an open issue. The aim of this study was to propose and validate a method for the determination of both temporal and spatial parameters that could be applied to normal and heavily compromised gait patterns.MethodsTwo MIMUs were attached above each subject's ankles. An instrumented gait mat was used as gold standard. Gait data were acquired from ten hemiparetic subjects, ten choreic subjects, ten subjects with Parkinson's disease and ten healthy older adults walking at two different gait speeds. The method detects gait events (GEs) taking advantage of the cyclic nature of gait and exploiting some lower limb invariant kinematic characteristics. A combination of a MIMU axes realignment along the direction of progression and of an optimally filtered direct and reverse integration is used to determine the stride length.ResultsOver the 4,514 gait cycles analyzed, neither missed nor extra GEs were generated. The errors in identifying both initial and final contact at comfortable speed ranged between 0 and 11 ms for the different groups analyzed. The stride length was estimated for all subjects with less than 3% error.ConclusionsThe proposed method is apparently extremely robust since gait speed did not substantially affect its performance and both missed and extra GEs were avoided. The spatio-temporal parameters estimates showed smaller errors than those reported in previous studies and a similar level of precision and accuracy for both healthy and pathologic gait patterns. The combination of robustness, precision and accuracy suggests that the proposed method is suitable for routine clinical use.

Project description:The parkinsonian gait disorder and freezing of gait are therapeutically demanding symptoms with considerable impact on quality of life. The aim of this study was to assess the role of subthalamic and nigral neurons in the parkinsonian gait control using intraoperative microelectrode recordings of basal ganglia neurons during a supine stepping task. Twelve male patients (56 ± 7 years) suffering from moderate idiopathic Parkinson's disease (disease duration 10 ± 3 years, Hoehn and Yahr stage 2), undergoing awake neurosurgery for deep brain stimulation, participated in the study. After 10 s resting, stepping at self-paced speed for 35 s was followed by short intervals of stepping in response to random 'start' and 'stop' cues. Single- and multi-unit activity was analysed offline in relation to different aspects of the stepping task (attentional 'start' and 'stop' cues, heel strikes, stepping irregularities) in terms of firing frequency, firing pattern and oscillatory activity. Subthalamic nucleus and substantia nigra neurons responded to different aspects of the stepping task. Of the subthalamic nucleus neurons, 24% exhibited movement-related activity modulation as an increase of the firing rate, suggesting a predominant role of the subthalamic nucleus in motor aspects of the task, while 8% of subthalamic nucleus neurons showed a modulation in response to the attentional cues. In contrast, responsive substantia nigra neurons showed activity changes exclusively associated with attentional aspects of the stepping task (15%). The firing pattern of subthalamic nucleus neurons revealed gait-related firing regularization and a drop of beta oscillations during the stepping performance. During freezing episodes instead, there was a rise of beta oscillatory activity. This study shows for the first time specific, task-related subthalamic nucleus and substantia nigra single-unit activity changes during gait-like movements in humans with differential roles in motor and attentional control of gait. The emergence of perturbed firing patterns in the subthalamic nucleus indicates a disrupted information transfer within the gait network, resulting in freezing of gait.

Project description:Freezing of gait is one of the most debilitating symptoms in Parkinson's disease as it causes falls and reduces mobility and quality of life. The pedunculopontine nucleus is one of the major nuclei of the mesencephalic locomotor region and has neurons related to anticipatory postural adjustments preceding step initiation as well as to the step itself, thus it may be critical for coupling posture and gait to avoid freezing. Because freezing of gait and postural impairments have been related to frontal lesions and frontal dysfunction such as executive function, we hypothesized that freezing is associated with disrupted connectivity between midbrain locomotor regions and medial frontal cortex. We used diffusion tensor imaging to quantify structural connectivity of the pedunculopontine nucleus in patients with Parkinson's disease with freezing of gait, without freezing, and healthy age-matched controls. We also included behavioural tasks to gauge severity of freezing of gait, quantify gait metrics, and assess executive cognitive functions to determine whether between-group differences in executive dysfunction were related to pedunculopontine nucleus structural network connectivity. Using seed regions from the pedunculopontine nucleus, we were able to delineate white matter connections between the spinal cord, cerebellum, pedunculopontine nucleus, subcortical and frontal/prefrontal cortical regions. The current study is the first to demonstrate differences in structural connectivity of the identified locomotor pathway in patients with freezing of gait. We report reduced connectivity of the pedunculopontine nucleus with the cerebellum, thalamus and multiple regions of the frontal cortex. Moreover, these structural differences were observed solely in the right hemisphere of patients with freezing of gait. Finally, we show that the more left hemisphere-lateralized the pedunculopontine nucleus tract volume, the poorer the performance on cognitive tasks requiring the initiation of appropriate actions and/or the inhibition of inappropriate actions, specifically within patients with freezing. These results support the notion that freezing of gait is strongly related to structural deficits in the right hemisphere's locomotor network involving prefrontal cortical areas involved in executive inhibition function.

Dataset Information

Quantifying normal and parkinsonian gait features from home movies: Practical application of a deep learning-based 2D pose estimator.

Publications

Quantifying normal and parkinsonian gait features from home movies: Practical application of a deep learning-based 2D pose estimator.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets