Using computer-based video analysis in the study of fidgety movements

Adde, Lars; Helbostad, Jorunn L.; Jensenius, Alexander Refsum; Taraldsen, Gunnar; Støen, Ragnhild

doi:10.1016/j.earlhumdev.2009.05.003

Cited by 92 publications

(139 citation statements)

References 19 publications

Supporting

Mentioning

132

Contrasting

Unclassified

Order By: Relevance

“…Although it is claimed that the identification of fidgety movements by the GMA does not depend on the rate of their occurrence (i.e. their quantity), 11 these results suggest that the total amount of movement captured by computer-based analysis does reflect a movement pattern that indicates that CP will not develop.Low centroid of motion standard deviation values imply a stable spatial centre in the motion image and seem to correlate with both the presence of fidgety movements in a previous study 18 and non-development of CP in the present study. A stable centroid of motion may reflect the ongoing stream of small movements in the whole body as a system, described in the GMA methodology as fidgety movements.…”

supporting

confidence: 76%

“…Using the customized software, movement variables have been demonstrated to identify infants with fidgety movements with high accuracy. 18 The aim of this study was to study how variables derived by the computer-based video analysis tool during the fidgety movements period can predict later CP. We also wanted to explore if the derived variables could predict gross motor function level in children diagnosed with CP.…”

mentioning

confidence: 99%

See 1 more Smart Citation

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

Adde

Helbostad

Jensenius

et al. 2010

Develop Med Child Neuro

Self Cite

110

162

View full text Add to dashboard Cite

AIM The aim of this study was to investigate the predictive value of a computer-based video analysis of the development of cerebral palsy (CP) in young infants.METHOD A prospective study of general movements used recordings from 30 high-risk infants (13 males, 17 females; mean gestational age 31wks, SD 6wks; range 23-42wks) between 10 and 15 weeks post term when fidgety movements should be present. Recordings were analysed using computer vision software. Movement variables, derived from differences between subsequent video frames, were used for quantitative analyses. CP status was reported at 5 years.RESULTS Thirteen infants developed CP (eight hemiparetic, four quadriparetic, one dyskinetic; seven ambulatory, three non-ambulatory, and three unknown function), of whom one had fidgety movements. Variability of the centroid of motion had a sensitivity of 85% and a specificity of 71% in identifying CP. By combining this with variables reflecting the amount of motion, specificity increased to 88%. Nine out of 10 children with CP, and for whom information about functional level was available, were correctly predicted with regard to ambulatory and non-ambulatory function.INTERPRETATION Prediction of CP can be provided by computer-based video analysis in young infants. The method may serve as an objective and feasible tool for early prediction of CP in highrisk infants.Cerebral palsy (CP) is a permanent disorder in the development of movement and posture in the developing fetal or infant brain 1 and is one of the major disabilities that result from extremely preterm birth. [2][3][4] The utility of predictive assessment tools in young infants is limited by the need for expensive equipment and highly experienced personnel, as well as low accuracy. Although the primary insult(s) cannot be repaired, early identification of CP enables intervention to be instituted while the plasticity of the nervous system is high. [5][6][7][8] Early identification may also lead to more focused follow-up and reassure the parents of those children who are unlikely to develop CP.In young infants, neurological damage is typically expressed by means of generalized and non-specific dysfunction. 9 The General Movement Assessment (GMA), based on systematic observation of infants' spontaneous movements from video recordings, has been shown to predict CP with high accuracy. 10,11 The absence of fidgety movements at 2 to 4 months corrected age may identify infants who will develop CP with more than 90% sensitivity. 10,[12][13][14] Although the GMA has been demonstrated to predict CP with high accuracy, it depends on highly experienced observers, and its use in clinical practice is limited. 12,15,16 A software program developed within the Max/MSP/Jitter environment for analysing music-related movements in musicians and dancers 17 has recently been customized for the purpose of studying fidgety movements. Using the customized software, movement variables have been demonstrated to identify infants with fidgety movements with high accuracy. 18 The aim of...

show abstract

supporting

confidence: 76%

mentioning

confidence: 99%

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

Adde

Helbostad

Jensenius

et al. 2010

Develop Med Child Neuro

Self Cite

110

162

View full text Add to dashboard Cite

show abstract

“…All recordings were performed during active wakefulness using a standardized set-up with a commercially available digital video camera (Panasonic HX-DC2) on a tripod with a standardized distance and angle to the mattress where the infant was placed (18,20). All infants were dressed in a white "onesie".…”

Section: Video Recordingmentioning

confidence: 99%

“…The video analysis software has been described in detail previously (19,20). The video contains 25 frames per second with a resolution of 1280 x 720 pixels.…”

Section: Computer-based Video Analysis Of General Movementsmentioning

confidence: 99%

“…Because of these limitations, several automated, computer-based methods for pattern recognition of infants' spontaneous movements are under development (18). We have previously published results from a feasibility study of a computer-based video analysis software for quantitative analysis of infants' general movements (19,20). In a convenience sample of high-risk infants, the software identified infants with FMs with a sensitivity and specificity of 81.5 and 85%, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer-based video analysis identifies infants with absence of fidgety movements

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

Computer Vision for Medical Infant Motion Analysis: State of the Art and RGB-D Data Set

Hesse

Bodensteiner

Arens

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Assessment of spontaneous movements of infants lets trained experts predict neurodevelopmental disorders like cerebral palsy at a very young age, allowing early intervention for affected infants. An automated motion analysis system requires to accurately capture body movements, ideally without markers or attached sensors to not affect the movements of infants. A vast majority of recent approaches for human pose estimation focuses on adults, leading to a degradation of accuracy if applied to infants. Hence, multiple systems for infant pose estimation have been developed. Due to the lack of publicly available benchmark data sets, a standardized evaluation, let alone a comparison of different approaches is impossible. We fill this gap by releasing the Moving INfants In RGB-D (MINI-RGBD) † data set, created using the recently introduced Skinned Multi-Infant Linear body model (SMIL). We map real infant movements to the SMIL model with realistic shapes and textures, and generate RGB and depth images with precise ground truth 2D and 3D joint positions. We evaluate our data set with state-of-the-art methods for 2D pose estimation in RGB images and for 3D pose estimation in depth images. Evaluation of 2D pose estimation results in a PCKh rate of 88.1% and 94.5% (depending on correctness threshold), and PCKh rates of 64.2%, respectively 90.4% for 3D pose estimation. We hope to foster research in medical infant motion analysis to get closer to an automated system for early detection of neurodevelopmental disorders.

show abstract

Using computer-based video analysis in the study of fidgety movements

Cited by 92 publications

References 19 publications

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

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

Computer-based video analysis identifies infants with absence of fidgety movements

Computer Vision for Medical Infant Motion Analysis: State of the Art and RGB-D Data Set

Contact Info

Product

Resources

About