A systematic review of the measurement of infant posture and movement using image or video data analysis
Article Sidebar
Main Article Content
Abstract
Gross motor skill development (spontaneous movement and posture) is the most basic assessment domain for infant body control and movement skills. Image or video analysis in early infancy is an alternative quantitative and qualitative method for assessing movement with the advantages of being cost-effective, requiring less set-up time without attaching markers, assessing natural movement, and availability in clinical settings. This study aimed to review novel methods for measuring posture and movement of infants using image or video analysis, focusing on studies that used the markerless technique. PubMed and EBSCO were searched using three main keywords (‘infants’, ‘posture and movement’, and ‘measurement’). Articles from other sources were screened and included, and a manual search was performed. Ultimately, 25 articles published since 2010 were selected. The outcomes of this review primarily focused on study purpose, subject information and position, recording tools, analysis techniques, and study features of interest. Image or video data analysis, primarily using two-dimensional and depth video cameras, was used for clinical investigation and technical evaluation, assuring assessment and treatment methods based on quantitative results. Infants aged 0–6 months were evaluated in the supine position in the studies in this review, with an analysis technique that was primarily computer-based. The parameters included variations regarding program or software; for example, the quantity of motion, the centroid of motion, area, velocity, acceleration, and coordinates. Regarding the advantages of using 2D video data analysis for natural movement assessment, further studies and novel technologies are required for clinical practice.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Hadders-Algra M. Early human motor development: From variation to the ability to vary and adapt. Neurosci Biobehav Rev 2018; 90: 411-27.
Dusing SC, Izzo TA, Thacker LR, Galloway JC. Postural complexity differs between infant born full term and preterm during the development of early behaviors. Early Hum Dev 2014; 90(3): 149-56.
Dusing SC, Thacker LR, Galloway JC. Infant born preterm have delayed development of adaptive postural control in the first 5 months of life. Infant Behav Dev 2016; 44: 49-58.
Einspieler C, Prechtl HFR. Prechtl’s assessment of general movements: a diagnostic tool for the functional assessment of the young nervous system. Ment Retard Dev Disabil Res Rev 2005; 11(1): 61-7.
Lucaccioni L, Bertoncelli N, Comini M, Martignoni L, Coscia A, Lugli L, et al. The ontogeny of limbs movements towards midline in healthy infants born at term. Early Hum Dev 2021; 155: 105324.
Dusing SC, Izzo T, Thacker LR, Galloway JC. Postural Complexity Influences Development in Infants Born Preterm With Brain Injury: Relating Perception-Action Theory to 3 Cases. Phys Ther 2014; 94(10): 1508-16.
Doroniewicz I, Ledwoń DJ, Affanasowicz A, Kieszczyńska K, Latos D, Matyja M, et al. Writhing movement detection in newborns on the second and third day of life using pose-based feature machine learning classification. Sensors (Basel) 2020; 20(21): 5986.
Silva N, Zhang D, Kulvicius T, Gail A, Barreiros C, Lindstaedt S, et al. The future of General Movement Assessment: The role of computer vision and machine learning – A scoping review. Res Dev Disabil 2021; 110: 103854.
Asan O, Montague E. Using video-based observation research methods in primary care health encounters to evaluate complex interactions. Inform Prim Care 2014; 21(4): 161-70.
Marcroft C, Khan A, Embleton ND, Trenell M, Plötz T. Movement recognition technology as a method of assessing spontaneous general movements in high risk infants. Front Neurol 2015; 5: 284.
National Center on Birth Defects and Developmental Disabilities, Centers for Disease Control and Prevention. Child development: Infants (0-1 year of age) [online] 2021 [cited 2022 Mar 21] Available from: https://www.cdc.gov/ncbddd/childdevelopment/positiveparenting/infants.html
Claudino L, Aloimonos Y. Studying human behavior from infancy: On the acquisition of infant postural data. Proceeding of the 4th International Conference on Development and Learning and on Epigenetic Robotics; 2014 Oct 13-16; Genoa, Italy. Joint IEEE International Conferences; 2014.
Nickel LR, Thatcher AR, Keller F, Wozniak RH, Iverson JM. Posture development in infants at heightened vs. low risk for autism spectrum disorders. Infancy 2013; 18(5): 639-61.
Adde L, Helbostad JL, Jensenius AR, Taraldsen G, Grunewaldt KH, Støen R. Early prediction of cerebral palsy by computer-based video analysis of general movements: a feasibility study. Dev Med Child Neurol 2010; 52(8): 773-8.
Adde L, Helbostad J, Jensenius AR, Langaas M, Støen R. Identification of fidgety movements and prediction of CP by the use of computerbased video analysis is more accurate when based on two video recordings. Physiother Theory Pract 2013; 29(6): 469-75.
Adde L, Thomas N, John HB, Oommen S, Vågen RT, Fjørtoft T, et al. Early motor repertoire in very low birth weight infants in India is associated with motor development at one year. Eur J Paediatr Neurol 2016; 20(6): 918-24.
Adde L, Yang H, Sæther R, Jensenius AR, Ihlen E, Cao J-Y, et al. Characteristics of general movements in preterm infants assessed by computer-based video analysis. Physiother Theory Pract 2018; 34(4): 286-92.
Baccinelli W, Bulgheroni M, Simonetti V, Fulceri F, Caruso A, Gila L, et al. Movidea: A software package for automatic video analysis of movements in infants at risk for neurodevelopmental disorders. Brain Sci 2020; 10(4): 203.
Caruso A, Gila L, Fulceri F, Salvitti T, Micai M, Baccinelli W, et al. Early motor development predicts clinical outcomes of siblings at high-risk for autism: Insight from an innovative motion-tracking technology. Brain Sci 2020; 10(6): E379.
Chambers C, Seethapathi N, Saluja R, Loeb H, Pierce SR, Bogen DK, et al. Computer vision to automatically assess infant neuromotor risk. IEEE Trans Neural Syst Rehabil Eng 2020; 28(11): 2431–42.
Dogra DP, Majumdar AK, Sural S, Mukherjee J, Mukherjee S, Singh A. Toward automating Hammersmith pulled-to-sit examination of infants using feature point based video object tracking. IEEE Trans Neural Syst Rehabil Eng 2012; 20(1): 38-47.
Ihlen EAF, Støen R, Boswell L, Regnier RA, Fjørtoft T, Gaebler-Spira D, et al. Machine learning of infant spontaneous movements for the early prediction of cerebral palsy: A multi-site cohort study. J Clin Med 2019; 9(1): E5.
Kawashima K, Funabiki Y, Ogawa S, Hayashi H, Soh Z, Furui A, et al. Video-based evaluation of infant crawling toward quantitative assessment of motor development. Sci Rep 2020; 10(1): 11266.
Khan MH, Helsper J, Farid MS, Grzegorzek M. A computer vision-based system for monitoring Vojta therapy. Int J Med Inform 2018; 113: 85-95.
Kinoshita N, Furui A, Soh Z, Hayashi H, Shibanoki T, Mori H, et al. Longitudinal assessment of U-shaped and inverted U-shaped developmental changes in the spontaneous movements of infants via markerless video analysis. Sci Rep 2020; 10(1): 16827.
Li M, Wei F, Li Y, Zhang S, Xu G. Three-dimensional pose estimation of infants lying supine using data from a Kinect sensor with low training cost. IEEE Sens J 2021; 21(5): 6904-13.
Marchi V, Hakala A, Knight A, D’Acunto F, Scattoni ML, Guzzetta A, et al. Automated pose estimation captures key aspects of General Movements at eight to 17 weeks from conventional videos. Acta Paediatr 2019; 108(10): 1817-24.
McCay KD, Ho ESL, Shum HPH, Fehringer G, Marcroft C, Embleton ND. Abnormal infant movements classification with deep learning on pose-based features. IEEE Access 2020; 8: 51582-92
Moccia S, Migliorelli L, Carnielli V, Frontoni E. Preterm infants’ pose estimation with spatio-temporal features. IEEE Trans Biomed Eng 2020; 67(8): 2370-80.
Raghuram K, Orlandi S, Shah V, Chau T, Luther M, Banihani R, et al. Automated movement analysis to predict motor impairment in preterm infants: a retrospective study. J Perinatol 2019; 39(10): 1362-9.
Schroeder AS, Hesse N, Weinberger R, Tacke U, Gerstl L, Hilgendorff A, et al. General Movement Assessment from videos of computed 3D infant body models is equally effective compared to conventional RGB video rating. Early Hum Dev 2020; 144: 104967.
Stahl A, Schellewald C, Stavdahl Ø, Aamo OM, Adde L, Kirkerod H. An optical flow-based method to predict infantile cerebral palsy. IEEE Trans Neural Syst Rehabil Eng 2012; 20(4) : 605-14.
Støen R, Songstad NT, Silberg IE, Fjørtoft T, Jensenius AR, Adde L. Computer-based video analysis identifies infants with absence of fidgety movements. Pediatr Res 2017; 82(4): 665-70.
Tacchino C, Impagliazzo M, Maggi E, Bertamino M, Blanchi I, Campone F, et al. Spontaneous movements in the newborns: a tool of quantitative video analysis of preterm babies. Comput Methods Programs Biomed 2021; 199: 105838.
Tsuji T, Nakashima S, Hayashi H, Soh Z, Furui A, Shibanoki T, et al. Markerless measurement and evaluation of general movements in infants. Sci Rep 2020; 10(1): 1422.
Valle SC, Støen R, Sæther R, Jensenius AR, Adde L. Test-retest reliability of computer based video analysis of general movements in healthy term-born infants. Early Hum Dev 2015; 91(10): 555-8.
Wu Q, Xu G, Wei F, Chen L, Zhang S. RGB-D videos-based early prediction of infant cerebral palsy via general movements complexity. IEEE Access 2021; 9: 42314-24.
Stenum J, Cherry-Allen KM, Pyles CO, Reetzke RD, Vignos MF, Roemmich RT. Applications of Pose Estimation in Human Health and Performance across the Lifespan. Sensors (Basel) 2021; 21(21): 7315.
Novak I, Morgan C, Adde L, Blackman J, Boyd RN, Brunstrom-Hernandez J, et al. Early, Accurate Diagnosis and Early Intervention in Cerebral Palsy: Advances in Diagnosis and Treatment. JAMA Pediatr 2017; 171(9): 897-907.
Regazzoni D, de Vecchi G, Rizzi C. RGB cams vs RGB-D sensors: Low cost motion capture technologies performances and limitations. J Manuf Syst 2014; 33(4): 897-907.