Analyse der Spontanmotorik im 1. Lebensjahr: Markerlose 3-D-Bewegungserfassung zur Früherkennung von Entwicklungsstörungen

Kinder mit motorischer Entwicklungsstörung profitieren von einer frühen Entwicklungsförderung. Eine frühe Diagnosestellung in der kinderärztlichen Vorsorge (U2–U5) kann durch ein automatisiertes Screening verbessert werden. Bisherige Ansätze einer automatisierten Bewegungsanalyse sind jedoch teuer und aufwendig und nicht in der Breite anwendbar. In diesem Beitrag soll ein neues System zur Videoanalyse, das Kinematic Motion Analysis Tool (KineMAT) vorgestellt werden. Es kann bei Säuglingen angewendet werden und kommt ohne Körpermarker aus. Die Methode wird anhand von 7 Patienten mit unterschiedlichen Diagnosen demonstriert. Mit einer kommerziell erhältlichen Tiefenbildkamera (RGB-D[Red-Green-Blue-Depth]-Kamera) werden 3‑minütige Videosequenzen von sich spontan bewegenden Säuglingen aufgenommen und mit einem virtuellen Säuglingskörpermodell (SMIL[Skinned Multi-infant Linear]-Modell) in Übereinstimmung gebracht. Das so erzeugte virtuelle Abbild erlaubt es, beliebige Messungen in 3‑D mit hoher Präzision durchzuführen. Eine Auswahl möglicher Bewegungsparameter wird mit diagnosespezifischen Bewegungsauffälligkeiten zusammengeführt. Der KineMAT und das SMIL-Modell erlauben eine zuverlässige, dreidimensionale Messung der Spontanaktivität bei Säuglingen mit einer sehr niedrigen Fehlerrate. Basierend auf maschinellen Lernalgorithmen kann der KineMAT trainiert werden, pathologische Spontanmotorik automatisiert zu erkennen. Er ist kostengünstig und einfach anzuwenden und soll als Screeninginstrument für die kinderärztliche Vorsorge weiterentwickelt werden. Children with motor development disorders benefit greatly from early interventions. An early diagnosis in pediatric preventive care (U2–U5) can be improved by automated screening. Current approaches to automated motion analysis, however, are expensive, require lots of technical support, and cannot be used in broad clinical application. Here we present an inexpensive, marker-free video analysis tool (KineMAT) for infants, which digitizes 3‑D movements of the entire body over time allowing automated analysis in the future. Three-minute video sequences of spontaneously moving infants were recorded with a commercially available depth-imaging camera and aligned with a virtual infant body model (SMIL model). The virtual image generated allows any measurements to be carried out in 3‑D with high precision. We demonstrate seven infants with different diagnoses. A selection of possible movement parameters was quantified and aligned with diagnosis-specific movement characteristics. KineMAT and the SMIL model allow reliable, three-dimensional measurements of spontaneous activity in infants with a very low error rate. Based on machine-learning algorithms, KineMAT can be trained to automatically recognize pathological spontaneous motor skills. It is inexpensive and easy to use and can be developed into a screening tool for preventive care for children.

[1]  Giovanni Cioni,et al.  An early marker for neurological deficits after perinatal brain lesions , 1997, The Lancet.

[2]  R. Ware,et al.  A systematic review of tests to predict cerebral palsy in young children , 2013, Developmental medicine and child neurology.

[3]  M. Hadders‐Algra Neural substrate and clinical significance of general movements: an update , 2018, Developmental medicine and child neurology.

[4]  Mijna Hadders-Algra,et al.  Early Diagnosis and Early Intervention in Cerebral Palsy , 2014, Front. Neurol..

[5]  Thomas Plötz,et al.  Movement Recognition Technology as a Method of Assessing Spontaneous General Movements in High Risk Infants , 2015, Front. Neurol..

[6]  Michael Arens,et al.  Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Giovanni Cioni,et al.  Early markers for cerebral palsy: insights from the assessment of general movements , 2012 .

[8]  Hartmut Dickhaus,et al.  Kinematic assessment of stereotypy in spontaneous movements in infants. , 2012, Gait & posture.

[9]  A. Spittle Early intervention cognitive effects not sustained past preschool. , 2015, The Journal of pediatrics.

[10]  M. Bonfert,et al.  Motorische Entwicklung im Kindesalter , 2019, Monatsschrift Kinderheilkunde.

[11]  M. Hadders‐Algra,et al.  Quality of general movements in infancy is related to neurological dysfunction, ADHD, and aggressive behaviour , 1999, Developmental medicine and child neurology.

[12]  Daniel Cohen-Or,et al.  Self‐similarity Analysis for Motion Capture Cleaning , 2018, Comput. Graph. Forum.

[13]  Thomas Schmitz-Rode,et al.  Movement analysis by accelerometry of newborns and infants for the early detection of movement disorders due to infantile cerebral palsy , 2010, Medical & Biological Engineering & Computing.

[14]  M. Hadders‐Algra Early human motor development: From variation to the ability to vary and adapt , 2018, Neuroscience & Biobehavioral Reviews.

[15]  Sarah McIntyre,et al.  Early, Accurate Diagnosis and Early Intervention in Cerebral Palsy: Advances in Diagnosis and Treatment , 2017, JAMA pediatrics.

[16]  Michael Arens,et al.  Computer Vision for Medical Infant Motion Analysis: State of the Art and RGB-D Data Set , 2018, ECCV Workshops.

[17]  Michael J. Black,et al.  SMPL: A Skinned Multi-Person Linear Model , 2015, ACM Trans. Graph..

[18]  Sebastian Thrun,et al.  SCAPE: shape completion and animation of people , 2005, SIGGRAPH '05.

[19]  H. König,et al.  Entwicklungsneurologie – vernetzte Medizin und neue Perspektiven , 2017, Der Nervenarzt.

[20]  R. Blank,et al.  International clinical practice recommendations on the definition, diagnosis, assessment, intervention, and psychosocial aspects of developmental coordination disorder , 2019, Developmental medicine and child neurology.

[21]  Michael J. Black,et al.  General Movement Assessment from videos of computed 3D infant body models is equally effective compared to conventional RGB video rating. , 2020, Early human development.

[22]  Alexander Refsum Jensenius,et al.  Using computer-based video analysis in the study of fidgety movements. , 2009, Early human development.

[23]  Helena M. Mentis,et al.  Vision-based body tracking: turning Kinect into a clinical tool , 2014, Disability and rehabilitation. Assistive technology.

[24]  G Rau,et al.  Movement analysis in the early detection of newborns at risk for developing spasticity due to infantile cerebral palsy. , 2006, Human movement science.

[25]  Michael J. Black,et al.  Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  H. Prechtl Qualitative changes of spontaneous movements in fetus and preterm infant are a marker of neurological dysfunction. , 1990, Early human development.

[27]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[28]  A. Jensenius,et al.  Early prediction of cerebral palsy by computer‐based video analysis of general movements: a feasibility study , 2010, Developmental medicine and child neurology.

[29]  Leeanne M. Carey,et al.  Fish Oil Diet Associated with Acute Reperfusion Related Hemorrhage, and with Reduced Stroke-Related Sickness Behaviors and Motor Impairment , 2014, Front. Neurol..

[30]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Michael Arens,et al.  Body pose estimation in depth images for infant motion analysis , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[32]  K. Goldberg,et al.  Assessment of Infant Movement With a Compact Wireless Accelerometer System , 2012 .

[33]  Michael Arens,et al.  Learning an Infant Body Model from RGB-D Data for Accurate Full Body Motion Analysis , 2018, MICCAI.

[34]  Michael Arens,et al.  Markerless Motion Analysis for Early Detection of Infantile Movement Disorders , 2017 .

[35]  Mijna Hadders-Algra,et al.  General movements: A window for early identification of children at high risk for developmental disorders. , 2004, The Journal of pediatrics.