Motion Estimation and Characterization in Premature Newborns Using Long Duration Video Recordings

Abstract Objectives In the context of neonatal non invasive monitoring, this paper proposes the estimation and characterization of the motion of premature newborns from long duration video recordings. Material and Methods A set of 13 videos from 9 different patients, corresponding to 190 hours of recordings, have been studied. An algorithm based on the analysis of changes in the image border has been used to remove intervals artifacted by adults' presence. Then, some features were computed to characterize the baby's motion. The approach was applied to compare two groups of premature newborns, with different severities of prematurity, recorded at the same postmenstrual age. Results Detection of adults' presence was achieved with 96.8% of sensitivity. All features were found statistically significant to differentiate the two groups. Conclusion This study shows that the automated video monitoring on long periods is achievable and provides relevant information about the premature newborns motion activity.

[1]  O. M. Aamo,et al.  An Optical Flow-Based Method to Predict Infantile Cerebral Palsy , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Guozhi Tao,et al.  Automated detection of videotaped neonatal seizures based on motion segmentation methods , 2006, Clinical Neurophysiology.

[3]  L. Curzi-Dascalova,et al.  Physiological correlates of sleep development in premature and full-term neonates , 1992, Neurophysiologie Clinique/Clinical Neurophysiology.

[4]  Øyvind Stavdahl,et al.  ENIGMA - Enhanced interactive general movement assessment , 2008, Expert Syst. Appl..

[5]  Hartmut Dickhaus,et al.  Quantification of the segmental kinematics of spontaneous infant movements. , 2008, Journal of biomechanics.

[6]  Sabine Van Huffel,et al.  Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy , 2010, Medical & Biological Engineering & Computing.

[7]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

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

[9]  Ann-Beth Moller,et al.  National, regional, and worldwide estimates of preterm birth rates in the year 2010 with time trends since 1990 for selected countries: a systematic analysis and implications , 2012, The Lancet.

[10]  Boualem Boashash,et al.  The bootstrap and its application in signal processing , 1998, IEEE Signal Process. Mag..

[11]  Nicola Vitiello,et al.  A Modular Sensorized Mat for Monitoring Infant Posture , 2013, Sensors.

[12]  G Cioni,et al.  The qualitative assessment of general movements in preterm, term and young infants--review of the methodology. , 1997, Early human development.

[13]  Roslyn N Boyd,et al.  Quality of General Movements Is Related to White Matter Pathology in Very Preterm Infants , 2008, Pediatrics.

[14]  Manolis Tsiknakis,et al.  Vision-based motion detection, analysis and recognition of epileptic seizures - A systematic review , 2012, Comput. Methods Programs Biomed..

[15]  Lars Adde,et al.  General movement assessment: predicting cerebral palsy in clinical practise. , 2007, Early human development.

[16]  Y. Ohno,et al.  Examination of non-restrictive and non-invasive sleep evaluation technique for children using difference images , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[17]  S. Blackburn,et al.  Comparison between time-lapse video recordings of behavior and polygraphic state determinations in premature infants. , 1978, Psychophysiology.

[18]  A. Murat Tekalp,et al.  Digital Video Processing , 1995 .

[19]  Yaohua Xiong,et al.  Quantifying motion in video recordings of neonatal seizures by robust motion trackers based on block motion models , 2005, IEEE Transactions on Biomedical Engineering.

[20]  William McGuire,et al.  Epidemiology of preterm birth , 2004, BMJ : British Medical Journal.