The role of artificial intelligence in the pose estimation method for early diagnosis of cerebral palsy: advances in diagnostic medical imaging
El rol de la inteligencia artificial en el método de estimación de pose para el diagnóstico temprano de la parálisis cerebral infantil: avances en la medicina de diagnóstico por imagen.
##plugins.themes.bootstrap3.article.sidebar##
PDF (Español (España))
FLIP
##plugins.themes.bootstrap3.article.main##
One of the traditional methods for diagnosing infantile cerebral palsy is general motor assessment, which analyzes the quality and complexity of the infant's movements by visual inspection of spontaneous movements. However, this assessment is subjective and requires highly trained clinicians, which can be
costly and time-consuming. To overcome this limitation, computer vision-based solutions are currently being developed to analyze infant movements. These analyses are based on pose estimation, obtained from artificial intelligence models, and then artificial intelligence-based classification algorithms are used to determine whether the movements are normal or abnormal. In this article, we present the use of pose estimation as a computer vision method to analyze fidgety movements in children with cerebral palsy and compare these estimated movements with how artificial intelligence algorithms classify them. Finally, some challenges and future perspectives on this technology are identified.
Downloads
##plugins.themes.bootstrap3.article.details##
Bax M, Goldstein M, Rosenbaum P, Leviton A, Paneth N, Dan B, et al. Proposed definition and classification of cerebral palsy, April 2005. Dev Med Child Neurol. 2005 Aug;47(8):571–6.
van Lieshout P, Candundo H, Martino R, Shin S, Barakat-Haddad C. Onset factors in cerebral palsy: A systematic review. Neurotoxicology [Internet]. 2017 Jul [cited 2023 Apr 21];61. Available from: https://pubmed.ncbi.nlm.nih.gov/27045882/
CDC. Data and Statistics for Cerebral Palsy [Internet]. Centers for Disease Control and Prevention. 2022 [cited 2023 Apr 21]. Available from: https://www.cdc.gov/ncbddd/cp/data.html
Marcroft C, Khan A, Embleton ND, Trenell M, Plotz T. Movement Recognition Technology as a Method of Assessing Spontaneous General Movements in High Risk Infants. Front Neurol [Internet]. 2015 Jan 9 [cited 2023 Apr 21];5. Available from: http://dx.doi.org/10.3389/fneur.2014.00284
Prechtl HF, Einspieler C, Cioni G, Bos AF, Ferrari F, Sontheimer D. An early marker for neurological deficits after perinatal brain lesions. Lancet. 1997 May 10;349(9062):1361–3.
Prechtl HF. Qualitative changes of spontaneous movements in fetus and preterm infant are a marker of neurological dysfunction. Early Human Development. 1990; 23(3):151–8.
Peyton C, Einspieler C. General Movements: A Behavioral Biomarker of Later Motor and Cognitive Dysfunction in NICU Graduates. Pediatr Ann. 2018 Apr 1;47(4):e159–64.
Ricci E, Einspieler C, Craig AK. Feasibility of Using the General Movements Assessment of Infants in the United States. Phys Occup Ther Pediatr. 2018 Aug;38(3):269–79.
Margot Bosanquet, Lisa Copeland, Robert Ware, Roslyn Boyd. A systematic review of tests to predict cerebral palsy in young children. Developmental Medicine & Child Neurology. 2013 Apr 11;55(5):418–26.
Einspieler C, Prechtl HF, Ferrari F, Cioni G, Bos AF. The qualitative assessment of general movements in preterm, term and young infants — review of the methodology. Early Hum Dev. 1997 Nov 24;50(1):47–60.
Fatima Yousif Ismail , Ali Fatemi, Michael V Johnston. Cerebral plasticity: Windows of opportunity in the developing brain. European journal of paediatric neurology : EJPN : official journal of the European Paediatric Neurology Society,. 2017;21(1):23–48.
Lars Adde, Jorunn L Helbostad, Alexander R Jensenius, Gunnar Taraldsen, Kristine H Grunewaldt, Ragnhild Stoen. Early prediction of cerebral palsy by computer-based video analysis of general movements: a feasibility study. Developmental medicine and child neurology. 2010;52(8):773–8.
Orlandi S, Raghuram K, Smith CR, Mansueto D, Church P, Shah V, et al. Detection of Atypical and Typical Infant Movements using Computer-based Video Analysis. Conf Proc IEEE Eng Med Biol Soc. 2018 Jul;2018:3598–601.
Stahl A, Schellewald C, Stavdahl O, Aamo OM, Adde L, Kirkerod H. An optical flow-based method to predict infantile cerebral palsy. IEEE Trans Neural Syst Rehabil Eng. 2012 Jul;20(4):605–14.
Stoen R, Songstad NT, Silberg IE, Fjortoft T, Jensenius AR, Adde L. Computer-based video analysis identifies infants with absence of fidgety movements. Pediatr Res. 2017 Oct;82(4):665–70.
McCay KD, Ho ESL, Marcroft C, Embleton ND. Establishing Pose Based Features Using Histograms for the Detection of Abnormal Infant Movements. Conf Proc IEEE Eng Med Biol Soc. 2019 Jul;2019:5469–72.
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 Nov;28(11):2431–42.
Chen Y, Tian Y, He M. Monocular human pose estimation: A survey of deep learning-based methods. Comput Vis Image Underst. 2020 Mar 1;192:102897.
Daniel Groos, Lars Adde, Ragnhild Stoen, Heri Ramampiaro, Espen A.F. Ihlen. Towards human-level performance on automatic pose estimation of infant spontaneous movements. Comput Med Imaging Graph. 2022 Jan 1;95:102012.
Wu Q, Xu G, Zhang S, Li Y, Wei F. Human 3D pose estimation in a lying position by RGB-D images for medical diagnosis and rehabilitation. Conf Proc IEEE Eng Med Biol Soc. 2020 Jul;2020:5802–5.
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.
Haomiao Ni, Yuan Xue, Liya Ma, Qian Zhang, Xiaoye Li, Sharon X. Huang. Semi-supervised body parsing and pose estimation for enhancing infant general movement assessment. Med Image Anal. 2023 Jan 1;83:102654.
Wu Q, Qin P, Kuang J, Wei F, Li Z, Bian R, et al. A Training-Free Infant Spontaneous Movement Assessment Method for Cerebral Palsy Prediction Based on Videos. IEEE Trans Neural Syst Rehabil Eng. 2023;31:1670–9.
Raghuram K, Orlandi S, Church P, Luther M, Kiss A, Shah V. Automated Movement Analysis to Predict Cerebral Palsy in Very Preterm Infants: An Ambispective Cohort Study. Children. 2022 Jun 7;9(6):843.
Zhang H, Shum HPH, Ho ESL. Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks. Conf Proc IEEE Eng Med Biol Soc. 2022 Jul;2022:1619–25.
Sakkos D, Mccay KD, Marcroft C, Embleton ND, Chattopadhyay S, Ho ESL. Identification of Abnormal Movements in Infants: A Deep Neural Network for Body Part-Based Prediction of Cerebral Palsy. IEEE Access. 2021;9:94281–92.
McCay KD, Hu P, Shum HPH, Woo WL, Marcroft C, Embleton ND, et al. A Pose-Based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants. IEEE Trans Neural Syst Rehabil Eng. 2022 Jan 28;30:8–19.
Medical Infant Motion Analysis [Internet]. Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB. 2021 [cited 2023 May 26]. Available from: https://www.iosb.fraunhofer.de/en/competences/image-exploitation/object-recognition/sensornetworks/motion-analysis.html
Nguyen-Thai B, Le V, Morgan C, Badawi N, Tran T, Venkatesh S. A Spatio-Temporal Attention-Based Model for Infant Movement Assessment From Videos. IEEE J Biomed Health Inform. 2021 Oct;25(10):3911–20.
Reich S, Zhang D, Kulvicius T, Bolte S, Nielsen-Saines K, Pokorny FB, et al. Novel AI driven approach to classify infant motor functions. Sci Rep. 2021 May 10;11(1):1–13.
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 . 2020 Oct 22;20(21):5986.
Rahmati H, Aamo OM, Stavdahl O, Dragon R, Adde L. Video-based early cerebral palsy prediction using motion segmentation. Conf Proc IEEE Eng Med Biol Soc. 2014;2014:3779–83.
Cao Z, Hidalgo G, Simon T, Wei SE, Sheikh Y. OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. IEEE Trans Pattern Anal Mach Intell. 2021 Jan;43(1):172–86.
Bukschat Y, Vetter M. EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach [Internet]. arXiv [cs.CV]. 2020. Available from: http://arxiv.org/abs/2011.04307
Dang Q, Yin J, Wang B, Zheng W. Deep learning based 2D human pose estimation: A survey. Tsinghua Sci Technol. 2019 Dec;24(6):663–76.
Huang X, Fu N, Liu S, Ostadabbas S. Invariant Representation Learning for Infant Pose Estimation with Small Data. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021). 2021. p. 1–8.
Janiesch C, Zschech P, Heinrich K. Machine learning and deep learning. Electronic Markets. 2021 Apr 8;31(3):685–95.
O’Mahony N, Campbell S, Carvalho A, Harapanahalli S, Hernandez GV, Krpalkova L, et al. Deep Learning vs. Traditional Computer Vision. Advances in Computer Vision. 2020;128–44.
Flores AR. Guia de practica clinica para la atencion de rehabilitación de paralisis cerebral infantil en el Instituto Nacional de Rehabilitación [Internet]. [cited 2023 May 24]. Available from: https://www.inr.gob.pe/transparencia/transparencia%20inr/resoluciones/2015/RD%20348-2015-SA-DG-INR.pdf
Nelson Silva, Dajie Zhang, Tomas Kulvicius, Alexander Gail, Carla Barreiros, Stefanie Lindstaedt, Marc Kraft, Sven Bolte, Luise Poustka, Karin Nielsen-Saines, Florentin Worgotter, Christa Einspieler, Peter B. Marschik. The future of General Movement Assessment: The role of computer vision and machine learning – A scoping review. Res Dev Disabil. 2021 Mar 1;110:103854.
