Infant Movement Detection via Eigenvalue-Entropy Based Subspace Method
Resumo
The early identification of anomalous movements in infants is crucial for intervening in potential neuromotor development disorders. The clinical method General Movement Assessment (GMA) is devoted to this identification task. However, since GMA is intensive and requires experts, new machine learning-based approaches and keypoints extracted from videos have emerged. However, challenges such as the underrepresentation of infants with writhing movements (WM)—general movements presented by infants in their first weeks of life; the scarcity of public datasets; and the fact that only video segments showing infants performing movements must be analyzed, are limitations to identify anomalous movements in infants automatically. This work introduces a method which uses spatial distance features extracted from skeletal data and employs subspace method based on the statistical analysis of the eigenvalue-entropy to enhance the detection of infants movements in video data, especially video from infants exhibiting WMs. The proposed method applies a subspace approach as an initial step to filter infant movements for further detection and subsequent classification, aiming to improve the detection and understanding of these critical early indicators. The results show that the proposed method is able to detect subtle nuances in infant movements more effectively than the baseline method, making it a promising tool for automatic developmental monitoring.
Referências
Einspieler, C., Prechtl, H. F., Ferrari, F., Cioni, G., and Bos, A. F. (1997). The qualitative assessment of general movements in preterm, term and young infants—review of the methodology. Early human development, 50(1):47–60.
Ferrari, F., Einspieler, C., Prechtl, H., Bos, A., Cioni, G., et al. (2004). Prechtl’s method on the qualitative assessment of general movements in preterm, term and young infants. Mac Keith Press.
Gao, Q., Yao, S., Tian, Y., Zhang, C., Zhao, T., Wu, D., Yu, G., and Lu, H. (2023). Automating general movements assessment with quantitative deep learning to facilitate early screening of cerebral palsy. Nature Communications, 14(1):8294.
Gatto, B. B., Fukui, K., Júnior, W. S., and dos Santos, E. M. (2021). Advances in subspace learning and its applications. In Anais Estendidos do XXXIV Conference on Graphics, Patterns and Images, pages 35–41. SBC.
Gong, X., Li, X., Ma, L., Tong, W., Shi, F., Hu, M., Zhang, X.-P., Yu, G., and Yang, C. (2022). Preterm infant general movements assessment via representation learning. Displays, 75:102308.
Groos, D., Adde, L., Aubert, S., Boswell, L., De Regnier, R.-A., Fjørtoft, T., Gaebler-Spira, D., Haukeland, A., Loennecken, M., Msall, M., et al. (2022). Development and validation of a deep learning method to predict cerebral palsy from spontaneous movements in infants at high risk. JAMA network open, 5(7):e2221325–e2221325.
Huang, J., Yoon, H., Wu, T., Candan, K. S., Pradhan, O., Wen, J., and O’Neill, Z. (2023). Eigen-entropy: A metric for multivariate sampling decisions. Information sciences, 619:84–97.
Irshad, M. T., Nisar, M. A., Gouverneur, P., Rapp, M., and Grzegorzek, M. (2020). Ai approaches towards prechtl’s assessment of general movements: A systematic literature review. Sensors, 20(18):5321.
Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics yolov8.
Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L., and Dollár, P. (2015). Microsoft coco: Common objects in context.
Maji, D., Nagori, S., Mathew, M., and Poddar, D. (2022). Yolo-pose: Enhancing yolo for multi person pose estimation using object keypoint similarity loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2637–2646.
Marschik, P. B., Kulvicius, T., Flügge, S., Widmann, C., Nielsen-Saines, K., Schulte-Rüther, M., Hüning, B., Bölte, S., Poustka, L., Sigafoos, J., et al. (2022). Open video data sharing in developmental and behavioural science. arXiv preprint arXiv:2207.11020.
Morais, R., Le, V., Morgan, C., Spittle, A., Badawi, N., Valentine, J., Hurrion, E. M., Dawson, P. A., Tran, T., and Venkatesh, S. (2023). Robust and interpretable general movement assessment using fidgety movement detection. IEEE Journal of Biomedical and Health Informatics.
Nguyen-Thai, B., Le, V., Morgan, C., Badawi, N., Tran, T., and Venkatesh, S. (2021). A spatio-temporal attention-based model for infant movement assessment from videos. IEEE journal of biomedical and health informatics, 25(10):3911–3920.
Palheta, M., Santos, G., Mendonça, A., Gonçalves, P., Albuquerque, R., Souto, E., and Santos, E. (2023). Fusão de dados de vídeos rgb e pontos-chaves para classificação de movimentos gerais de bebês. In Anais do XXIII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 384–394, Porto Alegre, RS, Brasil. SBC.
Shah, S. T. H. and Xuezhi, X. (2021). Traditional and modern strategies for optical flow: an investigation. SN Applied Sciences, 3(3):289.
Silva, N., Zhang, D., Kulvicius, T., Gail, A., Barreiros, C., Lindstaedt, S., Kraft, M., Bölte, S., Poustka, L., Nielsen-Saines, K., et al. (2021). The future of general movement assessment: The role of computer vision and machine learning–a scoping review. Research in developmental disabilities, 110:103854.
Sun, Y., Zhao, H., Liang, J., and Ma, X. (2021). Eigenvalue-based entropy in directed complex networks. Plos one, 16(6):e0251993.
