Towards human-level performance on automatic pose estimation of infant spontaneous movements. (January 2022)

• Record Type: Journal Article
• Authors: Groos, Daniel; Adde, Lars; Støen, Ragnhild; Ramampiaro, Heri; Ihlen, Espen A.F.
• Is Part Of: Computerized medical imaging and graphics. Volume 95(2022)
• Publication Date: 2022-01
• Subjects: Computer-based risk assessment -- Convolutional neural networks -- Developmental disorders -- Infant pose estimation -- Markerless video-based analysis; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2021.102012
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Assessment of spontaneous movements can predict the long-term developmental disorders in high-risk infants. In order to develop algorithms for automated prediction of later disorders, highly precise localization of segments and joints by infant pose estimation is required. Four types of convolutional neural networks were trained and evaluated on a novel infant pose dataset, covering the large variation in 1424 videos from a clinical international community. The localization performance of the networks was evaluated as the deviation between the estimated keypoint positions and human expert annotations. The computational efficiency was also assessed to determine the feasibility of the neural networks in clinical practice. The best performing neural network had a similar localization error to the inter-rater spread of human expert annotations, while still operating efficiently. Overall, the results of our study show that pose estimation of infant spontaneous movements has a great potential to support research initiatives on early detection of developmental disorders in children with perinatal brain injuries by quantifying infant movements from video recordings with human-level performance. Graphical Abstract: ga1 Highlights: Infant pose estimation localizes body postures of infants accurately in video frames. A large-scale database of infant videos from international clinical networks. Hospital recordings and home-based smartphone videos across various infant groups. Performance of convolutional neural networks approaches human annotation spread. Automatic, markerless pose estimation with real-time inference on consumer GPU.