Towards human-level performance on automatic pose estimation of infant spontaneous movements

TL;DR

This study develops and evaluates neural networks for infant pose estimation, achieving human-level accuracy and efficiency, which could enhance early detection of developmental disorders from video analysis.

Contribution

Introduces a novel infant pose dataset and demonstrates neural networks capable of human-level localization accuracy in infant movement analysis.

Findings

Best neural network matched human inter-rater variability

Achieved efficient computation suitable for clinical use

Potential to support early developmental disorder detection

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 1 424 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.