Automated Classification of General Movements in Infants Using a Two-stream Spatiotemporal Fusion Network
This work addresses the need for an automated, reliable tool to assist clinicians in early diagnosis of neurodevelopmental disorders in infants, representing an incremental improvement over existing video-based methods.
The authors tackled the problem of automating the classification of general movements (GMs) in infants for early diagnosis of neurodevelopmental disorders by proposing a two-stream spatiotemporal fusion network that removes background clutter and adjusts body position, achieving superior performance over baseline and existing methods in experiments with videos from 100 infants.
The assessment of general movements (GMs) in infants is a useful tool in the early diagnosis of neurodevelopmental disorders. However, its evaluation in clinical practice relies on visual inspection by experts, and an automated solution is eagerly awaited. Recently, video-based GMs classification has attracted attention, but this approach would be strongly affected by irrelevant information, such as background clutter in the video. Furthermore, for reliability, it is necessary to properly extract the spatiotemporal features of infants during GMs. In this study, we propose an automated GMs classification method, which consists of preprocessing networks that remove unnecessary background information from GMs videos and adjust the infant's body position, and a subsequent motion classification network based on a two-stream structure. The proposed method can efficiently extract the essential spatiotemporal features for GMs classification while preventing overfitting to irrelevant information for different recording environments. We validated the proposed method using videos obtained from 100 infants. The experimental results demonstrate that the proposed method outperforms several baseline models and the existing methods.