A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos

TL;DR

This paper introduces a spatio-temporal attention-based model that uses human pose estimation and graph convolutional networks to assess infant fidgety movements from videos, improving accuracy and interpretability for cerebral palsy screening.

Contribution

The study presents a novel approach combining pose-based features, graph neural networks, and attention mechanisms for infant movement assessment, addressing limitations of appearance-based methods.

Findings

Achieved ROC-AUC of 81.87% on real-life videos.

Outperformed existing methods in accuracy.

Enhanced interpretability of movement assessment.

Abstract

The absence or abnormality of fidgety movements of joints or limbs is strongly indicative of cerebral palsy in infants. Developing computer-based methods for assessing infant movements in videos is pivotal for improved cerebral palsy screening. Most existing methods use appearance-based features and are thus sensitive to strong but irrelevant signals caused by background clutter or a moving camera. Moreover, these features are computed over the whole frame, thus they measure gross whole body movements rather than specific joint/limb motion. Addressing these challenges, we develop and validate a new method for fidgety movement assessment from consumer-grade videos using human poses extracted from short clips. Human poses capture only relevant motion profiles of joints and limbs and are thus free from irrelevant appearance artifacts. The dynamics and coordination between joints are modeled using spatio-temporal graph convolutional networks. Frames and body parts that contain discriminative information about fidgety movements are selected through a spatio-temporal attention mechanism. We validate the proposed model on the cerebral palsy screening task using a real-life consumer-grade video dataset collected at an Australian hospital through the Cerebral Palsy Alliance, Australia. Our experiments show that the proposed method achieves the ROC-AUC score of 81.87%, significantly outperforming existing competing methods with better interpretability.