Computer vision to automatically assess infant neuromotor risk

Abstract

An infant's risk of developing neuromotor impairment is primarily assessed through visual examination by specialized clinicians. Therefore, many infants at risk for impairment go undetected, particularly in under-resourced environments. There is thus a need to develop automated, clinical assessments based on quantitative measures from widely-available sources, such as video cameras. Here, we automatically extract body poses and movement kinematics from the videos of at-risk infants (N=19). For each infant, we calculate how much they deviate from a group of healthy infants (N=85 online videos) using Naïve Gaussian Bayesian Surprise. After pre-registering our Bayesian Surprise calculations, we find that infants that are at higher risk for impairments deviate considerably from the healthy group. Our simple method, provided as an open source toolkit, thus shows promise as the basis for an automated and low-cost assessment of risk based on video recordings.

The future of General Movement Assessment: The role of computer vision and machine learning – A scoping review

“…Finally, the most popular algorithms for movement classification are currently SVMs, Random Forests and CNNs, due to their simplicity and straightforward application for a large variety of problems. Novel algorithms have been introduced to the field of automated GMA, such as the Naive Gaussian Bayesian Surprise (NGBS), applied to calculate how much each infant’s movements in a dataset deviate from a group of typically developing infants as the indicator of risk for atypical GMs ( Chambers et al, 2019 ). Similar as in choosing the suitable sensing setups, the selection of the most appropriate algorithm is also contingent on, among others, the data acquisition approaches, the dataset characteristics, and the goal of classification and detection.…”

AI Approaches towards Prechtl’s Assessment of General Movements: A Systematic Literature Review

“…In another paper, Olsen et al [ 19 ] presented a model-based approach for tracking infants in 3D. A Deep Learning-based approach [ 36 ] is also used on the dataset built upon YouTube videos. The hybrid approaches have also been experimented by incorporating the features extracted from motion and visual data [ 32 ] and implemented the motion segmentation methods.…”

“…Deep Learning for Pose Estimation: Chambers et al [ 36 ] built a Convolutional Neural Network to extract the pose of infants. They were the only ones to publish an unsupervised approach as preprint and showed that they can distinguish unhealthy movement from infants based on an NB classifier exclusively trained on healthy children.…”

“…Third, the movement features used in previous studies lack generality due to less number of subjects and examples. Lastly, all the reviews, except [ 17 , 20 , 23 , 24 , 35 , 36 ], are not using state-of-the-art Deep Learning (DL) algorithms to automate the GMA process. The DL algorithms are popular approaches of Artificial Intelligence (AI) which not only provide a generalized solution but also perform well for accurate detection of the classes in visual and time-series data.…”

Writhing Movement Detection in Newborns on the Second and Third Day of Life Using Pose-Based Feature Machine Learning Classification

“…The latest publications in the field of computer-aided diagnostics of infants indicate the direction of further development towards solutions based on human pose estimation algorithms [ 26 , 27 ]. The results of the research using this approach show the great potential of the OpenPose library for this type of application [ 28 , 30 , 36 ].…”