Automatic Assessment of Infant Face and Upper-Body Symmetry as Early Signs of Torticollis

TL;DR

This paper develops a computer vision approach tailored for infants to automatically assess facial and upper-body symmetry, aiding early detection of torticollis with high accuracy.

Contribution

It introduces infant-specific pose estimation techniques that outperform adult-oriented models for assessing symmetry related to torticollis.

Findings

Strong correlation with ground truth measurements

Outperforms adult-oriented pose estimation networks

Effective in data-scarce infant domain

Abstract

We apply computer vision pose estimation techniques developed expressly for the data-scarce infant domain to the study of torticollis, a common condition in infants for which early identification and treatment is critical. Specifically, we use a combination of facial landmark and body joint estimation techniques designed for infants to estimate a range of geometric measures pertaining to face and upper body symmetry, drawn from an array of sources in the physical therapy and ophthalmology research literature in torticollis. We gauge performance with a range of metrics and show that the estimates of most these geometric measures are successful, yielding strong to very strong Spearman's $\rho$ correlation with ground truth values. Furthermore, we show that these estimates, derived from pose estimation neural networks designed for the infant domain, cleanly outperform estimates derived from more widely known networks designed for the adult domain