Correlation between pose estimation features regarding movements towards the midline in early infancy

Abstract

In infants, spontaneous movement towards the midline (MTM) indicates the initiation of anti-gravity ability development. Markerless 2D pose estimation is a cost-effective, time-efficient, and quantifiable alternative to movement assessment. We aimed to establish correlations between pose estimation features and MTM in early-age infants. Ninety-four infant videos were analysed to calculate the percentage and rate of MTM occurrence. 2D Pose estimation processed the videos and determined the distances and areas using wrist and ankle landmark coordinates. We collected data using video recordings from 20 infants aged 8-16 weeks post-term age. Correlations between MTM observations and distance values were evaluated. Differences in areas between groups of videos showing MTM and no MTM in the total, lower-limb, and upper-limb categories were examined. MTM observations revealed common occurrences of hand-to-trunk and foot-to-foot movements. Weak correlations were noted between limb distances to the midbody imaginary line and MTM occurrence values. Lower MTM showed significant differences in the lower part (p = 0.003) and whole area (p = 0.001). Video recording by parents or guardians could extract features using 2D pose estimation, assisting in the early identification of MTM in infants. Further research is required to assess a larger sample size with the diversity of MTM motor behaviour, and later developmental skills, and collect data from at-risk infants.

Fig 1. Pose landmark [31] and calculated distance.

This figure shows the limbs’ distance (dash line, —) from the landmarks 15, 16, 27, and 28 to the midbody imaginary line.

Fig 2. Pose landmark [31] and calculated area.

This figure shows the calculated area using the limbs pose landmarks (15, 16, 27, and 28) and the centre of the body coordinate which are listed as: (A) presenting the whole area; (B) presenting ❶ = the upper part area, and ❷ = the lower part area.

Fig 3. Flow chart of the study methodology.

MTM = movement toward midline.

Fig 4. The distribution of MTM frequency among infants who showed MTM on the recording day.

This figure shows the MTM occurrence data that was observed based on infant age in days post-term age (PTA). MTM = movement toward midline.

Fig 5. The difference between groups of videos that showed MTM and those that did not.

(A) The Lower MTM group represents infants showing foot-to-foot contact, foot-to-leg contact, and pedipulation. The comparison of whole area and upper- and lower-part areas between the groups of videos that showed MTM and those that did not are presented. (B) The Upper MTM group represents infants showing hand-to-hand, hand-to-face, hand-to-mouth, hand-to-trunk, hand-to-leg, manipulation, and fiddling. The comparison of whole area and upper- and lower-part areas between the groups of videos that showed MTM and those that did not are presented. (C) The Total MTM group represents infants showing all 10 items: foot-to-foot contact, foot-to-leg contact, hand-to-hand, hand-to-face, hand-to-mouth, hand-to-trunk, hand-to-leg, pedipulation, manipulation, and fiddling. The comparison of whole area and upper- and lower-part areas between groups of videos that showed MTM and those that did not are presented. MTM = movement toward midline, * p-value < 0.05. The sign of ′ represents the group of videos showing MTM and ≤ represents the group of videos not showing MTM.