Automatic Torso Detection in Images of Preterm Infants.

Imaging systems have applications in patient respiratory monitoring but with limited application in neonatal intensive care units (NICU). In this paper we propose an algorithm to automatically detect the torso in an image of a preterm infant during non-invasive respiratory monitoring. The algorithm uses normalised cut to segment each image into clusters, followed by two fuzzy inference systems to detect the nappy and torso.

Characterisation of the Oxygenation Response to Inspired Oxygen Adjustments in Preterm Infants.

Background: Oxygen saturation (SpO2) targeting in the preterm infant may be improved with a better understanding of the SpO2 responses to changes in inspired oxygen (FiO2).

Objective: We investigated the first-order FiO2-SpO2 relationship, aiming to quantify the parameters governing that relationship, the influences on these parameters and their variability.

Methods: In recordings of FiO2 and SpO2 from preterm infants on continuous positive airway pressure and supplemental oxygen, we identified unique FiO2 adjustments and mapped the subsequent SpO2 responses.