eCite Digital Repository

Automatic torso detection in images of preterm infants


Kaur, M and Marshall, AP and Eastwood-Sutherland, C and Salmon, BP and Dargaville, PA and Gale, TJ, Automatic torso detection in images of preterm infants, Journal of Medical Systems, 41, (9) Article 134. ISSN 0148-5598 (2017) [Refereed Article]

Copyright Statement

Copyright 2017 Springer Science+Business Media, LLC

DOI: doi:10.1007/s10916-017-0782-8


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. Our dataset comprised overhead images of 16 preterm infants in a NICU, with uncontrolled illumination, and encompassing variations in poses, presence of medical equipment and clutter in the background. The algorithm successfully identified the torso region for 15 of the 16 images, with a high agreement between the detected torso and the torso identified by clinical experts.

Item Details

Item Type:Refereed Article
Keywords:image processing, NICU, non-contact respiratory monitoring, paediatrics, respiratory rate, torso detection
Research Division:Information and Computing Sciences
Research Group:Computer vision and multimedia computation
Research Field:Image processing
Objective Division:Health
Objective Group:Specific population health (excl. Indigenous health)
Objective Field:Neonatal and child health
UTAS Author:Kaur, M (Miss Meharmeet Kaur)
UTAS Author:Marshall, AP (Mr Andrew Marshall)
UTAS Author:Eastwood-Sutherland, C (Mr Caillin Eastwood-Sutherland)
UTAS Author:Salmon, BP (Dr Brian Salmon)
UTAS Author:Dargaville, PA (Professor Peter Dargaville)
UTAS Author:Gale, TJ (Dr Timothy Gale)
ID Code:120151
Year Published:2017
Web of Science® Times Cited:1
Deposited By:Information and Communication Technology
Deposited On:2017-08-11
Last Modified:2018-06-14

Repository Staff Only: item control page