Imaging software monitors tiny babies in ICU
Researchers at the University of South Australia (UniSA) have designed a computer vision system that can automatically detect a tiny baby’s face in a hospital bed and remotely monitor its vital signs from a digital camera — all with the same accuracy as an electrocardiogram (ECG) machine.
While the use of artificial intelligence-based software to detect human faces is common with adults, this is believed to be the first time that researchers have developed software to reliably detect a premature baby’s face and skin when covered in tubes and undergoing phototherapy. The team’s results have been published in the Journal of Imaging.
“Babies in neonatal intensive care can be extra difficult for computers to recognise because their faces and bodies are obscured by tubes and other medical equipment,” explained UniSA Professor Javaan Chahl, a lead researcher on the study.
“Many premature babies are being treated with phototherapy for jaundice, so they are under bright blue lights, which also makes it challenging for computer vision systems.”
The ‘baby detector’ was developed using a dataset of videos of babies in the neonatal intensive care unit (NICU) at Flinders Medical Centre to reliably detect their skin tone and faces. Infants were filmed with high-resolution cameras at close range and vital physiological data extracted using advanced signal processing techniques that can detect subtle colour changes from heartbeats and body movements not visible to the human eye.
Vital sign readings (including heart and respiratory rates) matched those of an ECG and in some cases appeared to outperform the conventional electrodes, endorsing the value of non-contact monitoring of pre-term babies in intensive care.
UniSA neonatal critical care specialist Kim Gibson said using neural networks to detect the faces of babies is a significant breakthrough for non-contact monitoring, with the study serving as just one part of an ongoing UniSA project to replace contact-based electrical sensors with non-contact video cameras — avoiding skin tearing and potential infections that adhesive pads can cause to babies’ fragile skin.
“Worldwide, more than 10% of babies are born prematurely and, due to their vulnerability, their vital signs need to be monitored continuously,” Gibson said. “Traditionally, this has been done with adhesive electrodes placed on the skin that can be problematic, and we believe non-contact monitoring is the way forward.”
Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletters and bimonthly magazine.
AI camera tech could help quickly identify serious infections
A combination of camera technology, software and AI has the potential to assess the severity of...
Machine learning identifies 800,000+ antimicrobial peptides
An international research team has used machine learning to search for antibiotics in a vast...
AI platform makes microscopy image analysis more accessible
DL4MicEverywhere makes artificial intelligence (AI) accessible for analysing microscopy images,...