Comparative Analysis of Binary and Multiclass Activity Recognition in High-Quality Newborn Resuscitation Videos

Jorge García-Torres, Øyvind Meinich-Bache, Siren Irene Rettedal, Amalie Kibsgaard, Sara Brunner, Kjersti Engan

Keywords: Newborn Resuscitation, Activity Recognition, Deep Learning, Automated Video Analysis

TL;DR: Implementation of a Deep Learning pipeline for Activity Recognition on Newborn Resuscitation Videos.

Abstract: Globally, 3-10% of newborns do not breathe spontaneously at birth and need resuscitation. Prompt initiation of resuscitative interventions such as tactile stimulation and positive pressure ventilation can reduce neonatal mortality and morbidity associated with birth asphyxia. Automated video analysis of resuscitation episodes may be beneficial for evaluation and debriefing purposes. In this work, a dataset of 220 newborn resuscitation videos collected at the Stavanger University Hospital (Norway) is used to develop NBT-I3D, a deep neural network pipeline to automatically recognize resuscitation activities. To assess the task, both binary and multiclass networks have undergone training, allowing for a comparison of the two approaches. Results obtained for binary classification show a mean precision and recall of 84.76% and 80.92%, respectively. For multiclass, a mean precision and recall of 72.26% and 74.80% are reported.

Submission Number: 17