Mercedes Torres Torres is a Transitional Assistant Professor at the School of Computer Science at the University of Nottingham. She is a member of the Computer Vision Lab and the Horizon Institute. She holds a PhD in Image Processing and Machine Learning from the University of Nottingham and her background is computer science, with particular focus on machine learning, and image analysis and processing. Her research interests lie at the intersection of computer vision, machine learning, and healthcare. Her current work focuses on developing new methods to combine deep learning with small and skewed datasets. Particularly, she has been working on automatically calculating the gestation age of new-borns using small and skewed datasets of photographs from their faces, ears and feet.

Automatic Gestational Age Estimation with Small Sample Deep Learning:

A baby’s gestational age determines whether or not they are preterm, which helps clinicians decide on suitable post-natal treatment. The most accurate dating methods use Ultrasound Scan (USS) machines, but these machines are expensive, require trained personnel and cannot always be deployed to remote areas. In the absence of USS, the Ballard Score can be used, which is a manual postnatal dating method. However, this method is highly subjective and results can vary widely depending on the experience of the rater. In this presentation, we will introduce an automatic system for postnatal gestational age estimation aimed to be deployed on mobile phones, using small sets of images of a newborn’s face, foot and ear. We have created a novel two-stage approach that makes the most out of Convolutional Neural Networks trained on small sets of images to predict broad classes of gestational age, and then fuse the outputs of these discrete classes with a baby’s weight to make fine-grained predictions of gestational age in weeks. We have collected a dataset of 88 babies, and experiments show that our approach attains an expected error of 6 days and is three times more accurate than the manual postnatal method (Ballard). Furthermore, making use of images improves predictions by 30% compared to using weight only. This indicates that even with a very small set of data, our method is a viable candidate for postnatal gestational age estimation in areas were USS is not available.