Small sample deep learning for newborn gestational age estimation
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 remot...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2017
|
| Online Access: | https://eprints.nottingham.ac.uk/40828/ |
| _version_ | 1848796142359281664 |
|---|---|
| author | Torres Torres, Mercedes Valstar, Michel F. Henry, Caroline Ward, Carole Sharkey, Don |
| author_facet | Torres Torres, Mercedes Valstar, Michel F. Henry, Caroline Ward, Carole Sharkey, Don |
| author_sort | Torres Torres, Mercedes |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | 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 paper, we present 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 present 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. On a purpose- collected dataset of 88 babies, experiments show that our approach attains an expected error of 6 days and is three times more accurate than the manual postnatal method (Ballard). 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. |
| first_indexed | 2025-11-14T19:43:17Z |
| format | Conference or Workshop Item |
| id | nottingham-40828 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:43:17Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-408282020-05-04T18:47:29Z https://eprints.nottingham.ac.uk/40828/ Small sample deep learning for newborn gestational age estimation Torres Torres, Mercedes Valstar, Michel F. Henry, Caroline Ward, Carole Sharkey, Don 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 paper, we present 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 present 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. On a purpose- collected dataset of 88 babies, experiments show that our approach attains an expected error of 6 days and is three times more accurate than the manual postnatal method (Ballard). 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. 2017-05-30 Conference or Workshop Item PeerReviewed Torres Torres, Mercedes, Valstar, Michel F., Henry, Caroline, Ward, Carole and Sharkey, Don (2017) Small sample deep learning for newborn gestational age estimation. In: 12th IEEE International Conference on Face and Gesture Recognition (FG 2017), 30 May - 3 June 2017, Washington, DC, USA. (In Press) |
| spellingShingle | Torres Torres, Mercedes Valstar, Michel F. Henry, Caroline Ward, Carole Sharkey, Don Small sample deep learning for newborn gestational age estimation |
| title | Small sample deep learning for newborn gestational age estimation |
| title_full | Small sample deep learning for newborn gestational age estimation |
| title_fullStr | Small sample deep learning for newborn gestational age estimation |
| title_full_unstemmed | Small sample deep learning for newborn gestational age estimation |
| title_short | Small sample deep learning for newborn gestational age estimation |
| title_sort | small sample deep learning for newborn gestational age estimation |
| url | https://eprints.nottingham.ac.uk/40828/ |