Postnatal gestational age estimation of newborns using Small Sample Deep Learning

作者：

Highlights：

• New small sample learning method combines photos/quantitative data, CNN & regression.

• Its application to GA estimation using newborns' photos (face/ear/foot) and weight

• In-depth analysis of data collected (& its effects) and the system (& its elements)

• Results improve current automatic & manual postnatal methods.

• Even with small dataset, viable postnatal estimation candidate in areas without USS

摘要

•New small sample learning method combines photos/quantitative data, CNN & regression.•Its application to GA estimation using newborns' photos (face/ear/foot) and weight•In-depth analysis of data collected (& its effects) and the system (& its elements)•Results improve current automatic & manual postnatal methods.•Even with small dataset, viable postnatal estimation candidate in areas without USS

论文关键词：Computer vision,Deep learning,Small sample,Gestational age

论文评审过程：Received 13 October 2017, Revised 26 April 2018, Accepted 12 September 2018, Available online 1 December 2018, Version of Record 5 April 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.09.003