AuthorsS. Hicks, T. B. Haugen, P. Halvorsen and M. Riegler
TitleUsing Deep Learning to Predict Motility and Morphology of Human Sperm
AfilliationMachine Learning
Project(s)Department of Holistic Systems
StatusPublished
Publication TypeProceedings, refereed
Year of Publication2019
Conference NameMediaEval 2019
PublisherCEUR Workshop Proceedings
Abstract

In the Medico Task 2019, the main focus is to predict sperm quality based on videos and other related data. In this paper, we present the approach of team LesCats which is based on deep convolution neural networks, where we experiment with different data preprocessing methods to predict the morphology and motility of human sperm. The achieved results show that deep learning is a promising method for human sperm analysis. Out best method achieves a mean absolute error of 8.962 for the motility task and a mean absolute error of 5.303 for the morphology task.

Citation Key26930