AUTHOR=Nye Jessica , Zingaretti Laura M. , Pérez-Enciso Miguel 

TITLE=Estimating Conformational Traits in Dairy Cattle With DeepAPS: A Two-Step Deep Learning Automated Phenotyping and Segmentation Approach

JOURNAL=Frontiers in Genetics

VOLUME=11

YEAR=2020

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2020.00513

DOI=10.3389/fgene.2020.00513

ISSN=1664-8021

ABSTRACT=<p>Assessing conformation features in an accurate and rapid manner remains a challenge in the dairy industry. While recent developments in computer vision has greatly improved automated background removal, these methods have not been fully translated to biological studies. Here, we present a composite method (DeepAPS) that combines two readily available algorithms in order to create a precise mask for an animal image. This method performs accurately when compared with manual classification of proportion of coat color with an adjusted <italic>R</italic><sup>2</sup> = 0.926. Using the output mask, we are able to automatically extract useful phenotypic information for 14 additional morphological features. Using pedigree and image information from a web catalog (<ext-link ext-link-type="uri" xlink:href="http://www.semex.com" xmlns:xlink="http://www.w3.org/1999/xlink">www.semex.com</ext-link>), we estimated high heritabilities (ranging from <italic>h</italic><sup>2</sup> = 0.18–0.82), indicating that meaningful biological information has been extracted automatically from imaging data. This method can be applied to other datasets and requires only a minimal number of image annotations (∼50) to train this partially supervised machine-learning approach. DeepAPS allows for the rapid and accurate quantification of multiple phenotypic measurements while minimizing study cost. The pipeline is available at <ext-link ext-link-type="uri" xlink:href="https://github.com/lauzingaretti/deepaps" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/lauzingaretti/deepaps</ext-link>.</p>