TY - JOUR T1 - Cell type classification and unsupervised morphological phenotype identification from low-res images with deep learning JF - bioRxiv DO - 10.1101/533216 SP - 533216 AU - Kai Yao AU - Nash D. Rochman AU - Sean X. Sun Y1 - 2019/01/01 UR - http://biorxiv.org/content/early/2019/01/29/533216.abstract N2 - Convolutional neural networks (ConvNets) have been used for both classification and semantic segmentation of cellular images. Here we establish a method for cell type classification utilizing images taken on a benchtop microscope directly from cell culture flasks eliminating the need for a dedicated imaging platform. Significant flask-to-flask heterogeneity was discovered and overcome to support network generalization to novel data. Cell density was found to be a prominent source of heterogeneity even within the single-cell regime indicating the presence of morphological effects due to diffusion-mediated cell-cell interaction. Expert classification was poor for single-cell images and excellent for multi-cell images suggesting experts rely on the identification of characteristic phenotypes within subsets of each population and not ubiquitous identifiers. Finally we introduce Self-Label Clustering, an unsupervised clustering method relying on ConvNet feature extraction able to identify distinct morphological phenotypes within a cell type, some of which are observed to be cell density dependent.Author summary K.Y., N.D.R., and S.X.S. designed experiments and computational analysis. K.Y. performed experiments and ConvNets design/training, K.Y., N.D.R and S.X.S wrote the paper. ER -