Pluri-IQ: Quantification of Embryonic Stem Cell Pluripotency through an Image-Based Analysis Software

Generative Adversarial Networks for Morphological-Temporal Classification of Stem Cell Images

Frequently, neural network training involving biological images suffers from a lack of data, resulting in inefficient network learning. This issue stems from limitations in terms of time, resources, and difficulty in cellular experimentation and data collection. For example, when performing experimental analysis, it may be necessary for the researcher to use most of their data for testing, as opposed to model training. Therefore, the goal of this paper is to perform dataset augmentation using generative adversarial networks (GAN) to increase the classification accuracy of deep convolutional neural networks (CNN) trained on induced pluripotent stem cell microscopy images. The main challenges are: 1. modeling complex data using GAN and 2. training neural networks on augmented datasets that contain generated data. To address these challenges, a temporally constrained, hierarchical classification scheme that exploits domain knowledge is employed for model learning. First, image patches of cell colonies from gray-scale microscopy images are generated using GAN, and then these images are added to the real dataset and used to address class imbalances at multiple stages of training. Overall, a 2% increase in both true positive rate and F1-score is observed using this method as compared to a straightforward, imbalanced classification network, with some greater improvements on a classwise basis. This work demonstrates that synergistic model design involving domain knowledge is key for biological image analysis and improves model learning in high-throughput scenarios.

Media composition modulates human embryonic stem cell morphology and may influence preferential lineage differentiation potential

Undifferentiated human embryonic stem cells have a distinct morphology (hESC). Changes in cell morphology during culture can be indicative of differentiation. hESC, maintained in diverse medias, demonstrated alterations in morphological parameters and subsequent alterations in underlying transcript expression and lineage differentiation. Analysis of morphological parameters showed distinct and significant differences between the undefined, less defined and Xeno-free medias while still maintaining pluripotency markers. This suggested that the less defined media may be creating dynamic instability in the cytoskeleton, with the cytoskeleton becoming more stabilised in the Xeno-free media as demonstrated by smaller and rounder cells. Examination of early lineage markers during undirected differentiation using d5 embryoid bodies demonstrated increased mesodermal lineage preference as compared to endodermal or ectoderm in cells originally cultured in Xeno-free media. Undefined media showed preference for mesoderm and ectoderm lineages, while less defined media (BSA present) demonstrated no preference. These data reveal that culture media may produce fundamental changes in cell morphology which are reflected in early lineage differentiation choice.