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

Iterative pseudo balancing for stem cell microscopy image classification

Many critical issues arise when training deep neural networks using limited biological datasets. These include overfitting, exploding/vanishing gradients and other inefficiencies which are exacerbated by class imbalances and can affect the overall accuracy of a model. There is a need to develop semi-supervised models that can reduce the need for large, balanced, manually annotated datasets so that researchers can easily employ neural networks for experimental analysis. In this work, Iterative Pseudo Balancing (IPB) is introduced to classify stem cell microscopy images while performing on the fly dataset balancing using a student-teacher meta-pseudo-label framework. In addition, multi-scale patches of multi-label images are incorporated into the network training to provide previously inaccessible image features with both local and global information for effective and efficient learning. The combination of these inputs is shown to increase the classification accuracy of the proposed deep neural network by 3[Formula: see text] over baseline, which is determined to be statistically significant. This work represents a novel use of pseudo-labeling for data limited settings, which are common in biological image datasets, and highlights the importance of the exhaustive use of available image features for improving performance of semi-supervised networks. The proposed methods can be used to reduce the need for expensive manual dataset annotation and in turn accelerate the pace of scientific research involving non-invasive cellular imaging.

Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods

Human pluripotent stem cells have the potential for unlimited proliferation and controlled differentiation into various somatic cells, making them a unique tool for regenerative and personalized medicine. Determining the best clone selection is a challenging problem in this field and requires new sensing instruments and methods able to automatically assess the state of a growing colony ('phenotype') and make decisions about its destiny. One possible solution for such label-free, non-invasive assessment is to make phase-contrast images and/or videos of growing stem cell colonies, process the morphological parameters ('morphological portrait', or signal), link this information to the colony phenotype, and initiate an automated protocol for the colony selection. As a step in implementing this strategy, we used machine learning methods to find an effective model for classifying the human pluripotent stem cell colonies of three lines according to their morphological phenotype ('good' or 'bad'), using morphological parameters from the previously published data as predictors. We found that the model using cellular morphological parameters as predictors and artificial neural networks as the classification method produced the best average accuracy of phenotype prediction (67%). When morphological parameters of colonies were used as predictors, logistic regression was the most effective classification method (75% average accuracy). Combining the morphological parameters of cells and colonies resulted in the most effective model, with a 99% average accuracy of phenotype prediction. Random forest was the most efficient classification method for the combined data. We applied feature selection methods and showed that different morphological parameters were important for phenotype recognition via either cellular or colonial parameters. Our results indicate a necessity for retaining both cellular and colonial morphological information for predicting the phenotype and provide an optimal choice for the machine learning method. The classification models reported in this study could be used as a basis for developing and/or improving automated solutions to control the quality of human pluripotent stem cells for medical purposes.

Pixel-level multimodal fusion deep networks for predicting subcellular organelle localization from label-free live-cell imaging

Complex intracellular organizations are commonly represented by dividing the metabolic process of cells into different organelles. Therefore, identifying sub-cellular organelle architecture is significant for understanding intracellular structural properties, specific functions, and biological processes in cells. However, the discrimination of these structures in the natural organizational environment and their functional consequences are not clear. In this article, we propose a new pixel-level multimodal fusion (PLMF) deep network which can be used to predict the location of cellular organelle using label-free cell optical microscopy images followed by deep-learning-based automated image denoising. It provides valuable insights that can be of tremendous help in improving the specificity of label-free cell optical microscopy by using the Transformer-Unet network to predict the ground truth imaging which corresponds to different sub-cellular organelle architectures. The new prediction method proposed in this article combines the advantages of a transformer's global prediction and CNN's local detail analytic ability of background features for label-free cell optical microscopy images, so as to improve the prediction accuracy. Our experimental results showed that the PLMF network can achieve over 0.91 Pearson's correlation coefficient (PCC) correlation between estimated and true fractions on lung cancer cell-imaging datasets. In addition, we applied the PLMF network method on the cell images for label-free prediction of several different subcellular components simultaneously, rather than using several fluorescent labels. These results open up a new way for the time-resolved study of subcellular components in different cells, especially for cancer cells.