Deep Learning of Cell Classification using Microscope Images of Intracellular Microtubule Networks
This work is significant for cell diagnostics, as it provides an automated method to classify MT images, which is a difficult task for human experts.
This paper addresses the problem of classifying microtubule (MT) images to determine the level of chemical compound exposure in animal cells. The deep learning model achieved performance on par with or better than human experts, particularly excelling at recognizing different levels of chemical agent exposure.
Microtubule networks (MTs) are a component of a cell that may indicate the presence of various chemical compounds and can be used to recognize properties such as treatment resistance. Therefore, the classification of MT images is of great relevance for cell diagnostics. Human experts find it particularly difficult to recognize the levels of chemical compound exposure of a cell. Improving the accuracy with automated techniques would have a significant impact on cell therapy. In this paper we present the application of Deep Learning to MT image classification and evaluate it on a large MT image dataset of animal cells with three degrees of exposure to a chemical agent. The results demonstrate that the learned deep network performs on par or better at the corresponding cell classification task than human experts. Specifically, we show that the task of recognizing different levels of chemical agent exposure can be handled significantly better by the neural network than by human experts.