Deep Learning of Cell Classification using Microscope Images of Intracellular Microtubule Networks

TL;DR

This paper demonstrates that deep learning models can classify microtubule network images of cells with higher accuracy than human experts, aiding in cell diagnostics and treatment assessment.

Contribution

It introduces a deep learning approach for classifying microtubule images and shows superior performance over human experts in detecting chemical exposure levels.

Findings

Deep learning models outperform humans in classifying MT images.

The approach achieves high accuracy on a large dataset.

Automated classification can improve cell therapy diagnostics.

Abstract

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.