Automated Classification of Bacterial Cell Sub-Populations with Convolutional Neural Networks

Abstract

Quantification of phenotypic heterogeneity present amongst bacterial cells can be a challenging task. Conventionally, classification and counting of bacteria sub-populations is achieved with manual microscopy, due to the lack of alternative, high-throughput, autonomous approaches. In this work, we apply classification-type convolutional neural networks (cCNN) to classify and enumerate bacterial cell sub-populations (B. subtilis clusters). Here, we demonstrate that the accuracy of the cCNN developed in this study can be as high as 86% when trained on a relatively small dataset (81 images). We also developed a new image preprocessing algorithm, specific to fluorescent microscope images, which increases the amount of training data available for the neural network by 72 times. By summing the classified cells together, the algorithm provides a total cell count which is on parity with manual counting, but is 10.2 times more consistent and 3.8 times faster. Finally, this work presents a complete solution framework for those wishing to learn and implement cCNN in their synthetic biology work.

Applications of Artificial Neural Networks in Microorganism Image Analysis: A Comprehensive Review from Conventional Multilayer Perceptron to Popular Convolutional Neural Network and Potential Visual Transformer

“…Conventional bacteria sub-population classification and counting are achieved by manual microscopy. In [139], a method to classify and enumerate bacterial cell sub-populations based on CNN is proposed. Besides, a pre-processing algorithm for augmenting fluorescent microscope images is developed.…”