Deep Learning to Detect Bacterial Colonies for the Production of Vaccines

TL;DR

This paper explores the use of U-Net based deep learning algorithms to automate and improve the accuracy of bacterial colony counting and classification during vaccine development, reducing manual effort and errors.

Contribution

It introduces a multiclass U-Net segmentation approach with a custom loss function for distinguishing virulent from avirulent bacterial colonies.

Findings

U-Net algorithms provide robust automated CFU counting.

Multiclass segmentation achieves acceptable accuracy in colony classification.

Deep learning shows potential for improving vaccine production workflows.

Abstract

During the development of vaccines, bacterial colony forming units (CFUs) are counted in order to quantify the yield in the fermentation process. This manual task is time-consuming and error-prone. In this work we test multiple segmentation algorithms based on the U-Net CNN architecture and show that these offer robust, automated CFU counting. We show that the multiclass generalisation with a bespoke loss function allows distinguishing virulent and avirulent colonies with acceptable accuracy. While many possibilities are left to explore, our results show the potential of deep learning for separating and classifying bacterial colonies.