Deep Learning to Detect Bacterial Colonies for the Production of Vaccines
This work addresses a time-consuming and error-prone task in vaccine development, though it appears incremental as it applies existing deep learning methods to a specific domain.
The paper tackled the problem of manually counting bacterial colonies for vaccine production by testing U-Net-based segmentation algorithms, achieving robust automated counting and distinguishing virulent from avirulent colonies with acceptable accuracy.
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.