Deep Learning to Detect Bacterial Colonies for the Production of\n Vaccines

2020/09/02 by Thomas Beznik, Paul Smyth, Beznik, Thomas +5 · 1 citation
Biochemistry, Genetics and Molecular Biology · Engineering · #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #Image Processing Techniques and Applications #Machine Learning (cs.LG) #Machine Learning in Bioinformatics #Quantitative Methods (q-bio.QM)

paper · pdf · doi:10.48550/arxiv.2009.00926

openalex publication_date 2020/09/02 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

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

Cited by

• A Comparison of Bacterial Colonies Count from Petri Dishes Utilizing Hough Transform and Traditional Manual Counting

Related

• A Mask R-CNN approach to counting bacterial colony forming units in pharmaceutical development
• Segmentation of dense and multi-species bacterial colonies using models trained on synthetic microscopy images
• AGAR a microbial colony dataset for deep learning detection
• A Comparison of Bacterial Colonies Count from Petri Dishes Utilizing Hough Transform and Traditional Manual Counting
• Efficient Deep Learning Architectures for Fast Identification of Bacterial Strains in Resource-Constrained Devices