Annotated dataset for deep-learning-based bacterial colony detection

Abstract

Quantifying bacteria per unit mass or volume is a common task in various fields of microbiology (e.g., infectiology and food hygiene). Most bacteria can be grown on culture media. The unicellular bacteria reproduce by dividing into two cells, which increases the number of bacteria in the population. Methodologically, this can be followed by culture procedures, which mostly involve determining the number of bacterial colonies on the solid culture media that are visible to the naked eye. However, it is a time-consuming and laborious professional activity. Addressing the automation of colony counting by convolutional neural networks in our work, we have cultured 24 bacteria species of veterinary importance with different concentrations on solid media. A total of 56,865 colonies were annotated manually by bounding boxes on the 369 digital images of bacterial cultures. The published dataset will help developments that use artificial intelligence to automate the counting of bacterial colonies.

Bacterial colony size growth estimation by deep learning

“…To detect bacterial colonies in the Detectron2 [ 16 ] environment, 10 pre-trained Faster R-CNN [ 17 ] models (R_50_C4_1x, R_50_C4_C4_3x, R_50_DC5_1x, R_50_DC5_3x, R_50_FPN_1x, R_50_FPN_3x, R_101_C4_C4_3x, R_101_DC5_3x, R_101_FPN_3x, X_101_32x8d_FPN_3x) were trained. For this purpose, our research group has previously created a manually annotated dataset (with bounding boxes enclosing the colonies) [ 12 ]. This dataset contains digital records of 24 bacterial species, 369 cultures with 56,865 annotated colonies.…”

“…The most common solutions [ 7 – 11 ] involve digital image analysis, used to detect colonies and then measure their size relying on a threshold-based approach. A limitation of these approaches is that objects in the image that are not colonies (e.g., pieces of the wall of a Petri dish, air bubbles) may also appear in the result as colonies [ 12 ]. More recently, the potential of laser speckle imaging (LSI) for the study of bacterial colony growth has been demonstrated by Balmages et al [ 13 ].…”

“…The data used in the study is freely available at https://doi.org/10.6084/m9.figshare.22022540.v3 [ 12 ] and https://doi.org/10.6084/m9.figshare.12951152.v1 [ 11 ]. The codes used during the current study are available from the corresponding author upon reasonable request.…”