Automated counting of bacterial colonies on agar plates based on images captured at near-infrared light

Quantitative characterization and dynamics of bacterial communities in ready-to-eat chicken using high-throughput sequencing combined with internal standard-based absolute quantification

Ready-to-eat (RTE) chicken products are prone to bacterial contamination, posing foodborne illness risks. High-throughput sequencing (HTS) has been widely used to study the distribution of pathogenic and spoilage bacteria in RTE chicken products but lacks quantitative data on taxa abundances. In this study, we employed a method combining HTS with absolute quantification, using Edwardsiella tarda as an internal standard strain, to achieve the relative and absolute abundances of microbiota in RTE chicken products stored at 4 and 25 °C. The results showed that the addition of appropriate concentration of internal standard strains exhibited no significant impact on the structure composition, relative abundance, and absolute abundance of bacterial communities in chicken meat, achieving comprehensive absolute quantification in RTE chicken products. Furthermore, the absolute abundance of bacterial genera at the end of storage followed a log-normal distribution, with most genera having an absolute abundance between 103 and 105 CFU/g. This study provides insights into the quantification of bacterial communities in RTE chicken products, laying a foundation for the development of strategies to extend the shelf life of RTE products.

Increasing segmentation performance with synthetic agar plate images

Background

Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse datasets hinders the development and evaluation of robust automated systems.

Methods

In this paper, two new annotated datasets and a novel methodology for synthetic agar plate generation are presented. The datasets comprise 854 images of cultivated agar plates and 1,588 images of empty agar plates, encompassing various agar plate types and microorganisms. These datasets are an extension of the publicly available BRUKERCOLONY dataset, collectively forming one of the largest publicly available annotated datasets for research. The methodology is based on an efficient image generation pipeline that also simulates cultivation-related phenomena such as haemolysis or chromogenic reactions.

Results

The augmentations significantly improved the Dice coefficient of trained U-Net models, increasing it from 0.671 to 0.721. Furthermore, training the U-Net model with a combination of real and 150% synthetic data demonstrated its efficacy, yielding a remarkable Dice coefficient of 0.729, a substantial improvement from the baseline of 0.518. UNet3+ exhibited the highest performance among the U-Net and Attention U-Net architectures, achieving a Dice coefficient of 0.767.

Conclusions

Our experiments showed the methodology's applicability to real-world scenarios, even with highly variable agar plates. Our paper contributes to automating agar plate analysis by presenting a new dataset and effective methodology, potentially enhancing fully automated microbiological testing.

An experimental setup and segmentation method for CFU counting on agar plate for the assessment of drinking water

Quantification of bacterial colonies on an agar plate is a daily routine for a microbiologist to determine the number of viable microorganisms in the sample. In general, microbiologists perform a visual assessment of bacterial colonies which is time-consuming (takes 2 min per plate), tedious, and subjective. Some automatic counting algorithms are developed that save labour and time, but their results are affected by the non-illumination on an agar plate. To improve this, the present manuscript aims to develop an inexpensive and efficient device to acquire S.aureus images via an automatic counting method using image processing techniques under real laboratory conditions. The proposed method (P_ColonyCount) includes the region of interest extraction and color space transformation followed by filtering, thresholding, morphological operation, distance transform, and watershed technique for the quantification of isolated and overlapping colonies. The present work also shows a comparative study on grayscale, K, and green channels by applying different filter and thresholding techniques on 42 images. The results of all channels were compared with the score provided by the expert (manual count). Out of all the proposed method (P_ColonyCount), the K channel gives the best outcome in comparison with the other two channels (grayscale and green) in terms of precision, recall, and F-measure which are 0.99, 0.99, and 0.99 (2 h), 0.98, 0.99, and 0.98 (4 h), and 0.98, 0.98, 0.98 (6 h) respectively. The execution time of the manual and the proposed method (P_ColonyCount) for 42 images ranges from 19 to 113 s and 15 to 31 s respectively. Apart from this, a user-friendly graphical user interface is also developed for the convenient enumeration of colonies without any expert knowledge/training. The developed imaging device will be useful for researchers and teaching lab settings.

Distinction of Different Colony Types by a Smart-Data-Driven Tool

BACKGROUND

Colony morphology (size, color, edge, elevation, and texture), as observed on culture media, can be used to visually discriminate different microorganisms.

METHODS

This work introduces a hybrid method that combines standard pre-trained CNN keras models and classical machine-learning models for supporting colonies discrimination, developed in Petri-plates. In order to test and validate the system, images of three bacterial species (Escherichia coli, Pseudomonas aeruginosa, and Staphylococcus aureus) cultured in Petri plates were used.

RESULTS

The system demonstrated the following Accuracy discrimination rates between pairs of study groups: 92% for Pseudomonas aeruginosa vs. Staphylococcus aureus, 91% for Escherichia coli vs. Staphylococcus aureus and 84% Escherichia coli vs. Pseudomonas aeruginosa.

CONCLUSIONS

These results show that combining deep-learning models with classical machine-learning models can help to discriminate bacteria colonies with good accuracy ratios.

Recent Methods for the Viability Assessment of Bacterial Pathogens: Advances, Challenges, and Future Perspectives

Viability assessment is a critical step in evaluating bacterial pathogens to determine infectious risks to public health. Based on three accepted viable criteria (culturability, metabolic activity, and membrane integrity), current viability assessments are categorized into three main strategies. The first strategy relies on the culturability of bacteria. The major limitation of this strategy is that it cannot detect viable but nonculturable (VBNC) bacteria. As the second strategy, based on the metabolic activity of bacteria, VBNC bacteria can be detected. However, VBNC bacteria sometimes can enter a dormant state that allows them to silence reproduction and metabolism; therefore, they cannot be detected based on culturability and metabolic activity. In order to overcome this drawback, viability assessments based on membrane integrity (third strategy) have been developed. However, these techniques generally require multiple steps, bulky machines, and laboratory technicians to conduct the tests, making them less attractive and popular applications. With significant advances in microfluidic technology, these limitations of current technologies for viability assessment can be improved. This review summarized and discussed the advances, challenges, and future perspectives of current methods for the viability assessment of bacterial pathogens.

A comprehensive review of image analysis methods for microorganism counting: from classical image processing to deep learning approaches

Microorganisms such as bacteria and fungi play essential roles in many application fields, like biotechnique, medical technique and industrial domain. Microorganism counting techniques are crucial in microorganism analysis, helping biologists and related researchers quantitatively analyze the microorganisms and calculate their characteristics, such as biomass concentration and biological activity. However, traditional microorganism manual counting methods, such as plate counting method, hemocytometry and turbidimetry, are time-consuming, subjective and need complex operations, which are difficult to be applied in large-scale applications. In order to improve this situation, image analysis is applied for microorganism counting since the 1980s, which consists of digital image processing, image segmentation, image classification and suchlike. Image analysis-based microorganism counting methods are efficient comparing with traditional plate counting methods. In this article, we have studied the development of microorganism counting methods using digital image analysis. Firstly, the microorganisms are grouped as bacteria and other microorganisms. Then, the related articles are summarized based on image segmentation methods. Each part of the article is reviewed by methodologies. Moreover, commonly used image processing methods for microorganism counting are summarized and analyzed to find common technological points. More than 144 papers are outlined in this article. In conclusion, this paper provides new ideas for the future development trend of microorganism counting, and provides systematic suggestions for implementing integrated microorganism counting systems in the future. Researchers in other fields can refer to the techniques analyzed in this paper.

Use of digital images to count colonies of biodiesel deteriogenic microorganisms

This work presents a novel, robust procedure for the semi-automated counting of colony-forming units of Bacillus pumilus (a bacterium) and Meyerozyma guilliermondii (a yeast) both isolated from diesel oil. The counting is performed from digital images of Petri dishes containing the samples by a developed Python code, and the images are acquired from a low-cost scanning apparatus. The counting algorithm is based on the similar morphological characteristics of the bacterium and the yeast colonies. It was compared with classical counting methodology, and the results showed calibration and validation curves with a coefficient of determination (R2) of 0.99 and 0.98, respectively. The developed methodology is a valuable alternative to estimate the microbial contamination of biofuels.

Sandwich immunoassay based on antimicrobial peptide-mediated nanocomposite pair for determination of Escherichia coli O157:H7 using personal glucose meter as readout

A sandwich immunoassay was developed for determination of E. coli O157:H7. This is based on an antimicrobial peptide-mediated nanocomposite pair and uses a personal glucose meter as signal readout. The antimicrobial peptides, magainins I, and cecropin P1 were employed as recognition molecules for the nanocomposite pair, respectively. With a one-step process, copper phosphate nanocomposites embedded by magainins I and Fe₃O₄ were used as "capturing" probes for bacterial magnetic isolation, and calcium phosphate nanocomplexes composed of cecropin P1 and invertase were used as signal tags. After magnetic separation, the invertase of the signal tags hydrolyzed sucrose to glucose, thereby converting E. coli O157:H7 levels to glucose levels. This latter can be quantified by a personal glucose meter. Under optimal conditions, the concentration of E. coli O157:H7 can be determined in a linear range of 10 to 10⁷ CFU·mL^-1 with a detection limit of 10 CFU·mL^-1. The method was successfully applied to the determination of E. coli O157:H7 in milk samples. Graphical abstract Schematic representation of sandwich immunoassay for E. coli O157:H7. One-pot synthetic of Fe₃O₄-magainins I nanocomposites (MMP) were used for magnetic capture. Cecropin P1-invertase nanocomposites (PIP) were used as signal tags. A personal glucose meter was used as readout to determine the target.