Classification of bacterial contamination using image processing and distributed computing

Embracing a Penta helix hub framework for co-creating sustaining and potentially disruptive sterilization innovation that enables artificial intelligence and sustainability: A scoping review

The supply of safe pipeline medical devices is of paramount importance. Opportunities exist to transform reusable medical devices for improved processing that meets diverse patient needs. There is increased interest in multi-actor hub frameworks to meet innovation challenges globally. The purpose of this scoping paper was to identify critical decontamination and sterilization needs for the medtech and pharmaceutical sectors with a focus on understanding how to effectively use the Penta helix hub framework that combines academia, industry, healthcare, policy-makers/regulators and patients/society. A PRISMA scoping review of PubMed publications was conducted over the period 2010 to January 2025. Thirty of the 124 'helix hub' papers addressed innovation where only 3 of 16 healthcare-focused helices used or mentioned the need for key performance indicators (KPIs). Early-phase helix innovation ecosystems are mainly supported by qualitative or non-empirical data. This review explores multi-actor needs along with describing quantifiable KPIs at micro (end-user), meso (innovation hub) and macro (regional, national and international) levels. This integrated Penta hub approach will help to effectively plan, co-create, manage, analyse and utilize voluminous data, for example there are ca. 60,000 and 56,000 publications per year on artificial intelligence (AI) and medical devices respectively along, with some 35,000 adverse reports on devices submitted to the US FDA. This review addresses sustaining and potentially disruptive opportunities for decontamination and sterilization that includes the use of AI-enabled devices, bespoke training and sustainability.

The synergistic antibacterial activity of ozone and surfactant mists

The microbiological safety of medical equipment and general surfaces is paramount to both the well-being of patients and the public. The application of ozone (a potent oxidant) has been recognised and implemented for this purpose, globally. However, it has primarily been utilised in the gaseous and aqueous forms. In this study, we investigate the potency of fine ozone mists and evaluate the synergistic effect when combined with cationic, anionic and non-ionic surfactants (dodecyl trimethyl ammonium bromide - DTAB, sodium dodecyl sulfate - SDS, alkyl polyglycoside - APG) as well as polyethylene glycol (PEG). Ozone mist is generated via a nebuliser (equipped with a compressed gas stream) and the piezoelectric method; whereas fabric substrates contaminated with Escherichia coli and Staphylococcus aureus are utilised in this study. Contamination levels on the fabric swatches are evaluated using agar dipslides. Compared to gaseous ozonation and aqueous ozonation (via nanobubble generation), the produced ozone mists showed significantly inferior antimicrobial properties for the tested conditions (6 ppm, 5-15 min). However, the hybrid mist-based application of 'ozone + surfactants' and 'ozone + PEG' showed considerable improvements compared to their independent applications (ozone mist only and surfactant mist only). The 'ozone + DTAB' mist had the highest activity, with better results observed with the micron-mist nebuliser than the piezoelectric transducer. We propose a likely mechanism for this synergistic performance (micellar encapsulation) and demonstrate the necessity for continued developments of novel decontamination technologies.

Machine Learning and Deep Learning Based Computational Approaches in Automatic Microorganisms Image Recognition: Methodologies, Challenges, and Developments

Microorganisms or microbes comprise majority of the diversity on earth and are extremely important to human life. They are also integral to processes in the ecosystem. The process of their recognition is highly tedious, but very much essential in microbiology to carry out different experimentation. To overcome certain challenges, machine learning techniques assist microbiologists in automating the entire process. This paper presents a systematic review of research done using machine learning (ML) and deep leaning techniques in image recognition of different microorganisms. This review investigates certain research questions to analyze the studies concerning image pre-processing, feature extraction, classification techniques, evaluation measures, methodological limitations and technical development over a period of time. In addition to this, this paper also addresses the certain challenges faced by researchers in this field. Total of 100 research publications in the chronological order of their appearance have been considered for the time period 1995-2021. This review will be extremely beneficial to the researchers due to the detailed analysis of different methodologies and comprehensive overview of effectiveness of different ML techniques being applied in microorganism image recognition field.

Automated Bacterial Classifications Using Machine Learning Based Computational Techniques: Architectures, Challenges and Open Research Issues

Bacteria are important in a variety of practical domains, including industry, agriculture, medicine etc. A very few species of bacteria are favourable to humans. Whereas, majority of them are extremely dangerous and causes variety of life threatening illness to different living organisms. Traditionally, this class of microbes is detected and classified using different approaches like gram staining, biochemical testing, motility testing etc. However with the availability of large amount of data and technical advances in the field of medical and computer science, the machine learning methods have been widely used and have shown tremendous performance in automatic detection of bacteria. The inclusion of latest technology employing different Artificial Intelligence techniques are greatly assisting microbiologist in solving extremely complex problems in this domain. This paper presents a review of the literature on various machine learning approaches that have been used to classify bacteria, for the period 1998-2020. The resources include research papers and book chapters from different publishers of national and international repute such as Elsevier, Springer, IEEE, PLOS, etc. The study carried out a detailed and critical analysis of penetrating different Machine learning methodologies in the field of bacterial classification along with their limitations and future scope. In addition, different opportunities and challenges in implementing these techniques in the concerned field are also presented to provide a deep insight to the researchers working in this field.

Deep Learning Model for Pathogen Classification Using Feature Fusion and Data Augmentation

Background:

Bacterial pathogens are deadly for animals and humans. The ease of their dissemination, coupled with their high capacity for ailment and death in infected individuals, makes them a threat to society.

Objective:

Due to high similarity among genera and species of pathogens, it is sometimes difficult for microbiologists to differentiate between them. Their automatic classification using deep-learning models can help in reliable, and accurate outcomes.

Method:

Deep-learning models, namely; AlexNet, GoogleNet, ResNet101, and InceptionV3 are used with numerous variations including training model from scratch, fine-tuning without pre-trained weights, fine-tuning along with freezing weights of initial layers, fine-tuning along with adjusting weights of all layers and augmenting the dataset by random translation and reflection. Moreover, as the dataset is small, fine-tuning and data augmentation strategies are applied to avoid overfitting and produce a generalized model. A merged feature vector is produced using two best-performing models and accuracy is calculated by xgboost algorithm on the feature vector by applying cross-validation.

Results:

Fine-tuned models where augmentation is applied produces the best results. Out of these, two-best-performing deep models i.e. (ResNet101, and InceptionV3) selected for feature fusion, produced a similar validation accuracy of 95.83 with a loss of 0.0213 and 0.1066, and a testing accuracy of 97.92 and 93.75, respectively. The proposed model used xgboost to attained a classification accuracy of 98.17% by using 35-folds cross-validation.

Conclusion:

The automatic classification using these models can help experts in the correct identification of pathogens. Consequently, they can help in controlling epidemics and thereby minimizing the socio-economic impact on the community.

Machine learning and applications in microbiology

To understand the intricacies of microorganisms at the molecular level requires making sense of copious volumes of data such that it may now be humanly impossible to detect insightful data patterns without an artificial intelligence application called machine learning. Applying machine learning to address biological problems is expected to grow at an unprecedented rate, yet it is perceived by the uninitiated as a mysterious and daunting entity entrusted to the domain of mathematicians and computer scientists. The aim of this review is to identify key points required to start the journey of becoming an effective machine learning practitioner. These key points are further reinforced with an evaluation of how machine learning has been applied so far in a broad scope of real-life microbiology examples. This includes predicting drug targets or vaccine candidates, diagnosing microorganisms causing infectious diseases, classifying drug resistance against antimicrobial medicines, predicting disease outbreaks and exploring microbial interactions. Our hope is to inspire microbiologists and other related researchers to join the emerging machine learning revolution.

Identification of Most Relevant Features for Classification of Francisella tularensis using Machine Learning

Background:

Francisella tularensis is a stealth pathogen fatal for animals and humans. Ease of its propagation, coupled with high capacity for ailment and death makes it a potential candidate for biological weapon.

Objective:

Work related to the pathogen’s classification and factors affecting its prolonged existence in soil is limited to statistical measures. Machine learning other than conventional analysis methods may be applied to better predict epidemiological modeling for this soil-borne pathogen.

Methods:

Feature-ranking algorithms namely; relief, correlation and oneR are used for soil attribute ranking. Moreover, classification algorithms; SVM, random forest, naive bayes, logistic regression and MLP are used for classification of the soil attribute dataset for Francisella tularensis positive and negative soils.

Results:

Feature-ranking methods concluded that clay, nitrogen, organic matter, soluble salts, zinc, silt and nickel are the most significant attributes while potassium, phosphorous, iron, calcium, copper, chromium and sand are the least contributing risk factors for the persistence of the pathogen. However, clay is the most significant and potassium is the least contributing attribute. Data analysis suggests that feature-ranking using relief produced classification accuracy of 84.35% for multilayer perceptron; 82.99% for linear regression; 80.27% for SVM and random forest; and 78.23% for naive bayes, which is better than other ranking methods. MLP outperforms other classifiers by generating an accuracy of 84.35%, 82.99% and 81.63% for feature-ranking using relief, correlation and oneR algorithms, respectively.

Conclusion:

These models can significantly improve accuracy and can minimize the risk of incorrect classification. They further help in controlling epidemics and thereby minimizing the socio-economic impact on the society.

Advances in Chemical and Biological Methods to Identify Microorganisms-From Past to Present

Fast detection and identification of microorganisms is a challenging and significant feature from industry to medicine. Standard approaches are known to be very time-consuming and labor-intensive (e.g., culture media and biochemical tests). Conversely, screening techniques demand a quick and low-cost grouping of bacterial/fungal isolates and current analysis call for broad reports of microorganisms, involving the application of molecular techniques (e.g., 16S ribosomal RNA gene sequencing based on polymerase chain reaction). The goal of this review is to present the past and the present methods of detection and identification of microorganisms, and to discuss their advantages and their limitations.

Simultaneous detection of Salmonella enterica, Escherichia coli and Listeria monocytogenes in food using a light scattering sensor

AIM

To investigate the use of a light scattering sensor, BActerial Rapid Detection using Optical scattering Technology (BARDOT) coupled with a multipathogen selective medium, Salmonella, Escherichia and Listeria (SEL), for concurrent detection of the three major foodborne pathogens in a single assay.

METHODS AND RESULTS

BARDOT was used to detect and distinguish the three major pathogens, Salmonella enterica, Shiga toxin-producing Escherichia coli (STEC) and Listeria monocytogenes from food based on colony scatter signature patterns on SEL agar (SELA). Multiple strains of three test pathogens were grown on SELA, and BARDOT was used to generate colony scatter image libraries for inclusive (SEL Library) and exclusive (non-SEL Library) bacterial group. These pathogens were further differentiated using the SEL scatter image library. Raw chicken and hotdog samples were artificially inoculated with pathogens (100 CFU per 25 g each), and enriched in SEL broth at 37°C for 18 h and colonies were grown on SELA for 11-22 h before screening with BARDOT. The BARDOT sensor successfully detected and differentiated Salmonella, STEC and Listeria on SELA with high classification accuracy 92-98%, 91-98% and 83-98% positive predictive values (PPV) respectively; whereas the nontarget strains showed only 0-13% PPV. BARDOT-identified colonies were further confirmed by multiplex PCR targeting inlB gene of L. monocytogenes, stx2 of STEC and sefA of S. enterica serovar Enteritidis.

CONCLUSIONS

The results show that BARDOT coupled with SELA can efficiently screen for the presence of three major pathogens simultaneously in a test sample within 29-40 h.

SIGNIFICANCE AND IMPACT OF THE STUDY

This innovative SELA-BARDOT detection platform can reduce turnaround time and economic burden on food industries by offering a label-free, noninvasive on-plate multipathogen screening technology for reducing microbial food safety and public health concerns.

Automatic hemolysis identification on aligned dual-lighting images of cultured blood agar plates

BACKGROUND AND OBJECTIVE

The recent introduction of Full Laboratory Automation systems in clinical microbiology opens to the availability of streams of high definition images representing bacteria culturing plates. This creates new opportunities to support diagnostic decisions through image analysis and interpretation solutions, with an expected high impact on the efficiency of the laboratory workflow and related quality implications. Starting from images acquired under different illumination settings (top-light and back-light), the objective of this work is to design and evaluate a method for the detection and classification of diagnostically relevant hemolysis effects associated with specific bacteria growing on blood agar plates. The presence of hemolysis is an important factor to assess the virulence of pathogens, and is a fundamental sign of the presence of certain types of bacteria.

METHODS

We introduce a two-stage approach. Firstly, the implementation of a highly accurate alignment of same-plate image scans, acquired using top-light and back-light illumination, enables the joint spatially coherent exploitation of the available data. Secondly, from each segmented portion of the image containing at least one bacterial colony, specifically designed image features are extracted to feed a SVM classification system, allowing detection and discrimination among different types of hemolysis.

RESULTS

The fine alignment solution aligns more than 98.1% images with a residual error of less than 0.13 mm. The hemolysis classification block achieves a 88.3% precision with a recall of 98.6%.

CONCLUSIONS

The results collected from different clinical scenarios (urinary infections and throat swab screening) together with accurate error analysis demonstrate the suitability of our system for robust hemolysis detection and classification, which remains feasible even in challenging conditions (low contrast or illumination changes).

Deep learning approach to bacterial colony classification

In microbiology it is diagnostically useful to recognize various genera and species of bacteria. It can be achieved using computer-aided methods, which make the recognition processes more automatic and thus significantly reduce the time necessary for the classification. Moreover, in case of diagnostic uncertainty (the misleading similarity in shape or structure of bacterial cells), such methods can minimize the risk of incorrect recognition. In this article, we apply the state of the art method for texture analysis to classify genera and species of bacteria. This method uses deep Convolutional Neural Networks to obtain image descriptors, which are then encoded and classified with Support Vector Machine or Random Forest. To evaluate this approach and to make it comparable with other approaches, we provide a new dataset of images. DIBaS dataset (Digital Image of Bacterial Species) contains 660 images with 33 different genera and species of bacteria.

Virulence Gene-Associated Mutant Bacterial Colonies Generate Differentiating Two-Dimensional Laser Scatter Fingerprints

In this study, we investigated whether a laser scatterometer designated BARDOT (bacterial rapid detection using optical scattering technology) could be used to directly screen colonies of Listeria monocytogenes, a model pathogen, with mutations in several known virulence genes, including the genes encoding Listeria adhesion protein (LAP; lap mutant), internalin A (ΔinlA strain), and an accessory secretory protein (ΔsecA2 strain). Here we show that the scatter patterns of lap mutant, ΔinlA, and ΔsecA2 colonies were markedly different from that of the wild type (WT), with >95% positive predictive values (PPVs), whereas for the complemented mutant strains, scatter patterns were restored to that of the WT. The scatter image library successfully distinguished the lap mutant and ΔinlA mutant strains from the WT in mixed-culture experiments, including a coinfection study using the Caco-2 cell line. Among the biophysical parameters examined, the colony height and optical density did not reveal any discernible differences between the mutant and WT strains. We also found that differential LAP expression in L. monocytogenes serotype 4b strains also affected the scatter patterns of the colonies. The results from this study suggest that BARDOT can be used to screen and enumerate mutant strains separately from the WT based on differential colony scatter patterns.

IMPORTANCE

In studies of microbial pathogenesis, virulence-encoding genes are routinely disrupted by deletion or insertion to create mutant strains. Screening of mutant strains is an arduous process involving plating on selective growth media, replica plating, colony hybridization, DNA isolation, and PCR or immunoassays. We applied a noninvasive laser scatterometer to differentiate mutant bacterial colonies from WT colonies based on forward optical scatter patterns. This study demonstrates that BARDOT can be used as a novel, label-free, real-time tool to aid researchers in screening virulence gene-associated mutant colonies during microbial pathogenesis, coinfection, and genetic manipulation studies.

Optical scatter patterns facilitate rapid differentiation of Enterobacteriaceae on CHROMagar™ Orientation medium

Enterobacteriaceae family comprised pathogens and commensals and has a significant impact on food safety and public health. Enterobacteriaceae is often enumerated and presumptively identified on chromogenic media, such as CHROMagar(TM) Orientation medium based on colony profile; however, classification is highly arbitrary, and some could not be differentiated due to similar chromogen production. Here, we investigated the ability of the laser optical sensor, BARDOT (bacterial rapid detection using optical scattering technology) for rapid screening and differentiation of colonies of the major bacterial genera from Enterobacteriaceae on CHROMagar(TM) Orientation. A total of 36 strains representing 12 genera and 15 species were used to generate colony scatter image library that comprised 1683 scatter images. This library was used to differentiate mixed cultures of Enterobacteriaceae family - Klebsiella pneumoniae, Enterobacter spp., Citrobacter freundii and Serratia marcescens (KECS group); Proteus mirabilis, Morganella morganii and Providencia rettgeri (PMP group); and non-Enterobacteriaceae family: Pseudomonas aeruginosa, Acinetobacter spp. and Staphylococcus aureus (PAS group) - and data show high accuracy (83-100%) for intra-group classification of colonies in 10-22 h or even before visible production of chromogens. BARDOT successfully differentiated the major genera, including the ones that do not produce visually distinguishable chromogens on CHROMagar(TM) Orientation, providing a label-free, real-time on-plate colony screening tool for Enterobacteriaceae.

Current status and future prospects of using advanced computer-based methods to study bacterial colonial morphology

Despite the advancement of recent molecular technologies, culturing is still considered the gold standard for microbial sample analysis. Here we review three different bacterial colony-based screening modalities that provide significant information beyond the simple shape and color of the colony. The plate imaging technique provides numeration and quantitative spectral reflectance information for each colony, while Raman spectroscopic analysis of bacteria colonies relates the Raman-shifted peaks to specific chemical bonding. Finally, the elastic-light-scatter technique provides a volumetric interaction of the whole colony through laser-bacteria interactions, instantly capturing the morphological traits of the colony and allowing quantitative classifications.

Novel PCR Assays Complement Laser Biosensor-Based Method and Facilitate Listeria Species Detection from Food

The goal of this study was to develop the Listeria species-specific PCR assays based on a house-keeping gene (lmo1634) encoding alcohol acetaldehyde dehydrogenase (Aad), previously designated as Listeria adhesion protein (LAP), and compare results with a label-free light scattering sensor, BARDOT (bacterial rapid detection using optical scattering technology). PCR primer sets targeting the lap genes from the species of Listeria sensu stricto were designed and tested with 47 Listeria and 8 non-Listeria strains. The resulting PCR primer sets detected either all species of Listeria sensu stricto or individual L. innocua, L. ivanovii and L. seeligeri, L. welshimeri, and L. marthii without producing any amplified products from other bacteria tested. The PCR assays with Listeria sensu stricto-specific primers also successfully detected all species of Listeria sensu stricto and/or Listeria innocua from mixed culture-inoculated food samples, and each bacterium in food was verified by using the light scattering sensor that generated unique scatter signature for each species of Listeria tested. The PCR assays based on the house-keeping gene aad (lap) can be used for detection of either all species of Listeria sensu stricto or certain individual Listeria species in a mixture from food with a detection limit of about 10⁴ CFU/mL.

Streptomycin Induced Stress Response in Salmonella enterica Serovar Typhimurium Shows Distinct Colony Scatter Signature

We investigated the streptomycin-induced stress response in Salmonella enterica serovars with a laser optical sensor, BARDOT (bacterial rapid detection using optical scattering technology). Initially, the top 20 S. enterica serovars were screened for their response to streptomycin at 100 μg/mL. All, but four S. enterica serovars were resistant to streptomycin. The MIC of streptomycin-sensitive serovars (Enteritidis, Muenchen, Mississippi, and Schwarzengrund) varied from 12.5 to 50 μg/mL, while streptomycin-resistant serovar (Typhimurium) from 125–250 μg/mL. Two streptomycin-sensitive serovars (Enteritidis and Mississippi) were grown on brain heart infusion (BHI) agar plates containing sub-inhibitory concentration of streptomycin (1.25–5 μg/mL) and a streptomycin-resistant serovar (Typhimurium) was grown on BHI containing 25–50 μg/mL of streptomycin and the colonies (1.2 ± 0.1 mm diameter) were scanned using BARDOT. Data show substantial qualitative and quantitative differences in the colony scatter patterns of Salmonella grown in the presence of streptomycin than the colonies grown in absence of antibiotic. Mass-spectrometry identified overexpression of chaperonin GroEL, which possibly contributed to the observed differences in the colony scatter patterns. Quantitative RT-PCR and immunoassay confirmed streptomycin-induced GroEL expression while, aminoglycoside adenylyltransferase (aadA), aminoglycoside efflux pump (aep), multidrug resistance subunit acrA, and ribosomal protein S12 (rpsL), involved in streptomycin resistance, were unaltered. The study highlights suitability of the BARDOT as a non-invasive, label-free tool for investigating stress response in Salmonella in conjunction with the molecular and immunoassay methods.

Hierarchical classification of large-scale patient records for automatic treatment stratification

In this paper, a hierarchical learning algorithm is developed for classifying large-scale patient records, e.g., categorizing large-scale patient records into large numbers of known patient categories (i.e., thousands of known patient categories) for automatic treatment stratification. Our hierarchical learning algorithm can leverage tree structure to train more discriminative max-margin classifiers for high-level nodes and control interlevel error propagation effectively. By ruling out unlikely groups of patient categories (i.e., irrelevant high-level nodes) at an early stage, our hierarchical approach can achieve log-linear computational complexity, which is very attractive for big data applications. Our experiments on one specific medical domain have demonstrated that our hierarchical approach can achieve very competitive results on both classification accuracy and computational efficiency as compared with other state-of-the-art techniques.