The potential of spectral and hyperspectral-imaging techniques for bacterial detection in food: A case study on lactic acid bacteria

Differentiation of Listeria monocytogenes serotypes using near infrared hyperspectral imaging

Among the severe foodborne illnesses, listeriosis resulting from the pathogen Listeria monocytogenes exhibits one of the highest fatality rates. This study investigated the application of near infrared hyperspectral imaging (NIR-HSI) for the classification of three L. monocytogenes serotypes namely serotype 4b, 1/2a and 1/2c. The bacteria were cultured on Brain Heart Infusion agar, and NIR hyperspectral images were captured in the spectral range 900-2500 nm. Different pre-processing methods were applied to the raw spectra and principal component analysis was used for data exploration. Classification was achieved with partial least squares discriminant analysis (PLS-DA). The PLS-DA results revealed classification accuracies exceeding 80 % for all the bacterial serotypes for both training and test set data. Based on validation data, sensitivity values for L. monocytogenes serotype 4b, 1/2a and 1/2c were 0.69, 0.80 and 0.98, respectively when using full wavelength data. The reduced wavelength model had sensitivity values of 0.65, 0.85 and 0.98 for serotype 4b, 1/2a and 1/2c, respectively. The most relevant bands for serotype discrimination were identified to be around 1490 nm and 1580-1690 nm based on both principal component loadings and variable importance in projection scores. The outcomes of this study demonstrate the feasibility of utilizing NIR-HSI for detecting and classifying L. monocytogenes serotypes on growth media.

Using staining as reference for spectral imaging: Its application for the development of an analytical method to predict the presence of bacterial biofilms

At present, although spectral imaging is known to have a great potential to provide a massive amount of valuable information, the lack of reference methods remains as one of the bottlenecks to access the full capacity of this technique. This work aims to present a staining-based reference method with digital image treatment for spectral imaging, in order to propose a fast, efficient, contactless and non-invasive analytical method to predict the presence of biofilms. Spectral images of Pseudomonasaeruginosa biofilms formed on high density polyethylene coupons were acquired in visible and near infrared (vis-NIR) range between 400 and 1000 nm. Crystal violet staining served as a biofilm indicator, allowing the bacterial cells and the extracellular matrix to be marked on the coupon. Treated digital images of the stained biofilms were used as a reference. The size and pixels of the hyperspectral and digital images were scaled and matched to each other. Intensity color thresholds were used to differentiate the pixels associate to areas containing biofilms from those ones placed in biofilm-free areas. The model facultative Gram-negative bacterium, P. aeruginosa, which can form highly irregularly shaped and heterogeneous biofilm structures, was used to enhance the strength of the method, due to its inherent difficulties. The results showed that the areas with high and low intensities were modeled with good performance, but the moderate intensity areas (with potentially weak or nascent biofilms) were quite challenging. Image processing and artificial neural networks (ANN) methods were performed to overcome the issues resulted from biofilm heterogeneity, as well as to train the spectral data for biofilm predictions.

Conventional and advanced detection techniques of foodborne pathogens: A comprehensive review

Foodborne pathogens are a major public health concern and have a significant economic impact globally. From harvesting to consumption stages, food is generally contaminated by viruses, parasites, and bacteria, which causes foodborne diseases such as hemorrhagic colitis, hemolytic uremic syndrome (HUS), typhoid, acute, gastroenteritis, diarrhea, and thrombotic thrombocytopenic purpura (TTP). Hence, early detection of foodborne pathogenic microbes is essential to ensure a safe food supply and to prevent foodborne diseases. The identification of foodborne pathogens is associated with conventional (e.g., culture-based, biochemical test-based, immunological-based, and nucleic acid-based methods) and advances (e.g., hybridization-based, array-based, spectroscopy-based, and biosensor-based process) techniques. For industrial food applications, detection methods could meet parameters such as accuracy level, efficiency, quickness, specificity, sensitivity, and non-labor intensive. This review provides an overview of conventional and advanced techniques used to detect foodborne pathogens over the years. Therefore, the scientific community, policymakers, and food and agriculture industries can choose an appropriate method for better results.

Efficient imaging based on P - and N-codoped carbon dots for tracking division and viability assessment of lactic acid bacteria

Assessment of lactic acid bacteria (LAB) activity plays a key role in the fermented food industry. Fluorescence imaging method based on dye is facile to detect LAB viability. However, it is difficult to obtain stable fluorescence, non-toxic and low-cost dyes. In this study, we prepare P- and N-doped carbon dots (PN-CDs) via microwave-assisted hydrothermal synthesis. The properties of high quantum yield (60.36%) and excitation dependence allowed for multicolor imaging of LAB (Lactobacillus plantarum [L.p] and Streptococcus thermophilus [S.t]). The abundant functional groups and positive charges (+2.34 mV) on the surface of PN-CDs facilitated their quickly integrated into cell wall of live LAB with obvious fluorescence or into dead cells. As a result, PN-CDs can not only be used to rapidly and efficiently monitor bacterial viability (one minute), but can also be used to visualize LAB division using fluorescence imaging. Importantly, the PN-CDs have potential to rapidly detect LAB activity in LAB-fermented juices.

Development and comparison of classification models on VIS-NIR hyperspectral imaging spectra for qualitative detection of the Staphylococcus aureus in fresh chicken breast

Chicken is at risk of contaminated foodborne pathogens in the production process. Timely and nondestructive detection of foodborne pathogens in chicken is essential for food security. The study aims to explore the feasibility of developing efficient classification models for qualitative detection of Staphylococcus aureus in chicken breast using the hyperspectral imaging technique. Principal component analysis was used to process the full spectral information and three wavelength selection methods (competitive adaptive reweighted sampling, genetic algorithm, and successive projections algorithm) were applied to extract effective wavelengths. These methods were combined with the support vector machine algorithm to develop conventional classification models, respectively. In addition, a convolutional neural network model based on deep learning was designed and trained for comparison. The performance of the convolutional neural network model was significantly better than that of conventional classification models. The overall accuracy for chicken sample classifications was improved from 83.88% to 91.38%. The results demonstrated that deep learning can effectively extract spectral features and promote the application of hyperspectral imaging in foodborne pathogens detection of chicken products.

Recent advances in muscle food safety evaluation: Hyperspectral imaging analyses and applications

As there is growing interest in process control for quality and safety in the meat industry, by integrating spectroscopy and imaging technologies into one system, hyperspectral imaging, or chemical or spectroscopic imaging has become an alternative analytical technique that can provide the spatial distribution of spectrum for fast and nondestructive detection of meat safety. This review addresses the configuration of the hyperspectral imaging system and safety indicators of muscle foods involving biological, chemical, and physical attributes and other associated hazards or poisons, which could cause safety problems. The emphasis focuses on applications of hyperspectral imaging techniques in the safety evaluation of muscle foods, including pork, beef, lamb, chicken, fish and other meat products. Although HSI can provide the spatial distribution of spectrum, characterized by overtones and combinations of the C-H, N-H, and O-H groups using different combinations of a light source, imaging spectrograph and camera, there still needs improvement to overcome the disadvantages of HSI technology for further applications at the industrial level.

Fast detection of bacterial contamination in fresh produce using FTIR and spectral classification

Screening for microbial contaminants in fresh produce is a lengthy process relative to their short shelf-life. The aim of this study is to develop a comprehensive assay which employs FTIR and spectral classification algorithm for detection of bacterial contamination of fresh produce. The procedure starts by soaking a sample of the fresh produce in broth for 5 h. Then, magnetic nanoparticles are added to capture bacteria which are then collected and prepared for FTIR scanning. The generated FTIR spectra are compared against an in-house database of different bacterial species (n = 6). The ability of the database to discriminate contaminated and uncontaminated samples and to identify the bacterial species was assessed. The compatibility of the FTIR procedures with subsequent DNA extraction and PCR was tested. The developed procedure was applied for assessment of bacterial contamination in fresh produce samples from the market (n = 78). Results were compared to the conventional culture methods. The generated FTIR database coupled to spectral classification was able to detect bacterial contamination with overall accuracy exceeding 90%. The sample processing did not alter the integrity of the bacterial DNA which was suitable for PCR. On application to fresh produce samples collected from the market, the developed method was able to detect bacterial contamination with 94% concordance with the culture method. In conclusion, the developed procedure can be applied for fast detection of microbial contamination in fresh produce with comparable accuracy to conventional microbiological assays and is compatible with subsequent molecular assays.

Hyperspectral imaging and machine learning in food microbiology: Developments and challenges in detection of bacterial, fungal, and viral contaminants

Hyperspectral imaging (HSI) is a robust and nondestructive method that can detect foreign particles such as microbial, chemical, and physical contamination in food. This review summarizes the work done in the last two decades in this field with a highlight on challenges, risks, and research gaps. Considering the challenges of using HSI on complex matrices like food (e.g., the confounding and masking effects of background signals), application of machine learning and modeling approaches that have been successful in achieving better accuracy as well as increasing the detection limit have also been discussed here. Foodborne microbial contaminants such as bacteria, fungi, viruses, yeast, and protozoa are of interest and concern to food manufacturers due to the potential risk of either food poisoning or food spoilage. Detection of these contaminants using fast and efficient methods would not only prevent outbreaks and recalls but will also increase consumer acceptance and demand for shelf-stable food products. The conventional culture-based methods for microbial detection are time and labor-intensive, whereas hyperspectral imaging (HSI) is robust, nondestructive with minimum sample preparation, and has gained significant attention due to its rapid approach to detection of microbial contaminants. This review is a comprehensive summary of the detection of bacterial, viral, and fungal contaminants in food with detailed emphasis on the specific modeling and datamining approaches used to overcome the specific challenges associated with background and data complexity.

Visual detection of microbial community during three bacteria mixed fermentation through hyperspectral imaging technology

Hyperspectral imaging technology with chemometrics was used for identifying and counting each species in microbial community during mixed fermentation. Hyperspectral images of microbial community of <i>Enterobacter</i> sp, <i>Acetobacter pasteurianus</i>, and <i>Lactobacillus paracasei</i> colonies were obtained and the spectra of strain colonies were extracted. Identification models were developed using linear discriminant analysis (LDA) and least-squares support vector machine (LS-SVM) by using 23 variables selected by genetic algorithm. The optimal LS-SVM model with identification rate of 96.67 % was used to identify colonies and prepare colony distribution maps in color for strains counting. The counting results by hyperspectral imaging technology agree with that of the manual counting method with average relative error of 3.70 %. The developed counting method has been successfully used to identify and count the specific strain from the mixed strains simultaneously. The hyperspectral imaging technology has a great potential to monitor changes in the microbial community structure.

Hyperspectral imaging and deep learning for quantification of Clostridium sporogenes spores in food products using 1D- convolutional neural networks and random forest model

Clostridium sporogenes spores are used as surrogates for Clostridium botulinum, to verify thermal exposure and lethality in sterilization regimes by food industries. Conventional methods to detect spores are time-consuming and labour intensive. The objectives of this study were to evaluate the feasibility of using hyperspectral imaging (HSI) and deep learning approaches, firstly to identify dead and live forms of C. sporogenes spores and secondly, to estimate the concentration of spores on culture media plates and ready-to-eat mashed potato (food matrix). C. sporogenes spores were inoculated by either spread plating or drop plating on sheep blood agar (SBA) and tryptic soy agar (TSA) plates and by spread plating on the surface of mashed potato. Reflectance in the spectral range of 547-1701 nm from the region of interest was used for principal component analysis (PCA). PCA was successful in distinguishing dead and live spores and different levels of inoculum (10² to 10⁶ CFU/ml) on both TSA and SBA plates, however, was not efficient on the mashed potato (food matrix). Hence, deep learning classification frameworks namely 1D- convolutional neural networks (CNN) and random forest (RF) model were used. CNN model outperformed the RF model and the accuracy for quantification of spores was improved by 4% and 8% in the presence and absence, respectively of dead spores. The screening system used in this study was a combination of HSI and deep learning modelling, which resulted in an overall accuracy of 90-94% when the dead/inactivated spores were present and absent, respectively. The only discrepancy detected was during the prediction of samples with low inoculum levels (<10² CFU/ml). In summary, it was evident that HSI in combination with a deep learning approach showed immense potential as a tool to detect and quantify spores on nutrient media as well as on specific food matrix (mashed potato). However, the presence of dead spores in any sample is postulated to affect the accuracy and would need replicates and confirmatory assays.

Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses

Biofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting Escherichia coli (E. coli) and Salmonella typhimurium (S. typhimurium) on the surface of food processing facilities by using fluorescence hyperspectral imaging. E. coli and S. typhimurium were cultured on high-density polyethylene and stainless steel coupons, which are the main materials used in food processing facilities. We obtained fluorescence hyperspectral images for the range of 420–730 nm by emitting UV light from a 365 nm UV light source. The images were used to perform discriminant analyses (linear discriminant analysis, k-nearest neighbor analysis, and partial-least squares discriminant analysis) to identify and classify coupons on which bacteria could be cultured. The discriminant performances of specificity and sensitivity for E. coli (1–4 log CFU·cm⁻²) and S. typhimurium (1–6 log CFU·cm⁻²) were over 90% for most machine learning models used, and the highest performances were generally obtained from the k-nearest neighbor (k-NN) model. The application of the learning model to the hyperspectral image confirmed that the biofilm detection was well performed. This result indicates the possibility of rapidly inspecting biofilms using fluorescence hyperspectral images.

Principal component analysis of hyperspectral data for early detection of mould in cheeselets

The application of non-destructive process analytical technologies in the area of food science got a lot of attention the past years. In this work we used hyperspectral imaging to detect mould on milk agar and cheese. Principal component analysis is applied to hyperspectral data to localise and visualise mycelia on the samples' surface. It is also shown that the PCA loadings obtained from a set of training samples can be applied to hyperspectral data from new test samples to detect the presence of mould on these. For both the agar and cheeselets, the first three principal components contained more than 99 % of the total variance. The spatial projection of the second principal component highlights the presence of mould on cheeselets. The proposed analysis methods can be adopted in industry to detect mould on cheeselets at an early stage and with further testing this application may also be extended to other food products.

Assessing the capability of Fourier transform infrared spectroscopy in tandem with chemometric analysis for predicting poultry meat spoilage

Background

Use of traditional methods for determining meat spoilage is quite laborious and time consuming. Therefore, alternative approaches are needed that can predict the spoilage of meat in a rapid, non-invasive and more elaborative way. In this regard, the spectroscopic techniques have shown their potential for predicting the microbial spoilage of meat-based products. Consequently, the present work was aimed to demonstrate the competence of Fourier transform infrared spectroscopy (FTIR) to detect spoilage in chicken fillets stored under aerobic refrigerated conditions.

Methods

This study was conducted under controlled randomized design (CRD). Chicken samples were stored for 8 days at 4 + 0.5 °C and FTIR spectra were collected at regular intervals (after every 2 days) directly from the sample surface using attenuated total reflectance during the study period. Additionally, total plate count (TPC), Entetobacteriaceae count, pH, CTn (Color transmittance number) color analysis, TVBN (total volatile basic nitrogen) contents, and shear force values were also measured through traditional approaches. FTIR spectral data were interpreted through principal component analysis (PCA) and partial least square (PLS) regression and compared with results of traditional methods for precise estimation of spoilage.

Results

Results of TPC (3.04–8.20 CFU/cm²), Entetobacteriaceae counts (2.39–6.33 CFU/cm²), pH (4.65–7.05), color (57.00–142.00 CTn), TVBN values (6.72–33.60 mg/100 g) and shear force values (8.99–39.23) were measured through traditional methods and compared with FTIR spectral data. Analysis of variance (ANOVA) was applied on data obtained through microbial and quality analyses and results revealed significant changes (P < 0.05) in the values of microbial load and quality parameters of chicken fillets during the storage. FTIR spectra were collected and PCA was applied to illuminate the wavenumbers potentially correlated to the spoilage of meat. PLS regression analysis permitted the estimates of microbial spoilage and quality parameters from the spectra with a fit of R² = 0.66 for TPC, R² = 0.52 for Entetobacteriaceae numbers and R² = 0.56 for TVBN analysis of stored broiler meat.

Discussion

PLS regression was applied for quantitative interpretation of spectra, which allowed estimates of microbial loads on chicken surfaces during the storage period. The results suggest that FTIR spectra retain information regarding the spoilage of poultry meat.

Conclusion

The present work concluded that FTIR spectroscopy coupled with multivariate analysis can be successfully used for quantitative determination of poultry meat spoilage.

Multifunctional bacterial imaging and therapy systems

Advanced antibacterial materials are classified and introduced, and their applications in multimodal imaging and therapy are reviewed.