Nondestructive multiplex detection of foodborne pathogens with background microflora and symbiosis using a paper chromogenic array and advanced neural network

Identifying freshness of various chilled pork cuts using rapid imaging analysis

BACKGROUND

Determining the freshness of chilled pork is of paramount importance to consumers worldwide. Established freshness indicators such as total viable count, total volatile basic nitrogen and pH are destructive and time-consuming. Color change in chilled pork is also associated with freshness. However, traditional detection methods using handheld colorimeters are expensive, inconvenient and prone to limitations in accuracy. Substantial progress has been made in methods for pork preservation and freshness evaluation. However, traditional methods often necessitate expensive equipment or specialized expertise, restricting their accessibility to general consumers and small-scale traders. Therefore, developing a user-friendly, rapid and economical method is of particular importance.

RESULTS

This study conducted image analysis of photographs captured by smartphone cameras of chilled pork stored at 4 °C for 7 days. The analysis tracked color changes, which were then used to develop predictive models for freshness indicators. Compared to handheld colorimeters, smartphone image analysis demonstrated superior stability and accuracy in color data acquisition. Machine learning regression models, particularly the random forest and decision tree models, achieved prediction accuracies of more than 80% and 90%, respectively.

CONCLUSION

Our study provides a feasible and practical non-destructive approach to determining the freshness of chilled pork. © 2024 Society of Chemical Industry.

Analysis of Outbreak Data Reveals Factors Contributing to Salmonellosis Outbreaks Linked to Cantaloupes

Over the last thirty years, the presence of Salmonella spp. on cantaloupes has been linked to multiple large and deadly foodborne outbreaks in multiple countries. To identify factors associated with the number of cases and risk of severe illness in these outbreaks, information from previous melon-associated salmonellosis outbreaks was analyzed. Data were collected from sixty outbreak investigations. Compared to other melon types, such as watermelon, honeydew, and Galia melon, cantaloupes had the highest public health burden. Cantaloupes were implicated in 43% of reported melon-related outbreaks, 51% of melon-related laboratory-confirmed cases, 54% of melon-related hospitalizations, and 76% of melon-related deaths. In the United States, imported cantaloupes were associated with higher rates of severe salmonellosis and a greater diversity of Salmonella spp. serovars compared to domestically grown cantaloupes. Cantaloupes implicated in outbreaks were equally likely to have been consumed in either private or public settings. Larger outbreaks were associated with the consumption of precut cantaloupe and/or the consumption of cantaloupes in public settings. With the identification of these contributing factors, a literature search was conducted to assess the state of knowledge concerning Salmonella and cantaloupes. Several gaps in the literature were noted and are discussed in the context of reducing the number of illnesses associated with the presence of Salmonella on cantaloupes.

LoMAE: Simple Streamlined Low-Level Masked Autoencoders for Robust, Generalized, and Interpretable Low-Dose CT Denoising

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In computer vision and natural language processing, masked autoencoders (MAE) have been recognized as a powerful self-pretraining method for transformers, due to their exceptional capability to extract representative features. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective streamlined low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE's robustness and generability across a variety of noise levels. Experimental findings show that the proposed LoMAE enhances the denoising capabilities of the transformer and substantially reduce their dependency on high-quality, ground-truth data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels. In summary, the proposed LoMAE provides promising solutions to the major issues in LDCT including interpretability, ground truth data dependency, and model robustness/generalizability.

Machine learning-enabled colorimetric sensors for foodborne pathogen detection

In the past decade, there have been various advancements to colorimetric sensors to improve their potential applications in food and agriculture. One application of growing interest is sensing foodborne pathogens. There are unique considerations for sensing in the food industry, including food sample destruction, specificity amidst a complex food matrix, and high sensitivity requirements. Incorporating novel technology, such as nanotechnology, microfluidics, and smartphone app development, into colorimetric sensing methodology can enhance sensor performance. Nonetheless, there remain challenges to integrating sensors with existing food safety infrastructure. Recently, increasingly advanced machine learning techniques have been employed to facilitate nondestructive, multiplex detection for feasible assimilation of sensors into the food industry. With its ability to analyze and make predictions from highly complex data, machine learning holds potential for advanced yet practical colorimetric sensing of foodborne pathogens. This article summarizes recent developments and hurdles of machine learning-enabled colorimetric foodborne pathogen sensing. These advancements underscore the potential of interdisciplinary, cutting-edge technology in providing safer and more efficient food systems.

Microfluidic paper analytic device (μPAD) technology for food safety applications

Foodborne pathogens, food adulterants, allergens, and toxic chemicals in food can cause major health hazards to humans and animals. Stringent quality control measures at all stages of food processing are required to ensure food safety. There is, therefore, a global need for affordable, reliable, and rapid tests that can be conducted at different process steps and processing sites, spanning the range from the sourcing of food to the end-product acquired by the consumer. Current laboratory-based food quality control tests are well established, but many are not suitable for rapid on-site investigations and are costly. Microfluidic paper analytical devices (μPADs) are a fast-growing field in medical diagnostics that can fill these gaps. In this review, we describe the latest developments in the applications of microfluidic paper analytic device (μPAD) technology in the food safety sector. State-of-the-art μPAD designs and fabrication methods, microfluidic assay principles, and various types of μPAD devices with food-specific applications are discussed. We have identified the prominent research and development trends and future directions for maximizing the value of microfluidic technology in the food sector and have highlighted key areas for improvement. We conclude that the μPAD technology is promising in food safety applications by using novel materials and improved methods to enhance the sensitivity and specificity of the assays, with low cost.

Machine-Learning-Assisted Aggregation-Induced Emissive Nanosilicon-Based Sensor Array for Point-of-Care Identification of Multiple Foodborne Pathogens

How timely identification and determination of pathogen species in pathogen-contaminated foods are responsible for rapid and accurate treatments for food safety accidents. Herein, we synthesize four aggregation-induced emissive nanosilicons with different surface potentials and hydrophobicities by encapsulating four tetraphenylethylene derivatives differing in functional groups. The prepared nanosilicons are utilized as receptors to develop a nanosensor array according to their distinctive interactions with pathogens for the rapid and simultaneous discrimination of pathogens. By coupling with machine-learning algorithms, the proposed nanosensor array achieves high performance in identifying eight pathogens within 1 h with high overall accuracy (93.75-100%). Meanwhile, Cronobacter sakazakii and Listeria monocytogenes are taken as model bacteria for the quantitative evaluation of the developed nanosensor array, which can successfully distinguish the concentration of C. sakazakii and L. monocytogenes at more than 103 and 102 CFU mL-1, respectively, and their mixed samples at 105 CFU mL-1 through the artificial neural network. Moreover, eight pathogens at 1 × 104 CFU mL-1 in milk can be successfully identified by the developed nanosensor array, indicating its feasibility in monitoring food hazards.

A paper-based ratiometric fluorescent sensor for NH3 detection in gaseous phase: Real-time monitoring of chilled chicken freshness

A ratiometric fluorescence sensor platform with easy-to-use and accurate is nanoengineered for NH3 quantitative detection and visual real-time monitoring of chicken freshness using smartphones. The ratiometric fluorescent probe formed by combining the zinc ion complex and carbon dots has a double-emitted fluorescence peak. The fluorescence intensity of the complex changed can be clearly observed with the increase of the concentration of ammonia solution under 365 nm wavelength excitation. In order to detect NH3 concentration in gaseous phase, a portable paper-based sensor was designed. The sensor had a good linear relationship with NH3 concentration ranging from 10.0 to 90.0 μmol/L and the LOD value was 288 nM. This fluorescent paper-based sensor was used to check the freshness of chicken breast refrigerated at 4 °C, revealed observable shifts from blue to green. The fluorescent paper-based sensor can detect NH3 concentration in real time and simplify the monitoring process of meat freshness while ensuring accuracy and stability.

Surveillance of pathogenic bacteria on a food matrix using machine-learning-enabled paper chromogenic arrays

Global food systems can benefit significantly from continuous monitoring of microbial food safety, a task for which tedious operations, destructive sampling, and the inability to monitor multiple pathogens remain challenging. This study reports significant improvements to a paper chromogenic array sensor - machine learning (PCA-ML) methodology sensing concentrations of volatile organic compounds (VOCs) emitted on a species-specific basis by pathogens by streamlining dye selection, sensor fabrication, database construction, and machine learning and validation. This approach enables noncontact, time-dependent, simultaneous monitoring of multiple pathogens (Listeria monocytogenes, Salmonella, and E. coli O157:H7) at levels as low as 1 log CFU/g with over 90% accuracy. The report provides theoretical and practical frameworks demonstrating that chromogenic response, including limits of detection, depends on time integrals of VOC concentrations. The paper also discusses the potential for implementing PCA-ML in the food supply chain for different food matrices and pathogens, with species- and strain-specific identification.

Progress and Challenge of Sensors for Dairy Food Safety Monitoring

One of the most consumed foods is milk and milk products, and guaranteeing the suitability of these products is one of the major concerns in our society. This has led to the development of numerous sensors to enhance quality controls in the food chain. However, this is not a simple task, because it is necessary to establish the parameters to be analyzed and often, not only one compound is responsible for food contamination or degradation. To attempt to address this problem, a multiplex analysis together with a non-directed (e.g., general parameters such as pH) analysis are the most relevant alternatives to identifying the safety of dairy food. In recent years, the use of new technologies in the development of devices/platforms with optical or electrochemical signals has accelerated and intensified the pursuit of systems that provide a simple, rapid, cost-effective, and/or multiparametric response to the presence of contaminants, markers of various diseases, and/or indicators of safety levels. However, achieving the simultaneous determination of two or more analytes in situ, in a single measurement, and in real time, using only one working 'real sensor', remains one of the most daunting challenges, primarily due to the complexity of the sample matrix. To address these requirements, different approaches have been explored. The state of the art on food safety sensors will be summarized in this review including optical, electrochemical, and other sensor-based detection methods such as magnetoelastic or mass-based sensors.

Progress in methods for the detection of viable Escherichia coli

Escherichia coli (E. coli) is a prevalent enteric bacterium and a necessary organism to monitor for food safety and environmental purposes. Developing efficient and specific methods is critical for detecting and monitoring viable E. coli due to its high prevalence. Conventional culture methods are often laborious and time-consuming, and they offer limited capability in detecting potentially harmful viable but non-culturable E. coli in the tested sample, which highlights the need for improved approaches. Hence, there is a growing demand for accurate and sensitive methods to determine the presence of viable E. coli. This paper scrutinizes various methods for detecting viable E. coli, including culture-based methods, molecular methods that target DNAs and RNAs, bacteriophage-based methods, biosensors, and other emerging technologies. The review serves as a guide for researchers seeking additional methodological options and aiding in the development of rapid and precise assays. Moving forward, it is anticipated that methods for detecting E. coli will become more stable and robust, ultimately contributing significantly to the improvement of food safety and public health.

Machine learning assisted biosensing technology: An emerging powerful tool for improving the intelligence of food safety detection

Recently, the application of biosensors in food safety assessment has gained considerable research attention. Nevertheless, the evaluation of biosensors' sensitivity, accuracy, and efficiency is still ongoing. The advent of machine learning has enhanced the application of biosensors in food security assessment, yielding improved results. Machine learning has been preliminarily applied in combination with different biosensors in food safety assessment, with positive results. This review offers a comprehensive summary of the diverse machine learning methods employed in biosensors for food safety. Initially, the primary machine learning methods were outlined, and the integrated application of biosensors and machine learning in food safety was thoroughly examined. Lastly, the challenges and limitations of machine learning and biosensors in the realm of food safety were underscored, and potential solutions were explored. The review's findings demonstrated that algorithms grounded in machine learning can aid in the early detection of food safety issues. Furthermore, preliminary research suggests that biosensors could be optimized through machine learning for real-time, multifaceted analyses of food safety variables and their interactions. The potential of machine learning and biosensors in real-time monitoring of food quality has been discussed.

Porous Structural Microfluidic Device for Biomedical Diagnosis: A Review

Microfluidics has recently received more and more attention in applications such as biomedical, chemical and medicine. With the development of microelectronics technology as well as material science in recent years, microfluidic devices have made great progress. Porous structures as a discontinuous medium in which the special flow phenomena of fluids lead to their potential and special applications in microfluidics offer a unique way to develop completely new microfluidic chips. In this article, we firstly introduce the fabrication methods for porous structures of different materials. Then, the physical effects of microfluid flow in porous media and their related physical models are discussed. Finally, the state-of-the-art porous microfluidic chips and their applications in biomedicine are summarized, and we present the current problems and future directions in this field.

Paper-based sensors for bacteria detection

The detection of pathogenic bacteria is essential to prevent and treat infections and to provide food security. Current gold-standard detection techniques, such as culture-based assays and polymerase chain reaction, are time-consuming and require centralized laboratories. Therefore, efforts have focused on developing point-of-care devices that are fast, cheap, portable and do not require specialized training. Paper-based analytical devices meet these criteria and are particularly suitable to deployment in low-resource settings. In this Review, we highlight paper-based analytical devices with substantial point-of-care applicability for bacteria detection and discuss challenges and opportunities for future development.

Simpler Procedure and Improved Performance for Pathogenic Bacteria Analysis with a Paper-Based Ratiometric Fluorescent Sensor Array

Bacterial infections are the leading cause of morbidity and mortality in the world, particularly due to a delay in treatment and misidentification of the bacterial species causing the infection. Therefore, rapid and accurate identification of these pathogens has been of prime importance. The conventional diagnostic techniques include microbiological, biochemical, and genetic analyses, which are time-consuming, require large sample volumes, expensive equipment, reagents, and trained personnel. In response, we have now developed a paper-based ratiometric fluorescent sensor array. Environment-sensitive fluorescent dyes (3-hydroxyflavone derivatives) pre-adsorbed on paper microzone plates fabricated using photolithography, upon interaction with bacterial cell envelopes, generate unique fluorescence response patterns. The stability and reproducibility of the sensor array response were thoroughly investigated, and the analysis procedure was refined for optimal performance. Using neural networks for response pattern analysis, the sensor was able to identify 16 bacterial species and recognize their Gram status with an accuracy rate greater than 90%. The paper-based sensor was stable for up to 6 months after fabrication and required 30 times lower dye and sample volumes as compared to the analogous solution-based sensor. Therefore, this approach opens avenues to a state-of-the-art diagnostic tool that can be potentially translated into clinical applications in low-resource environments.

Pattern-based colorimetric sensor array to monitor food spoilage using automated high-throughput analysis

Despite the existing rapid and reliable analytical methods for determining biogenic amine in food matrices, recently special efforts have been devoted for development of portable and inexpensive devices for discrimination of biogenic amines (BAs) in food products to achieve onsite detection of food-spoilage. Thus, in this context, a field deployable cross-reactive sensor array and a field-portable array reader has been developed for determination of food quality. The sensor array consisting of metal complexes (C1 - C11) of single azophenol dye-based receptor generated a unique visible response on interaction with different amines (A1 - A7). Further, the colorimetric pattern and discrimination efficacy of the sensor array was evaluated using multivariate statistical techniques such as principal component analysis and linear discriminant analysis. Motivated by outstanding discriminatory power of sensor array, titration experiment was performed with BAs, and colorimetric response of array was linearly corelated to concentrations of BAs such as tryptamine and spermine with R² values of 0.9596 and 0.967 respectively. Finally, for practical utility and the field analysis, a portable reader was developed and utilized for quantification of biogenic amines in meat and cottage cheese samples spiked with spermine and tryptamine up to the concentrations of 40 μM; therefore, apparently proving the potential applicability of the designed sensing method for food quality monitoring.