Optical detection of aflatoxins B in grained almonds using fluorescence spectroscopy and machine learning algorithms

Deep Learning-Based Detection of Aflatoxin B1 Contamination in Almonds Using Hyperspectral Imaging: A Focus on Optimized 3D Inception-ResNet Model

Aflatoxin B1, a toxic carcinogen frequently contaminating almonds, nuts, and food products, poses significant health risks. Therefore, a rapid and non-destructive detection method is crucial to detect aflatoxin B1-contaminated almonds to ensure food safety. This study introduces a novel deep learning approach utilizing 3D Inception-ResNet architecture with fine-tuning to classify aflatoxin B1-contaminated almonds using hyperspectral images. The proposed model achieved higher classification accuracy than traditional methods, such as support vector machine (SVM), random forest (RF), quadratic discriminant analysis (QDA), and decision tree (DT), for classifying aflatoxin B1 contaminated almonds. A feature selection algorithm was employed to enhance processing efficiency and reduce spectral dimensionality while maintaining high classification accuracy. Experimental results demonstrate that the proposed 3D Inception-ResNet (Lightweight) model achieves superior classification performance with a 90.81% validation accuracy, an F1-score of 0.899, and an area under the curve value of 0.964, outperforming traditional machine learning approaches. The Lightweight 3D Inception-ResNet model, with 381 layers, offers a computationally efficient alternative suitable for real-time industrial applications. These research findings highlight the potential of hyperspectral imaging combined with deep learning for aflatoxin B1 detection in almonds with higher accuracy. This approach supports the development of real-time automated screening systems for food safety, reducing contamination-related risks in almonds.

Recovery of AFB1 intrinsic fluorescence in vegetable oils with continuous variations in matrices by theoretical analysis and experiments

The fluorescence characteristics of aflatoxin B1 (AFB1) have enabled the development of an effective and non-destructive screening method for AFB1 in agro-products using fluorescence spectroscopy. However, the complex and varied matrices present in most foodstuffs can significantly distort the intrinsic fluorescence of AFB1. In this study, the absorption and scattering properties of vegetable oils were obtained using double integrating spheres (DIS), and fluorescence intensity was obtained using laser-induced fluorescence (LIF) technique. A six-parameter analytical model has been developed to recover AFB1 intrinsic fluorescence based on the absorption and scattering features at excitation (375 nm) and emission (424 nm) wavelengths employing a one-dimensional convolutional neural network (1D-CNN). Prediction models for AFB1 concentration in vegetable oils with gradient variations of matrices were calibrated using the disturbed and recovered intrinsic fluorescence intensity, respectively. The models were validated and compared to demonstrate the feasibility and superiority of the proposed method.

Detection of Mycotoxin Contamination in Foods Using Artificial Intelligence: A Review

Mycotoxin contamination of foods is a major concern for food safety and public health worldwide. The contamination of agricultural commodities employed by humankind with mycotoxins (toxic secondary metabolites of fungi) is a major risk to the health of the human population. Common methods for mycotoxin detection include chromatographic separation, often combined with mass spectrometry (accurate but time-consuming to prepare the sample and requiring skilled technicians). Artificial intelligence (AI) has been introduced as a new technique for mycotoxin detection in food, providing high credibility and accuracy. This review article provides an overview of recent studies on the use of AI methods for the discovery of mycotoxins in food. The new approach demonstrated that a variety of AI technologies could be correlated. Deep learning models, machine learning algorithms, and neural networks were implemented to analyze elaborate datasets from different analytical platforms. In addition, this review focuses on the advancement of AI to work concomitantly with smart sensing technologies or other non-conventional techniques such as spectroscopy, biosensors, and imaging techniques for rapid and less damaging mycotoxin detection. We question the requirement for large and diverse datasets to train AI models, discuss the standardization of analytical methodologies, and discuss avenues for regulatory approval of AI-based approaches, among other top-of-mind issues in this domain. In addition, this research provides some interesting use cases and real commercial applications where AI has been able to outperform other traditional methods in terms of sensitivity, specificity, and time required. This review aims to provide insights for future directions in AI-enabled mycotoxin detection by incorporating the latest research results and stressing the necessity of multidisciplinary collaboration among food scientists, engineers, and computer scientists. Ultimately, the use of AI could revolutionize systems monitoring mycotoxins, improving food safety and safeguarding global public health.

Recent advances in non-invasive techniques for assessing food quality: Applications and innovations

The global concern for ensuring the safety and authenticity of high-quality food necessitates continuous advancements in food assessment technologies. While conventional methods of food assessment are accurate and precise, they are also laborious, destructive, time-consuming, energy-intensive, chemical-demanding, and less eco-friendly. Their reliability diminishes when dealing with large numbers of food samples. This chapter explores recent advances in non-invasive technologies for food quality assessment, including spectroscopy, optical imaging, and e-sensors. Enhanced by artificial intelligence (AI), these technologies have shown remarkable capabilities in rapid and accurate food identification, authentication, physical appraisal, early disease detection, chemical analysis, and biochemical evaluation. As a result, non-invasive technology holds the potential to revolutionize food quality assessment and assure food safety at every stage of the food supply chain.

Novel Sensor Approaches of Aflatoxins Determination in Food and Beverage Samples

The rapid quantification of toxins in food and beverage products has become a significant issue in overcoming and preventing many life-threatening diseases. Aflatoxin-contaminated food is one of the reasons for primary liver cancer and induces some tumors and cancer types. Advancements in biosensors technology have brought out different analysis methods. Therefore, the sensing performance has been improved for agricultural and beverage industries or food control processes. Nanomaterials are widely used for the enhancement of sensing performance. The enzymes, molecularly imprinted polymers (MIP), antibodies, and aptamers can be used as biorecognition elements. The transducer part of the biosensor can be selected, such as optical, electrochemical, and mass-based. This review explains the classification of major types of aflatoxins, the importance of nanomaterials, electrochemical, optical biosensors, and QCM and their applications for the determination of aflatoxins.

SERS and MRS signals engineered dual-mode aptasensor for simultaneous distinguishment of aflatoxin subtypes

The accurate monitoring of aflatoxin subtypes is vitally important for food safety. Herein, a dual-mode aptasensor with surface-enhanced Raman scattering (SERS) and magnetic relaxation switching (MRS) signals is developed for the detection of aflatoxin B1, B2 and M1 (i.e. AFB1, AFB2 and AFM1). Au-Ag Janus NPs and Au-mushroom NPs are prepared and show intense and non-interfering SERS peaks without the additional modification of Raman molecules, and are utilized as SERS nanotags for the distinguishment of AFB1 and AFB2. Fe3O4@Au NPs functionalized by AFM1 aptamers are applied as MRS nanoprobes for the monitoring of AFM1. Aptamers engineered SERS nanotags and MRS nanoprobes are assembled, and show strong SERS performances and high transverse relaxation time (T2). AFB1, AFB2 and AFM1 induce the separation of SERS nanotags from the assemblies and the dispersion of Fe3O4@Au NPs, resulting in the decrease of SERS signals at 1278 cm-1 and 1000 cm-1 as well as the reduction of T2 values. The dual-mode but three kinds of detection signals don't interfere with each other and exhibit a significant linear relationship with the concentration of targets. This platform provides a high throughput monitoring strategy for the simultaneous analysis of different subtypes of mycotoxin.

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.

Combining AI Tools with Non-Destructive Technologies for Crop-Based Food Safety: A Comprehensive Review

On a global scale, food safety and security aspects entail consideration throughout the farm-to-fork continuum, considering food's supply chain. Generally, the agrifood system is a multiplex network of interconnected features and processes, with a hard predictive rate, where maintaining the food's safety is an indispensable element and is part of the Sustainable Development Goals (SDGs). It has led the scientific community to develop advanced applied analytical methods, such as machine learning (ML) and deep learning (DL) techniques applied for assessing foodborne diseases. The main objective of this paper is to contribute to the development of the consensus version of ongoing research about the application of Artificial Intelligence (AI) tools in the domain of food-crop safety from an analytical point of view. Writing a comprehensive review for a more specific topic can also be challenging, especially when searching within the literature. To our knowledge, this review is the first to address this issue. This work consisted of conducting a unique and exhaustive study of the literature, using our TriScope Keywords-based Synthesis methodology. All available literature related to our topic was investigated according to our criteria of inclusion and exclusion. The final count of data papers was subject to deep reading and analysis to extract the necessary information to answer our research questions. Although many studies have been conducted, limited attention has been paid to outlining the applications of AI tools combined with analytical strategies for crop-based food safety specifically.

Anti-Idiotypic Nanobody Alkaline Phosphatase Fusion Protein-Triggered On-Off-On Fluorescence Immunosensor for Aflatoxin in Cereals

Nanobodies (Nbs) are widely used in immunoassays with the advantages of small size and high stability. Here, the nanobody employed as the surrogate of aflatoxin antigen and the recognition mechanism of antiaflatoxin mAb with nanobody was studied by molecular modeling, which verified the feasibility of Nbs as antigen substitutes. On this basis, a nanobody-alkaline phosphatase fusion protein (Nb-AP) was constructed, and a highly sensitive "on-off-on" fluorescent immunosensor (OFO-FL immunosensor) based on the calcein/Ce3+ system was developed for aflatoxin quantification. Briefly, calcein serves as a signal transducer, and its fluorescence can be quenched after it is bound with Ce3+. In the presence of Nb-AP, AP catalyzed p-nitrophenyl phosphate to generate orthophosphate, which competes in binding with Ce3+, leading to fluorescence recovery. The method has a linearity range of 0.005-100 ng/mL, and the IC50 of the OFO-FL immunosensor was 0.063 ng/mL, which was 18-fold lower than that of conventional enzyme-linked immunosorbent assay. The assay was successfully applied in food samples with a recovery of 88-121%.

Aflatoxin detection technologies: recent advances and future prospects

Aflatoxins have posed serious threat to food safety and human health. Therefore, it is important to detect aflatoxins in samples rapidly and accurately. In this review, various technologies to detect aflatoxins in food are discussed, including conventional ones such as thin-layer chromatography (TLC), high performance liquid chromatography (HPLC), enzyme linked immunosorbent assay (ELISA), colloidal gold immunochromatographic assay (GICA), radioimmunoassay (RIA), fluorescence spectroscopy (FS), as well as emerging ones (e.g., biosensors, molecular imprinting technology, surface plasmon resonance). Critical challenges of these technologies include high cost, complex processing procedures and long processing time, low stability, low repeatability, low accuracy, poor portability, and so on. Critical discussion is provided on the trade-off relationship between detection speed and detection accuracy, as well as the application scenario and sustainability of different technologies. Especially, the prospect of combining different technologies is discussed. Future research is necessary to develop more convenient, more accurate, faster, and cost-effective technologies to detect aflatoxins.

Syntheses of APTMS-Coated ZnO: An Investigation towards Penconazole Detection

Extrinsic chemiluminescence can be an efficient tool for determining pesticides and fungicides, which do not possess any intrinsic fluorescent signal. On this basis, (3-aminopropyl) trimethoxysilane (APTMS)-coated ZnO (APTMS@ZnO) was synthesized and tested as an extrinsic probe for the fungicide penconazole. Several synthetic routes were probed using either a one-pot or two-steps method, in order to ensure both a green synthetic pathway and a good signal variation for the penconazole concentration. The synthesized samples were characterized using X-ray diffraction (XRD), infrared (IR), Raman and ultraviolet-visible (UV-Vis) spectroscopy, scanning electron microscopy (SEM) imaging and associated energy-dispersive X-ray (EDX) analysis. The average size of the synthesized ZnO nanoparticles (NPs) is 54 ± 10 nm, in line with previous preparations. Of all the samples, those synthesized in two steps, at temperatures ranging from room temperature (RT) to a maximum of 40 °C, using water solvent (G-APTMG@ZnO), appeared to be composed of nanoparticles, homogeneously coated with APTMS. Chemiluminescence tests of G-APTMG@ZnO, in the penconazole concentration range 0.7-1.7 ppm resulted in a quenching of the native signal between 6% and 19% with a good linear response, thus indicating a green pathway for detecting the contaminant. The estimated detection limit (LOD) is 0.1 ± 0.01 ppm.

Quantitative detection of Aflatoxin B1 by subpixel CNN regression

Aflatoxin is a highly toxic substance dispersed in peanuts, which seriously harms the health of humans and animals. In this paper, we propose a new method for aflatoxin B1(AFB1) detection inspired by quantitative remote sensing. Firstly, we obtained the relative content of AFB1 at the sub-pixel level by subpixel decomposition (endmember extraction, nonnegative matrix decomposition). Then we modified the transfer learning models (LeNet5, AlexNet, VGG16, and ResNet18) to construct a deep learning regression network for quantitative detection of AFB1. There are 67,178 pixels used for training and 67,164 pixels used for testing. After subpixel decomposition, each aflatoxin pixel was determined to contain content, and each pixel had 400 hyperspectral values (415-799 nm). The experimental results showed that, among the four models, the modified ResNet18 model achieved the best effect, with R² of 0.8898, RMSE of 0.0138, and RPD of 2.8851. Here, we implemented a sub-pixel model for quantitative AFB1 detection and proposed a regression method based on deep learning. Meanwhile, the modified convolution classification model has high predictive ability and robustness. This method provides a new scheme in designing the sorting machine and has practical value.

Research advancements in optical imaging and spectroscopic techniques for nondestructive detection of mold infection and mycotoxins in cereal grains and nuts

Cereal grains and nuts are represented as the economic backbone of many developed and developing countries. Kernels of cereal grains and nuts are prone to mold infection under high relative humidity and suitable temperature conditions in the field as well as storage conditions. Health risks caused by molds and their molecular metabolite mycotoxins are, therefore, important topics to investigate. Strict regulations have been developed by international trade regulatory bodies for the detection of mold growth and mycotoxin contamination across the food chain starting from the harvest to storage and consumption. Molds and aflatoxins are not evenly distributed over the bulk of grains, thus appropriate sampling for detection and quantification is crucial. Existing reference methods for mold and mycotoxin detection are destructive in nature as well as involve skilled labor and hazardous chemicals. Also, these methods cannot be used for inline sorting of the infected kernels. Thus, analytical methods have been extensively researched to develop the one that is more practical to be used in commercial detection and sorting processes. Among various analytical techniques, optical imaging and spectroscopic techniques are attracting growers' attention for their potential of nondestructive and rapid inline identification and quantification of molds and mycotoxins in various food products. This review summarizes the recent application of rapid and nondestructive optical imaging and spectroscopic techniques, including digital color imaging, X-ray imaging, near-infrared spectroscopy, fluorescent, multispectral, and hyperspectral imaging. Advance chemometric techniques to identify very low-level mold growth and mycotoxin contamination are also discussed. Benefits, limitations, and challenges of deploying these techniques in practice are also presented in this paper.

Classification of Aflatoxin B1 Concentration of Single Maize Kernel Based on Near-Infrared Hyperspectral Imaging and Feature Selection

A rapid and nondestructive method is greatly important for the classification of aflatoxin B1 (AFB1) concentration of single maize kernel to satisfy the ever-growing needs of consumers for food safety. A novel method for classification of AFB1 concentration of single maize kernel was developed on the basis of the near-infrared (NIR) hyperspectral imaging (1100–2000 nm). Four groups of AFB1 samples with different concentrations (10, 20, 50, and 100 ppb) and one group of control samples were prepared, which were preprocessed with Savitzky–Golay (SG) smoothing and first derivative (FD) algorithms for their raw NIR spectra. A key wavelength selection method, combining the variance and order of average spectral intensity, was proposed on the basis of pretreated spectra. Moreover, principal component analysis (PCA) was conducted to reduce the dimensionality of hyperspectral data. Finally, a classification model for AFB1 concentrations was developed through linear discriminant analysis (LDA), combined with five key wavelengths and the first three PCs. The results show that the proposed method achieved an ideal performance for classifying AFB1 concentrations in a single maize kernel with overall accuracy, with an F1-score and Kappa values of 95.56%, 0.9554, and 0.9444, respectively, as well as the test accuracy yield of 88.67% for independent validation samples. The combinations of variance and order of average spectral intensity can be used for key wavelength selection which, combined with PCA, can achieve an ideal dimensionality reduction effect for model development. The findings of this study have positive significance for the classification of AFB1 concentration of maize kernels.

An overview of nanomaterial based biosensors for detection of Aflatoxin B1 toxicity in foods

Aflatoxin B1 (AFB1) is one of the most potent mycotoxin contaminating several foods and feeds. It suppresses immunity and consequently increases mutagenicity, carcinogenicity, teratogenicity, hepatotoxicity, embryonic toxicity and increasing morbidity and mortality. Continuous exposure of AFB1 causes liver damage and thus increases the prevalence of cirrhosis and hepatic cancer. This article was planned to provide understanding of AFB1 toxicity and provides future directions for fabrication of cost effective and user-friendly nanomaterials based analytical devices. In the present article various conventional (chromatographic & spectroscopic), modern (PCR & immunoassays) and nanomaterials based biosensing techniques (electrochemical, optical, piezoelectrical and microfluidic) are discussed alongwith their merits and demerits. Nanomaterials based amperometric biosensors are found to be more stable, selective and cost-effective analytical devices in comparison to other biosensors. But many unresolved issues about their stability, toxicity and metabolic fate needs further studies. In-depth studies are needed for development of advanced nanomaterials integrated biosensors for specific, sensitive and fast monitoring of AFB1 toxicity in foods. Integration of biosensing system with micro array technology for simultaneous and automated detection of multiple AFs in real samples is also needed. Concerted efforts are also required to reduce their possible hazardous consequences of nanomaterials based biosensors.

A review on the application of spectroscopy to the condiments detection: from safety to authenticity

Condiments are the magical ingredients that make the food present a richer taste. In recent years, due to the increasing consciousness of food safety and human health, much progress has been made in developing rapid and nondestructive techniques for the evaluation of food condiments safety, authentication, and traceability. The potential of spectroscopy techniques, such as near-infrared (NIR), mid-infrared (MIR), Raman, fluorescence, inductively coupled plasma (ICP), and hyperspectral imaging techniques, has been widely enhanced by numerous applications in this field because of their advantages over other analytical techniques. Following a brief introduction of condiment and safety basics, this review mainly focuses on recent vibrational and atomic spectral applications for condiment nondestructive analysis and evaluation, including (1) chemical hazards detection; (2) microbiological hazards detection; and (3) authenticity concerns. The review shows current spectroscopies to be effective tools that will play indispensable roles for food condiment evaluation. In addition, online/real-time applications of these techniques promise to be a huge growth field in the near future.

Smartphone-based optical assays in the food safety field

Smartphone based devices (SBDs) have the potential to revolutionize food safety control by empowering citizens to perform screening tests. To achieve this, it is of paramount importance to understand current research efforts and identify key technology gaps. Therefore, a systematic review of optical SBDs in the food safety sector was performed. An overview of reviewed SBDs is given focusing on performance characteristics as well as image analysis procedures. The state-of-the-art on commercially available SBDs is also provided. This analysis revealed several important technology gaps, the most prominent of which are: (i) the need to reach a consensus regarding optimal image analysis, (ii) the need to assess the effect of measurement variation caused by using different smartphones and (iii) the need to standardize validation procedures to obtain robust data. Addressing these issues will drive the development of SBDs and potentially unlock their massive potential for citizen-based food control.

•

Optical smartphone based sensors in the food safety field are systematically reviewed.

•

Recommendations on image analysis optimization are given.

•

The analytical performance of smartphone based sensors is discussed.

•

Available commercial devises are critically compared.