Computer vision-based image analysis for rapid detection of acrylamide in heated foods

Computer vision based deep learning approach for toxic and harmful substances detection in fruits

Formaldehyde (CH₂O) is one of the significant chemicals mixed with different perishable fruits in Bangladesh. The fruits are artificially preserved for extended periods by dishonest vendors using this dangerous chemical. Such substances are complicated to detect in appearance. Hence, a reliable and robust detection technique is required. To overcome this challenge and address the issue, we introduce comprehensive deep learning-based techniques for detecting toxic substances. Four different types of fruits, both in fresh and chemically mixed conditions, are used in this experiment. We have applied diverse data augmentation techniques to enlarge the dataset. The performance of four different pre-trained deep learning models was then assessed, and a brand-new model named "DurbeenNet," created especially for this task, was presented. The primary objective was to gauge the efficacy of our proposed model compared to well-established deep learning architectures. Our assessment centered on the models' accuracy in detecting toxic substances. According to our research, GoogleNet detected toxic substances with an accuracy rate of 85.53 %, VGG-16 with an accuracy rate of 87.44 %, DenseNet with an impressive accuracy rate of 90.37 %, and ResNet50 with an accuracy rate of 91.66 %. Notably, the proposed model, DurbeenNet, outshone all other models, boasting an impressive accuracy rate of 96.71 % in detecting toxic substances among the sample fruits.

Biomedical rationale for acrylamide regulation and methods of detection

Acrylamide is the product of the Maillard reaction, which occurs when starchy, asparagine-rich foods including potato or grain products and coffee are fried, baked, roasted, or heated. Studies in rodents provide evidence that acrylamide is carcinogenic and a male reproductive harmful agent when administered in exceedingly high levels. A 2002 study identified acrylamide in popular consumer food and beverage products, stimulating the European Union (EU) and California to legislate public notice of acrylamide presence in fried and baked foods, and coffee products. The regulatory legislation enacted in the EU and California has scientists working to develop foods and processes aimed at reducing acrylamide formation and advancing rapid and accurate analytical methods for the quantitative and qualitative determination of acrylamide in food and beverage products. The purpose of this review is to survey the studies performed on rodents and humans that identified the potential health impact of acrylamide in the human diet, and provide insight into established and emerging analytical methods used to detect acrylamide in blood, aqueous samples, and food.

Effect of Microwave Heating on the Acrylamide Formation in Foods

Acrylamide (AA) is a neurotoxic and carcinogenic substance that has recently been discovered in food. One of the factors affecting its formation is the heat treatment method. This review discusses the microwave heating as one of the methods of thermal food processing and the influence of microwave radiation on the acrylamide formation in food. In addition, conventional and microwave heating were compared, especially the way they affect the AA formation in food. Available studies demonstrate differences in the mechanisms of microwave and conventional heating. These differences may be beneficial or detrimental depending on different processes. The published studies showed that microwave heating at a high power level can cause greater AA formation in products than conventional food heat treatment. The higher content of acrylamide in microwave-heated foods may be due to differences in its formation during microwave heating and conventional methods. At the same time, short exposure to microwaves (during blanching and thawing) at low power may even limit the formation of acrylamide during the final heat treatment. Considering the possible harmful effects of microwave heating on food quality (e.g., intensive formation of acrylamide), further research in this direction should be carried out.

Acrylamide and Thermal-Processing Indexes in Market-Purchased Food

Determining acrylamide (AA) content in foods using chromatographic methods is expensive and time-consuming. Therefore, there is a need to develop a simple, economical method for monitoring the content of acrylamide in foods. This study analysed whether there is a relationship between acrylamide levels with some heat-induced parameters, such as 5-hydroxymethylfurfural (HMF) and browning, in order to assess their usefulness in predicting the potential acrylamide levels in market-purchased food. Sixty plant-based food products were tested. The correlation coefficients for AA levels with L*, a* and b* values and HMF content were significant (p < 0.05) for French fries and potato chips. There was no statistically significant correlation between thermal-processing indexes (HMF and colour parameters) and acrylamide levels in commercial bread, breakfast cereals and biscuits. The results indicate that these classical thermal-processing indexes are not directly related to the acrylamide content in commercial cereal-based food and they cannot be indicators of AA level. Thus, the correlation between HMF and colour parameters with acrylamide content depends on the type of food and it is difficult to estimate the amount of AA based on these classical thermal-processing indexes of market-purchased food.

Effect of Chitosan-Ascorbic Acid Coatings on the Refrigerated Storage Stability of Fresh-Cut Apples

Using natural antimicrobial substances in edible films becomes crucial to extend the shelf-life of fresh-cut fruits due to the consumers’ preferences. In this study chitosan and ascorbic acid based film was used to improve the shelf-life of fresh-cut apples. Fresh-cut apple cubes were dipped in water (control), ascorbic acid (1%) or mixtures of chitosan–ascorbic acid in different ratios (1%:1%, 2%:2% or 1%:5%) for 5 min. After draining, fresh-cut apples were packed in sterile polypropylene jars and stored at 5 °C for 14 days. The treatment with chitosan and ascorbic acid suppressed browning, retained flesh firmness and maintained phenolic compounds throughout the storage period. Moreover, the treatment with chitosan–ascorbic acid significantly retarded the microbial growth during storage. Those findings suggested that the best performance was acquired in 1% chitosan and 5% ascorbic acid coating. That coating could be practical and useful to prolonging the chemical and microbial shelf lives of fresh-cut apples during refrigerated storage.

Computer vision-based analysis of foods: a non-destructive colour measurement tool to monitor quality and safety

Computer vision-based image analysis has been widely used in food industry to monitor food quality. It allows low-cost and non-contact measurements of colour to be performed. In this paper, two computer vision-based image analysis approaches are discussed to extract mean colour or featured colour information from the digital images of foods. These types of information may be of particular importance as colour indicates certain chemical changes or physical properties in foods. As exemplified here, the mean CIE a* value or browning ratio determined by means of computer vision-based image analysis algorithms can be correlated with acrylamide content of potato chips or cookies. Or, porosity index as an important physical property of breadcrumb can be calculated easily. In this respect, computer vision-based image analysis provides a useful tool for automatic inspection of food products in a manufacturing line, and it can be actively involved in the decision-making process where rapid quality/safety evaluation is needed.

Selective cultivation and rapid detection of Staphylococcus aureus by computer vision

In this paper, we developed a selective growth medium and a more rapid detection method based on computer vision for selective isolation and identification of Staphylococcus aureus from foods. The selective medium consisted of tryptic soy broth basal medium, 3 inhibitors (NaCl, K2 TeO3 , and phenethyl alcohol), and 2 accelerators (sodium pyruvate and glycine). After 4 h of selective cultivation, bacterial detection was accomplished using computer vision. The total analysis time was 5 h. Compared to the Baird-Parker plate count method, which requires 4 to 5 d, this new detection method offers great time savings. Moreover, our novel method had a correlation coefficient of greater than 0.998 when compared with the Baird-Parker plate count method. The detection range for S. aureus was 10 to 10(7) CFU/mL.

PRACTICAL APPLICATION

Our new, rapid detection method for microorganisms in foods has great potential for routine food safety control and microbiological detection applications.

Current issues in dietary acrylamide: formation, mitigation and risk assessment

Acrylamide (AA) is known as a neurotoxin in humans and it is classified as a probable human carcinogen by the International Agency of Research on Cancer. AA is produced as by-product of the Maillard reaction in starchy foods processed at high temperatures (>120 °C). This review includes the investigation of AA precursors, mechanisms of AA formation and AA mitigation technologies in potato, cereal and coffee products. Additionally, most relevant issues of AA risk assessment are discussed. New technologies tested from laboratory to industrial scale face, as a major challenge, the reduction of AA content of browned food, while still maintaining its attractive organoleptic properties. Reducing sugars such as glucose and fructose are the major contributors to AA in potato-based products. On the other hand, the limiting substrate of AA formation in cereals and coffee is the free amino acid asparagine. For some products the addition of glycine or asparaginase reduces AA formation during baking. Since, for potatoes, the limiting substrate is reducing sugars, increases in sugar content in potatoes during storage then introduce some difficulties and potentially quite large variations in the AA content of the final product. Sugars in potatoes may be reduced by blanching. Levels of AA in different foods show large variations and no general upper limit is easily applicable, since some formation will always occur. Current policy is that practical measures should be taken voluntarily to reduce AA formation in vulnerable foods since AA is considered a health risk at the concentrations found in foods.