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

Abstract

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.

Keywords: artificial intelligence; chromatography; deep learning; food safety; hyperspectral imaging; machine learning; multi-mycotoxin detection; mycotoxin detection; spectroscopy.

Figure 1

Adverse meteorological and weather conditions promote the growth of fungi, such as A. flavus, on food products. These fungi produce mycotoxins on the food’s surface, which can then be transmitted to humans through various channels. Mycotoxins can lead to several health issues in humans, including liver cancer, stunted growth, acute aflatoxicosis, and immune suppression. Reprint from [31]. Copyright © 2024 by the authors and ACS Publishers.

Figure 2

The number of published articles identified between 2014 and 2024 (until 10 September 2024) using the keyword “detection of mycotoxin in food using machine learning techniques”.

Figure 3

The number of published articles identified between 2014 and 2024 (until 10 September 2024) using the keyword “detection of mycotoxin in food using deep learning techniques”.

Figure 4

Block diagram representing the machine learning process. Reprint from [18]. Copyright © 2024 by the authors and MDPI Publishers.

Figure 5

Hyperparameter tuning is first conducted using a random search method, followed by the development of a custom network architecture. To illustrate how the input is transformed to extract features, the convolutional layers are shown with their intermediate activations, representing the outputs of the convolutional network. The dimensions of each step are indicated by the numbers displayed above the layers. Reprinted from [59]. Copyright © 2024 by the authors and Agriculture, MDPI Publishers.

Figure 6

Detection of mycotoxins on wheat using a deep learning technique. Reprint from [67]. Copyright © 2024 by the authors and Scientific Report, Nature.