Quantitative detection of Aflatoxin B1 by subpixel CNN regression

Spectral intelligent detection for aflatoxin B1 via contrastive learning based on Siamese network

Aflatoxins, harmful substances found in peanuts, corn, and their derivatives, pose significant health risks. Addressing this, the presented research introduces an innovative MSGhostDNN model, merging contrastive learning with multi-scale convolutional networks for precise aflatoxin detection. The method significantly enhances feature discrimination, achieving an impressive 97.87% detection accuracy with a pre-trained model. By applying Grad-CAM, it further refines the model to identify key wavelengths, particularly 416 nm, and focuses on 40 key wavelengths for optimal performance with 97.46% accuracy. The study also incorporates a task dimensionality reduction approach for continuous learning, allowing effective ongoing aflatoxin spectrum monitoring in peanuts and corn. This approach not only boosts aflatoxin detection efficiency but also sets a precedent for rapid online detection of similar toxins, offering a promising solution to mitigate the health risks associated with aflatoxin exposure.

Detection of Water pH Using Visible Near-Infrared Spectroscopy and One-Dimensional Convolutional Neural Network

pH is an important parameter for water quality detection. This study proposed a novel calibration regression strategy based on a one-dimensional convolutional neural network (1D-CNN) for water pH detection using visible near-infrared (Vis-NIR) spectroscopy. Two groups of Vis-NIR spectral analysis experiments of water pH detection were employed to evaluate the performance of 1D-CNN. Two conventional multivariate regression calibration methods, including partial least squares (PLS) and least squares support vector machine (LS-SVM), were introduced for comparative analysis with 1D-CNN. The successive projections algorithm (SPA) was adopted to select the feature variables. In addition, the learning mechanism of 1D-CNN was interpreted through visual feature maps by convolutional layers. The results showed that the 1D-CNN models obtained the highest prediction accuracy based on full spectra for the two experiments. For the spectrophotometer experiment, the root mean square error of prediction (RMSEP) was 0.7925, and the determination coefficient of prediction (Rp2) was 0.8515. For the grating spectrograph experiment, the RMSEP was 0.5128 and the Rp2 was 0.9273. The convolutional layers could automatically preprocess the spectra and effectively extract the spectra features. Compared with the traditional regression methods, 1D-CNN does not need complex spectra pretreatment and variable selection. Therefore, 1D-CNN is a promising regression approach, with higher prediction accuracy and better modeling convenience for rapid water pH detection using Vis-NIR spectroscopy.

Markov Transition Field Combined with Convolutional Neural Network Improved the Predictive Performance of Near-Infrared Spectroscopy Models for Determination of Aflatoxin B1 in Maize

This work provides a novel approach to monitor the aflatoxin B₁ (AFB₁) content in maize by near-infrared (NIR) spectra-based deep learning models that integrates Markov transition field (MTF) image coding and a convolutional neural network (CNN) strategy. According to the data structure characteristics of near-infrared spectra, new structures of one-dimensional CNN (1D-CNN) and two-dimensional MTF-CNN (2D-MTF-CNN) were designed to construct a deep learning model for the monitoring of AFB₁ in maize. The results obtained showed that compared with the 1D-CNN model, the performance of the 2D-MTF-CNN model had been significantly improved, and its root mean square error of prediction, coefficient of predictive determination, and relative percent deviation were 1.3591 μg·kg^-1, 0.9955, and 14.9386, respectively. The results indicate that the MTF is an effective data encoding technique for converting one-dimensional spectra into two-dimensional images. It more intuitively reflects the intrinsic characteristics of the NIR spectra from a new perspective and provides richer spectral information for the construction of deep learning models, which can ensure the detection accuracy and generalization performance of deep learning quantitative detection models. This study provides a new analytical perspective for the chemometrics analysis of the NIR spectroscopy.

Coexposure of Cyclopiazonic Acid with Aflatoxin B1 Involved in Disrupting Amino Acid Metabolism and Redox Homeostasis Causing Synergistic Toxic Effects in Hepatocyte Spheroids

Cyclopiazonic acid (CPA), an emerging toxin, has been found in various foods such as corn, peanuts, and figs. Aspergillus flavus can produce CPA, leading to coexposure with highly toxic aflatoxin B1 (AFB1), but the mechanism of their combined action is not clear. In this study, cocultured hepatocyte spheroids were used as the evaluation model, and two concentration settings of isotoxicity and different toxicity ratios were used to investigate the combined toxic effects. Metabolomics was subsequently used to analyze the potential mechanisms underlying the effects of their exposure. AFB1 and CPA might exhibit stronger cytotoxicity, with significant combined effects on mitochondrial morphology, activity, and reactive oxygen levels. The gene expression analysis revealed that the overexpression of AKT genes could mitigate the combined effects of AFB1 and CPA to some extent. Metabolomics analysis indicated that AFB1 and CPA significantly downregulated the metabolism of l-aspartate and antioxidant substances (e.g., penicillamine, myricetin, and ethanolamine). The pathway enrichment analysis also revealed a large impact on amino acid metabolism, likely affecting intracellular redox homeostasis. In addition, the presence of CPA affects intracellular glucose metabolism and lipid metabolism pathways. This study suggested a direction for future research on relevant toxic pathways and provided possible ideas for inhibiting or mitigating toxicity.