Dietary Exposure and Risk Assessment of Mycotoxins in Thyme and Thyme-Based Products Marketed in Lebanon

Enhancing accessibility for improved diagnosis with modified EfficientNetV2-S and cyclic learning rate strategy in women with disabilities and breast cancer

Breast cancer, a prevalent cancer among women worldwide, necessitates precise and prompt detection for successful treatment. While conventional histopathological examination is the benchmark, it is a lengthy process and prone to variations among different observers. Employing machine learning to automate the diagnosis of breast cancer presents a viable option, striving to improve both precision and speed. Previous studies have primarily focused on applying various machine learning and deep learning models for the classification of breast cancer images. These methodologies leverage convolutional neural networks (CNNs) and other advanced algorithms to differentiate between benign and malignant tumors from histopathological images. Current models, despite their potential, encounter obstacles related to generalizability, computational performance, and managing datasets with imbalances. Additionally, a significant number of these models do not possess the requisite transparency and interpretability, which are vital for medical diagnostic purposes. To address these limitations, our study introduces an advanced machine learning model based on EfficientNetV2. This model incorporates state-of-the-art techniques in image processing and neural network architecture, aiming to improve accuracy, efficiency, and robustness in classification. We employed the EfficientNetV2 model, fine-tuned for the specific task of breast cancer image classification. Our model underwent rigorous training and validation using the BreakHis dataset, which includes diverse histopathological images. Advanced data preprocessing, augmentation techniques, and a cyclical learning rate strategy were implemented to enhance model performance. The introduced model exhibited remarkable efficacy, attaining an accuracy rate of 99.68%, balanced precision and recall as indicated by a significant F1 score, and a considerable Cohen's Kappa value. These indicators highlight the model's proficiency in correctly categorizing histopathological images, surpassing current techniques in reliability and effectiveness. The research emphasizes improved accessibility, catering to individuals with disabilities and the elderly. By enhancing visual representation and interpretability, the proposed approach aims to make strides in inclusive medical image interpretation, ensuring equitable access to diagnostic information.

Assessment of mycotoxins in cornflakes marketed in Lebanon

Cornflakes are a popular and convenient breakfast cereal made from corn and widely consumed worldwide, including in Lebanon. However, they are susceptible to mycotoxin contamination, which can have harmful effects on human health. Our study evaluated the occurrence of five mycotoxins (AFB1, OTA, FUM, ZEA, DON) levels in packed cornflakes marketed in Lebanon. A market screening identified 35 different cornflake stock-keeping units (SKU) in the Lebanese market, originating from 10 different brands and having different tastes and shapes. SKUs were collected and tested for five mycotoxins in triplicates using enzyme-linked immunosorbent assay technique. The results showed the presence of the five mycotoxins in the samples. The average levels of AFB1, OTA, ZEA and FUM among positive samples (above limit of detection) were 1.58, 1.2, 15.1 and 774.1 μg/kg, respectively, and were below the EU limits. On the other hand, the average level of DON was 1206.7 μg/kg, exceeding the EU limit. Furthermore, out of the positive samples, 60%, 17%, 9%, 14%, and 6% exceeded the EU limits for DON, OTA, AFB1, FUM, and ZEA, respectively. Notably, SKUs made in Lebanon had significantly (p < 0.05) higher levels of AFB1 and FUM. The packing size of the cornflakes had no significant (p > 0.05) effect on the levels of the five mycotoxins detected in the samples. AFB1, FUM and ZEA levels differed significantly among SKUs (p > 0.05). Considering these findings, further studies should be conducted to assess the exposure to mycotoxins from the consumption of cornflakes in Lebanon, especially among children.

Cancer Diagnosis through Contour Visualization of Gene Expression Leveraging Deep Learning Techniques

Prompt diagnostics and appropriate cancer therapy necessitate the use of gene expression databases. The integration of analytical methods can enhance detection precision by capturing intricate patterns and subtle connections in the data. This study proposes a diagnostic-integrated approach combining Empirical Bayes Harmonization (EBS), Jensen-Shannon Divergence (JSD), deep learning, and contour mathematics for cancer detection using gene expression data. EBS preprocesses the gene expression data, while JSD measures the distributional differences between cancerous and non-cancerous samples, providing invaluable insights into gene expression patterns. Deep learning (DL) models are employed for automatic deep feature extraction and to discern complex patterns from the data. Contour mathematics is applied to visualize decision boundaries and regions in the high-dimensional feature space. JSD imparts significant information to the deep learning model, directing it to concentrate on pertinent features associated with cancerous samples. Contour visualization elucidates the model's decision-making process, bolstering interpretability. The amalgamation of JSD, deep learning, and contour mathematics in gene expression dataset analysis diagnostics presents a promising pathway for precise cancer detection. This method taps into the prowess of deep learning for feature extraction while employing JSD to pinpoint distributional differences and contour mathematics for visual elucidation. The outcomes underscore its potential as a formidable instrument for cancer detection, furnishing crucial insights for timely diagnostics and tailor-made treatment strategies.

Cloud-Based Quad Deep Ensemble Framework for the Detection of COVID-19 Omicron and Delta Variants

The mortality rates of patients contracting the Omicron and Delta variants of COVID-19 are very high, and COVID-19 is the worst variant of COVID. Hence, our objective is to detect COVID-19 Omicron and Delta variants from lung CT-scan images. We designed a unique ensemble model that combines the CNN architecture of a deep neural network-Capsule Network (CapsNet)-and pre-trained architectures, i.e., VGG-16, DenseNet-121, and Inception-v3, to produce a reliable and robust model for diagnosing Omicron and Delta variant data. Despite the solo model's remarkable accuracy, it can often be difficult to accept its results. The ensemble model, on the other hand, operates according to the scientific tenet of combining the majority votes of various models. The adoption of the transfer learning model in our work is to benefit from previously learned parameters and lower data-hunger architecture. Likewise, CapsNet performs consistently regardless of positional changes, size changes, and changes in the orientation of the input image. The proposed ensemble model produced an accuracy of 99.93%, an AUC of 0.999 and a precision of 99.9%. Finally, the framework is deployed in a local cloud web application so that the diagnosis of these particular variants can be accomplished remotely.

Aflatoxins and Ochratoxin A in Tea Sold in Lebanon: Effects of Type, Packaging, and Origin

Tea is among the oldest and most-known beverages around the world, and it has many flavors and types. Tea can be easily contaminated in any of its production steps, especially with mycotoxins that are produced particularly in humid and warm environments. This study aims to examine the level of ochratoxin A (OTA) and total aflatoxin (AF) contamination in black and green tea sold in Lebanon, evaluate its safety compared to international standards, and assess the effect of different variables on the levels of OTA and AFs. For this, the Lebanese market was screened and all tea brands (n = 37; 24 black and 13 green) were collected twice. The Enzyme-Linked Immunoassay (ELISA) method was used to determine OTA and AFs in the samples. AFs and OTA were detected in 28 (75.7%) and 31 (88.6%) samples, respectively. The average of AFs in the positive (above detection limit: 1.75 μg/kg) samples was 2.66 ± 0.15 μg/kg, while the average of OTA in the positive (above detection limit: 1.6 μg/kg) samples was 3.74 ± 0.72 μg/kg. The mean AFs in black and green tea were 2.65 ± 0.55 and 2.54 ± 0.40 μg/kg, respectively, while for OTA, the mean levels were 3.67 ± 0.96 and 3.46 ± 1.09 μg/kg in black and green tea samples, respectively. Four brands (10.8%) contained total aflatoxin levels above the EU limit (4 μg/kg). As for OTA, all samples had OTA levels below the Chinese limit (5 μg/kg). No significant association (p > 0.05) was found between OTA and tea type, level of packaging, country of origin, country of packing, and country of distribution. However, AF contamination was significantly (p < 0.05) higher in unpacked tea, and in brands where the country of origin, packing, and distributor was in Asia. The results showed that the tea brands in Lebanon are relatively safe in terms of AFs and OTA.

Plant Antimicrobials for Food Quality and Safety: Recent Views and Future Challenges

The increasing demand for natural, safe, and sustainable food preservation methods drove research towards the use of plant antimicrobials as an alternative to synthetic preservatives. This review article comprehensively discussed the potential applications of plant extracts, essential oils, and their compounds as antimicrobial agents in the food industry. The antimicrobial properties of several plant-derived substances against foodborne pathogens and spoilage microorganisms, along with their modes of action, factors affecting their efficacy, and potential negative sensory impacts, were presented. The review highlighted the synergistic or additive effects displayed by combinations of plant antimicrobials, as well as the successful integration of plant extracts with food technologies ensuring an improved hurdle effect, which can enhance food safety and shelf life. The review likewise emphasized the need for further research in fields such as mode of action, optimized formulations, sensory properties, safety assessment, regulatory aspects, eco-friendly production methods, and consumer education. By addressing these gaps, plant antimicrobials can pave the way for more effective, safe, and sustainable food preservation strategies in the future.

Single, Subsequent, or Simultaneous Treatments to Mitigate Mycotoxins in Solid Foods and Feeds: A Critical Review

Mycotoxins in solid foods and feeds jeopardize the public health of humans and animals and cause food security issues. The inefficacy of most preventive measures to control the production of fungi in foods and feeds during the pre-harvest and post-harvest stages incited interest in the mitigation of these mycotoxins that can be conducted by the application of various chemical, physical, and/or biological treatments. These treatments are implemented separately or through a combination of two or more treatments simultaneously or subsequently. The reduction rates of the methods differ greatly, as do their effect on the organoleptic attributes, nutritional quality, and the environment. This critical review aims at summarizing the latest studies related to the mitigation of mycotoxins in solid foods and feeds. It discusses and evaluates the single and combined mycotoxin reduction treatments, compares their efficiency, elaborates on their advantages and disadvantages, and sheds light on the treated foods or feeds, as well as on their environmental impact.