IremulbNet: Rethinking the inverted residual architecture for image recognition.

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices encourages the studies on efficient and lightweight neural network model. In this paper, an Inverse Residual Multi-Branch Network named IremulbNet is proposed to solve the problem of insufficient classification accuracy in existing lightweight network models. The core module of this model is to reconstruct an inverse residual structure, in which a special feature fusion method, multi-branch feature extraction, and depthwise separable convolution techniques are used to improve the classification accuracy. The performance of model is tested using image databases. Experimental results show that for the fine-grained image dataset Imagenet-woof, IremulbNet achieved 10.9%, 12.2%, and 15.3% higher accuracy than that of MobileNet V3, ShuffleNet V2, and PeleeNet, respectively. Moreover, it can reduce inference time (GPU) about 42.09% and 75.56% compared to classic ResNet50 and DenseNet121.

Metagenomic Insights into the Microbiome and Resistance Genes of Traditional Fermented Foods in Arabia.

This study uncovered microbial communities and evaluated the microbiological safety of traditional fermented foods consumed in the Arab region. Samples of dairy and non-dairy fermented foods-mish, jibneh, zabadi, and pickles-were collected from local markets in Saudi Arabia. Using the MiSeq system, samples were sequenced using 16S amplicons and shotgun metagenomics. Alpha and beta diversity indicated inter- and intra-variation in the studied fermented foods' bacterial communities. In the case of mish, the replicates were clustered. Twenty-one genera were found to be significantly different (FDR < 0.05) in abundance in pairwise comparison of fermented foods. Five high-quality, metagenome-assembled genomes (MAGs) of Lactococcus lactis, Lactobacillus helveticus, Pseudoalteromonas nigrifaciens, Streptococcus thermophiles, and Lactobacillus acetotolerans were retrieved from the shotgun sequencing representing the dominant taxa in the studied fermented foods. Additionally, 33 genes that cause antimicrobial resistance (ARGs) against ten different antibiotic classes were detected. Metabolic pathways were abundant in the studied metagenomes, such as amino acid metabolism, carbohydrate metabolism, cofactors, and vitamin biosynthesis. Metagenomic evaluation of Arabian fermented foods, including the identification of probiotics, pathogenic bacteria, and ARGs, illustrates the importance of microbiological analysis in evaluating their health effects.

ETL-YOLO v4: A face mask detection algorithm in era of COVID-19 pandemic.

During the last two years, several deep learning-based methods for face mask detection have been proposed by researchers. However, most of the proposed methods struggle with the detection of face masks that are too small an object to detect and further achieve low detection accuracy. Considering the issues of the existing methods, in this work, we have proposed ETL-YOLO v4 with a modified and improved feature extraction and prediction network for tiny YOLO v4 which surpasses all its predecessors and other related work in the literature. To develop ETL-YOLO v4, we have improved the backbone architecture of tiny YOLO v4 by adding a modified-dense SPP network, two additional detection layers with modified and optimized CNN layers that aid in accurate prediction, used Mish as the activation function, and utilized modified anchor boxes. Furthermore, to obtain detection results in images of varied viewpoints, we have added Mosaic and CutMix data augmentation at training time. The proposed ETL-YOLO v4 achieved 9.93% higher mAP, 5.75% higher average precision (AP) for faces with masks, and 16.6% higher average precision (AP) for the face mask region as compared to its original base-line variant.

A novel deep learning based method for COVID-19 detection from CT image.

The novel Coronavirus named COVID-19 that World Health Organization (WHO) announced as a pandemic rapidly spread worldwide. Fast diagnosis of the virus infection is critical to prevent further spread of the virus, help identify the infected population, and cure the patients. Due to the increasing rate of infection and the limitations of the diagnosis kit, auxiliary detection tools are needed. Recent studies show that a deep learning model that comes up with the salient information of CT images can aid in the COVID-19 diagnosis. This study proposes a novel deep learning structure that the pooling layer of this model is a combination of pooling and the Squeeze Excitation Block (SE-block) layer. The proposed model uses Batch Normalization and Mish Function to optimize convergence time and performance of COVID-19 diagnosis. A dataset of two public hospitals was used to evaluate the proposed model. Moreover, it was compared to some different popular deep neural networks (DNN). The results expressed an accuracy of 99.03 with a recognition time of test mode of 0.069 ms in graphics processing unit (GPU). Furthermore, the best network results in classification metrics parameters and real-time applications belong to the proposed model.

An Improved Deep Residual Network Prediction Model for the Early Diagnosis of Alzheimer's Disease.

The early diagnosis of Alzheimer's disease (AD) can allow patients to take preventive measures before irreversible brain damage occurs. It can be seen from cross-sectional imaging studies of AD that the features of the lesion areas in AD patients, as observed by magnetic resonance imaging (MRI), show significant variation, and these features are distributed throughout the image space. Since the convolutional layer of the general convolutional neural network (CNN) cannot satisfactorily extract long-distance correlation in the feature space, a deep residual network (ResNet) model, based on spatial transformer networks (STN) and the non-local attention mechanism, is proposed in this study for the early diagnosis of AD. In this ResNet model, a new Mish activation function is selected in the ResNet-50 backbone to replace the Relu function, STN is introduced between the input layer and the improved ResNet-50 backbone, and a non-local attention mechanism is introduced between the fourth and the fifth stages of the improved ResNet-50 backbone. This ResNet model can extract more information from the layers by deepening the network structure through deep ResNet. The introduced STN can transform the spatial information in MRI images of Alzheimer's patients into another space and retain the key information. The introduced non-local attention mechanism can find the relationship between the lesion areas and normal areas in the feature space. This model can solve the problem of local information loss in traditional CNN and can extract the long-distance correlation in feature space. The proposed method was validated using the ADNI (Alzheimer's disease neuroimaging initiative) experimental dataset, and compared with several models. The experimental results show that the classification accuracy of the algorithm proposed in this study can reach 97.1%, the macro precision can reach 95.5%, the macro recall can reach 95.3%, and the macro F1 value can reach 95.4%. The proposed model is more effective than other algorithms.

Lightweight Image Restoration Network for Strong Noise Removal in Nuclear Radiation Scenes.

In order to remove the strong noise with complex shapes and high density in nuclear radiation scenes, a lightweight network composed of a Noise Learning Unit (NLU) and Texture Learning Unit (TLU) was designed. The NLU is bilinearly composed of a Multi-scale Kernel Module (MKM) and a Residual Module (RM), which learn non-local information and high-level features, respectively. Both the MKM and RM have receptive field blocks and attention blocks to enlarge receptive fields and enhance features. The TLU is at the bottom of the NLU and learns textures through an independent loss. The entire network adopts a Mish activation function and asymmetric convolutions to improve the overall performance. Compared with 12 denoising methods on our nuclear radiation dataset, the proposed method has the fewest model parameters, the highest quantitative metrics, and the best perceptual satisfaction, indicating its high denoising efficiency and rich texture retention.

Catalytic effect on hydrogen de/absorption properties of MgH2 - x wt% MM (x = 0, 10, 20, 30) nanomaterials.

Reversible hydrogen storage in MgH2 under specified conditions is a possible way for the positive reception of hydrogen economy, in which the developments of cheap and highly efficient catalysts are the major challenge, still now. Herein, MgH2 - x wt% MM (x = 0, 10, 20, 30) nanomaterials are prepared via ball milling method and has been evaluated for the hydrogen storage performance, which are characterized by XRD, SEM and DTA/DSC. The hydrogen absorption properties of nanomaterials are measured by pressure composition isotherm, and analysis show that the MgH2 - 30 wt% MM nanomaterials have the maximum hydrogen absorption capacity (~ 3.27 wt% at 300 °C) than MgH2. The activation energy of nanomaterials is remarkably changed by the introduction of MM as additives in MgH2.

Isolation of enterotoxigenic Staphylococcus aureus harboring seb gene and enteropathogenic Escherichia coli (serogroups O18, O114, and O125) from soft and hard artisanal cheeses in Egypt.

Background: Soft and hard artisanal cheeses are regularly consumed in Egypt. These products are usually processed from raw milk which may harbor many pathogenic and spoilage microorganisms. Aim: To evaluate the safety of some artisanal cheeses in Egypt, such as Ras, Domiati, and Mish, through chemical and microbiological examination. Methods: One hundred and fifty random samples of traditional Ras, Domiati, and Mish cheeses (50 each) were microbiologically and chemically analyzed. Counts of total bacteria, presumptive coliform, staphylococci, yeast, and mold were estimated. Furthermore, isolation of Escherichia coli and Staphylococcus aureus was performed, followed by PCR confirmation; isolates of E. coli were examined for the presence of virulence genes; on the other hand, the detection of the five classical enterotoxin genes of S. aureus was performed using multiplex PCR. Regarding chemical analysis, moisture, salt, and acidity content were measured. Correlations between chemical and microbial findings were investigated. Results: Mean counts of total bacteria, presumptive coliform, staphylococci, yeast, and mold were (2 × 108, 3 × 106 and 1 × 107 ), (3 × 105, 5 × 10 and 5 × 102), (1 × 106, 4 × 105and 1 × 105), (3 × 105, 1 × 105 and 5 × 105), and (7 × 103, 4 × 103 and 3 × 104) for Ras, Domiati and Mish cheeses, respectively. Serological identification of suspected E. coli revealed that E. coli O125 was isolated from Ras and Domiati samples, E. coli O18 was recovered from Ras samples, while E. coli O114 was isolated from Mish samples. PCR results revealed that all detected isolates of E. coli were positive for both iss (increased serum survival) and fimH (type 1 fimbriae) genes. Concerning isolated S. aureus, all examined products were harboring S. aureus enterotoxigenic strains, with seb and sed genes being the most common. The mean values of moisture, salt, and acidity were (30.03, 56.44, and 58.70), (3.30, 6.63, and 7.56) and (0.65, 0.68, and 0.50) for Ras, Domiati, and Mish cheeses, respectively. Conclusion: Enterotoxigenic S. aureus harboring seb gene and enteropathogenic E. coli (serogroups O18, O114, and O125) were frequently isolated from soft and hard artisanal cheeses in Egypt. Therefore, strict hygienic measures should be applied during their manufacture, handing, and distribution.

Analyzing Malaria Disease Using Effective Deep Learning Approach.

Medical tools used to bolster decision-making by medical specialists who offer malaria treatment include image processing equipment and a computer-aided diagnostic system. Malaria images can be employed to identify and detect malaria using these methods, in order to monitor the symptoms of malaria patients, although there may be atypical cases that need more time for an assessment. This research used 7000 images of Xception, Inception-V3, ResNet-50, NasNetMobile, VGG-16 and AlexNet models for verification and analysis. These are prevalent models that classify the image precision and use a rotational method to improve the performance of validation and the training dataset with convolutional neural network models. Xception, using the state of the art activation function (Mish) and optimizer (Nadam), improved the effectiveness, as found by the outcomes of the convolutional neural model evaluation of these models for classifying the malaria disease from thin blood smear images. In terms of the performance, recall, accuracy, precision, and F1 measure, a combined score of 99.28% was achieved. Consequently, 10% of all non-dataset training and testing images were evaluated utilizing this pattern. Notable aspects for the improvement of a computer-aided diagnostic to produce an optimum malaria detection approach have been found, supported by a 98.86% accuracy level.

Analyzing Lung Disease Using Highly Effective Deep Learning Techniques.

Image processing technologies and computer-aided diagnosis are medical technologies used to support decision-making processes of radiologists and medical professionals who provide treatment for lung disease. These methods involve using chest X-ray images to diagnose and detect lung lesions, but sometimes there are abnormal cases that take some time to occur. This experiment used 5810 images for training and validation with the MobileNet, Densenet-121 and Resnet-50 models, which are popular networks used to classify the accuracy of images, and utilized a rotational technique to adjust the lung disease dataset to support learning with these convolutional neural network models. The results of the convolutional neural network model evaluation showed that Densenet-121, with a state-of-the-art Mish activation function and Nadam-optimized performance. All the rates for accuracy, recall, precision and F1 measures totaled 98.88%. We then used this model to test 10% of the total images from the non-dataset training and validation. The accuracy rate was 98.97% for the result which provided significant components for the development of a computer-aided diagnosis system to yield the best performance for the detection of lung lesions.

A review of the current understanding and clinical utility of miRNAs in esophageal cancer.

BACKGROUND: MicroRNAs (miRNAs) are a class of small, well-conserved, non-coding RNAs that regulate the translation of RNAs. They have a role in biological and pathological process including cell differentiation, apoptosis, proliferation and metabolism. Since their discovery, they have been shown to have a potential role in cancer pathogenesis through their function as oncogenes or tumor suppressors. A substantial number of miRNAs show differential expression in esophageal cancer tissues, and so have been investigated for possible use in diagnosis. Furthermore, there is increasing interest in their use as prognostic markers and determining treatment response, as well as identifying their downstream targets and understanding their mode of action. METHODS: We analyzed the most recent studies on miRNAs in esophageal cancer and/or Barrett's esophagus (BE). The publications were identified by searching in PuBMed for the following terms: Barrett's esophagus and microRNA; esophageal cancer and microRNA. RESULTS: Four miRNAs (mi-R-25, -99a, -133a and -133b) showed good potential as diagnostic markers and interestingly five (mi-R-21, -27b, -126, - 143 and -145) appeared to be useful both as diagnostic and prognostic/predictive markers. CONCLUSION: The data so far on miRNAs in esophageal carcinogenesis is promising but further work is required to determine whether miRNAs can be used as biomarkers, not only in the clinical setting or added to individualized treatment regimes but also in non-invasive test by making use of miRNAs identified in blood.