Sci Rep. 2024 Apr 15;14(1):8660. doi: 10.1038/s41598-024-56393-8.

ABSTRACT

Agriculture plays a pivotal role in the economic development of a nation, but, growth of agriculture is affected badly by the many factors one such is plant diseases. Early stage prediction of these disease is crucial role for global health and even for game changers the farmer's life. Recently, adoption of modern technologies, such as the Internet of Things (IoT) and deep learning concepts has given the brighter light of inventing the intelligent machines to predict the plant diseases before it is deep-rooted in the farmlands. But, precise prediction of plant diseases is a complex job due to the presence of noise, changes in the intensities, similar resemblance between healthy and diseased plants and finally dimension of plant leaves. To tackle this problem, high-accurate and intelligently tuned deep learning algorithms are mandatorily needed. In this research article, novel ensemble of Swin transformers and residual convolutional networks are proposed. Swin transformers (ST) are hierarchical structures with linearly scalable computing complexity that offer performance and flexibility at various scales. In order to extract the best deep key-point features, the Swin transformers and residual networks has been combined, followed by Feed forward networks for better prediction. Extended experimentation is conducted using Plant Village Kaggle datasets, and performance metrics, including accuracy, precision, recall, specificity, and F1-rating, are evaluated and analysed. Existing structure along with FCN-8s, CED-Net, SegNet, DeepLabv3, Dense nets, and Central nets are used to demonstrate the superiority of the suggested version. The experimental results show that in terms of accuracy, precision, recall, and F1-rating, the introduced version shown better performances than the other state-of-art hybrid learning models.

PMID:38622177 | DOI:10.1038/s41598-024-56393-8

J Imaging Inform Med. 2024 Apr 15. doi: 10.1007/s10278-024-01108-8. Online ahead of print.

ABSTRACT

Convolutional neural networks (CNN) have been used for a wide variety of deep learning applications, especially in computer vision. For medical image processing, researchers have identified certain challenges associated with CNNs. These challenges encompass the generation of less informative features, limitations in capturing both high and low-frequency information within feature maps, and the computational cost incurred when enhancing receptive fields by deepening the network. Transformers have emerged as an approach aiming to address and overcome these specific limitations of CNNs in the context of medical image analysis. Preservation of all spatial details of medical images is necessary to ensure accurate patient diagnosis. Hence, this research introduced the use of a pure Vision Transformer (ViT) for a denoising artificial neural network for medical image processing specifically for low-dose computed tomography (LDCT) image denoising. The proposed model follows a U-Net framework that contains ViT modules with the integration of Noise2Neighbor (N2N) interpolation operation. Five different datasets containing LDCT and normal-dose CT (NDCT) image pairs were used to carry out this experiment. To test the efficacy of the proposed model, this experiment includes comparisons between the quantitative and visual results among CNN-based (BM3D, RED-CNN, DRL-E-MP), hybrid CNN-ViT-based (TED-Net), and the proposed pure ViT-based denoising model. The findings of this study showed that there is about 15-20% increase in SSIM and PSNR when using self-attention transformers than using the typical pure CNN. Visual results also showed improvements especially when it comes to showing fine structural details of CT images.

PMID:38622385 | DOI:10.1007/s10278-024-01108-8

Brief Bioinform. 2024 Mar 27;25(3):bbae170. doi: 10.1093/bib/bbae170.

ABSTRACT

N6-methyladenosine (m6A) is the most abundant mRNA modification within mammalian cells, holding pivotal significance in the regulation of mRNA stability, translation and splicing. Furthermore, it plays a critical role in the regulation of RNA degradation by primarily recruiting the YTHDF2 reader protein. However, the selective regulation of mRNA decay of the m6A-methylated mRNA through YTHDF2 binding is poorly understood. To improve our understanding, we developed m6A-BERT-Deg, a BERT model adapted for predicting YTHDF2-mediated degradation of m6A-methylated mRNAs. We meticulously assembled a high-quality training dataset by integrating multiple data sources for the HeLa cell line. To overcome the limitation of small training samples, we employed a pre-training-fine-tuning strategy by first performing a self-supervised pre-training of the model on 427 760 unlabeled m6A site sequences. The test results demonstrated the importance of this pre-training strategy in enabling m6A-BERT-Deg to outperform other benchmark models. We further conducted a comprehensive model interpretation and revealed a surprising finding that the presence of co-factors in proximity to m6A sites may disrupt YTHDF2-mediated mRNA degradation, subsequently enhancing mRNA stability. We also extended our analyses to the HEK293 cell line, shedding light on the context-dependent YTHDF2-mediated mRNA degradation.

PMID:38622358 | DOI:10.1093/bib/bbae170

Sci Rep. 2024 Apr 15;14(1):8718. doi: 10.1038/s41598-024-58628-0.

ABSTRACT

Chronic Obstructive Pulmonary Disease (COPD) is characterized by progressive and irreversible airflow limitation, with individual body composition influencing disease severity. Severe emphysema worsens symptoms through hyperinflation, which can be relieved by bronchoscopic lung volume reduction (BLVR). To investigate how body composition, assessed through CT scans, impacts outcomes in emphysema patients undergoing BLVR. Fully automated CT-based body composition analysis (BCA) was performed in patients with end-stage emphysema receiving BLVR with valves. Post-interventional muscle and adipose tissues were quantified, body size-adjusted, and compared to baseline parameters. Between January 2015 and December 2022, 300 patients with severe emphysema underwent endobronchial valve treatment. Significant improvements were seen in outcome parameters, which were defined as changes in pulmonary function, physical performance, and quality of life (QoL) post-treatment. Muscle volume remained stable (1.632 vs. 1.635 for muscle bone adjusted ratio (BAR) at baseline and after 6 months respectively), while bone adjusted adipose tissue volumes, especially total and pericardial adipose tissue, showed significant increase (2.86 vs. 3.00 and 0.16 vs. 0.17, respectively). Moderate to strong correlations between bone adjusted muscle volume and weaker correlations between adipose tissue volumes and outcome parameters (pulmonary function, QoL and physical performance) were observed. Particularly after 6-month, bone adjusted muscle volume changes positively corresponded to improved outcomes (ΔForced expiratory volume in 1 s [FEV1], r = 0.440; ΔInspiratory vital capacity [IVC], r = 0.397; Δ6Minute walking distance [6MWD], r = 0.509 and ΔCOPD assessment test [CAT], r = -0.324; all p < 0.001). Group stratification by bone adjusted muscle volume changes revealed that groups with substantial muscle gain experienced a greater clinical benefit in pulmonary function improvements, QoL and physical performance (ΔFEV1%, 5.5 vs. 39.5; ΔIVC%, 4.3 vs. 28.4; Δ6MWDm, 14 vs. 110; ΔCATpts, -2 vs. -3.5 for groups with ΔMuscle, BAR% < -10 vs. > 10, respectively). BCA results among patients divided by the minimal clinically important difference for forced expiratory volume of the first second (FEV1) showed significant differences in bone-adjusted muscle and intramuscular adipose tissue (IMAT) volumes and their respective changes after 6 months (ΔMuscle, BAR% -5 vs. 3.4 and ΔIMAT, BAR% -0.62 vs. 0.60 for groups with ΔFEV1 ≤ 100 mL vs > 100 mL). Altered body composition, especially increased muscle volume, is associated with functional improvements in BLVR-treated patients.

PMID:38622275 | DOI:10.1038/s41598-024-58628-0

Med Eng Phys. 2024 Apr;126:104132. doi: 10.1016/j.medengphy.2024.104132. Epub 2024 Mar 2.

ABSTRACT

This research work explores the integration of medical and information technology, particularly focusing on the use of data analytics and deep learning techniques in medical image processing. Specifically, it addresses the diagnosis and prediction of fetal conditions, including Down Syndrome (DS), through the analysis of ultrasound images. Despite existing methods in image segmentation, feature extraction, and classification, there is a pressing need to enhance diagnostic accuracy. Our research delves into a comprehensive literature review and presents advanced methodologies, incorporating sophisticated deep learning architectures and data augmentation techniques to improve fetal diagnosis. Moreover, the study emphasizes the clinical significance of accurate diagnostics, detailing the training and validation process of the AI model, ensuring ethical considerations, and highlighting the potential of the model in real-world clinical settings. By pushing the boundaries of current diagnostic capabilities and emphasizing rigorous clinical validation, this research work aims to contribute significantly to medical imaging and pave the way for more precise and reliable fetal health assessments.

PMID:38621854 | DOI:10.1016/j.medengphy.2024.104132

Med Eng Phys. 2024 Apr;126:104161. doi: 10.1016/j.medengphy.2024.104161. Epub 2024 Mar 28.

ABSTRACT

The application of deep learning to the classification of pulse waves in Traditional Chinese Medicine (TCM) related to hypertensive target organ damage (TOD) is hindered by challenges such as low classification accuracy and inadequate generalization performance. To address these challenges, we introduce a lightweight transfer learning model named MobileNetV2SCP. This model transforms time-domain pulse waves into 36-dimensional frequency-domain waveform feature maps and establishes a dedicated pre-training network based on these maps to enhance the learning capability for small samples. To improve global feature correlation, we incorporate a novel fusion attention mechanism (SAS) into the inverted residual structure, along with the utilization of 3 × 3 convolutional layers and BatchNorm layers to mitigate model overfitting. The proposed model is evaluated using cross-validation results from 805 cases of pulse waves associated with hypertensive TOD. The assessment metrics, including Accuracy (92.74 %), F1-score (91.47 %), and Area Under Curve (AUC) (97.12 %), demonstrate superior classification accuracy and generalization performance compared to various state-of-the-art models. Furthermore, this study investigates the correlations between time-domain and frequency-domain features in pulse waves and their classification in hypertensive TOD. It analyzes key factors influencing pulse wave classification, providing valuable insights for the clinical diagnosis of TOD.

PMID:38621841 | DOI:10.1016/j.medengphy.2024.104161

Med Eng Phys. 2024 Apr;126:104138. doi: 10.1016/j.medengphy.2024.104138. Epub 2024 Mar 4.

ABSTRACT

Lung cancer is one of the most deadly diseases in the world. Lung cancer detection can save the patient's life. Despite being the best imaging tool in the medical sector, clinicians find it challenging to interpret and detect cancer from Computed Tomography (CT) scan data. One of the most effective ways for the diagnosis of certain malignancies like lung tumours is Positron Emission Tomography (PET) imaging. So many diagnosis models have been implemented nowadays to diagnose various diseases. Early lung cancer identification is very important for predicting the severity level of lung cancer in cancer patients. To explore the effective model, an image fusion-based detection model is proposed for lung cancer detection using an improved heuristic algorithm of the deep learning model. Firstly, the PET and CT images are gathered from the internet. Further, these two collected images are fused for further process by using the Adaptive Dilated Convolution Neural Network (AD-CNN), in which the hyperparameters are tuned by the Modified Initial Velocity-based Capuchin Search Algorithm (MIV-CapSA). Subsequently, the abnormal regions are segmented by influencing the TransUnet3+. Finally, the segmented images are fed into the Hybrid Attention-based Deep Networks (HADN) model, encompassed with Mobilenet and Shufflenet. Therefore, the effectiveness of the novel detection model is analyzed using various metrics compared with traditional approaches. At last, the outcome evinces that it aids in early basic detection to treat the patients effectively.

PMID:38621836 | DOI:10.1016/j.medengphy.2024.104138

Cold Spring Harb Perspect Biol. 2024 Apr 15:a041467. doi: 10.1101/cshperspect.a041467. Online ahead of print.

ABSTRACT

Over the years, many computational methods have been created for the analysis of the impact of single amino acid substitutions resulting from single-nucleotide variants in genome coding regions. Historically, all methods have been supervised and thus limited by the inadequate sizes of experimentally curated data sets and by the lack of a standardized definition of variant effect. The emergence of unsupervised, deep learning (DL)-based methods raised an important question: Can machines learn the language of life from the unannotated protein sequence data well enough to identify significant errors in the protein "sentences"? Our analysis suggests that some unsupervised methods perform as well or better than existing supervised methods. Unsupervised methods are also faster and can, thus, be useful in large-scale variant evaluations. For all other methods, however, their performance varies by both evaluation metrics and by the type of variant effect being predicted. We also note that the evaluation of method performance is still lacking on less-studied, nonhuman proteins where unsupervised methods hold the most promise.

PMID:38621825 | DOI:10.1101/cshperspect.a041467

Osong Public Health Res Perspect. 2024 Mar 28. doi: 10.24171/j.phrp.2023.0287. Online ahead of print.

ABSTRACT

OBJECTIVES: The coronavirus disease 2019 (COVID-19) pandemic continues to pose significant challenges to the public health sector, including that of the United Arab Emirates (UAE). The objective of this study was to assess the efficiency and accuracy of various deep-learning models in forecasting COVID-19 cases within the UAE, thereby aiding the nation's public health authorities in informed decision-making.

METHODS: This study utilized a comprehensive dataset encompassing confirmed COVID-19 cases, demographic statistics, and socioeconomic indicators. Several advanced deep learning models, including long short-term memory (LSTM), bidirectional LSTM, convolutional neural network (CNN), CNN-LSTM, multilayer perceptron, and recurrent neural network (RNN) models, were trained and evaluated. Bayesian optimization was also implemented to fine-tune these models.

RESULTS: The evaluation framework revealed that each model exhibited different levels of predictive accuracy and precision. Specifically, the RNN model outperformed the other architectures even without optimization. Comprehensive predictive and perspective analytics were conducted to scrutinize the COVID-19 dataset.

CONCLUSION: This study transcends academic boundaries by offering critical insights that enable public health authorities in the UAE to deploy targeted data-driven interventions. The RNN model, which was identified as the most reliable and accurate for this specific context, can significantly influence public health decisions. Moreover, the broader implications of this research validate the capability of deep learning techniques in handling complex datasets, thus offering the transformative potential for predictive accuracy in the public health and healthcare sectors.

PMID:38621765 | DOI:10.24171/j.phrp.2023.0287

Methods. 2024 Apr 13:S1046-2023(24)00087-2. doi: 10.1016/j.ymeth.2024.04.004. Online ahead of print.

ABSTRACT

Epigenetic proteins (EP) play a role in the progression of a wide range of diseases, including autoimmune disorders, neurological disorders, and cancer. Recognizing their different functions has prompted researchers to investigate them as potential therapeutic targets and pharmacological targets. This paper proposes a novel deep learning-based model that accurately predicts EP. This study introduces a novel deep learning-based model that accurately predicts EP. Our approach entails generating two distinct datasets for training and evaluating the model. We then use three distinct strategies to transform protein sequences to numerical representations: Dipeptide Deviation from Expected Mean (DDE), Dipeptide Composition (DPC), and Group Amino Acid (GAAC). Following that, we train and compare the performance of four advanced deep learning models algorithms: Ensemble Residual Convolutional Neural Network (ERCNN), Generative Adversarial Network (GAN), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU). The DDE encoding combined with the ERCNN model demonstrates the best performance on both datasets. This study demonstrates deep learning's potential for precisely predicting EP, which can considerably accelerate research and streamline drug discovery efforts. This analytical method has the potential to find new therapeutic targets and advance our understanding of EP activities in disease.

PMID:38621436 | DOI:10.1016/j.ymeth.2024.04.004

J Plant Physiol. 2024 Apr 2;297:154236. doi: 10.1016/j.jplph.2024.154236. Online ahead of print.

ABSTRACT

Germline cells are critical for transmitting genetic information to subsequent generations in biological organisms. While their differentiation from somatic cells during embryonic development is well-documented in most animals, the regulatory mechanisms initiating plant germline cells are not well understood. To thoroughly investigate the complex morphological transformations of their ultrastructure over developmental time, nanoscale 3D reconstruction of entire plant tissues is necessary, achievable exclusively through electron microscopy imaging. This paper presents a full-process framework designed for reconstructing large-volume plant tissue from serial electron microscopy images. The framework ensures end-to-end direct output of reconstruction results, including topological networks and morphological analysis. The proposed 3D cell alignment, denoise, and instance segmentation pipeline (3DCADS) leverages deep learning to provide a cell instance segmentation workflow for electron microscopy image series, ensuring accurate and robust 3D cell reconstructions with high computational efficiency. The pipeline involves five stages: the registration of electron microscopy serial images; image enhancement and denoising; semantic segmentation using a Transformer-based neural network; instance segmentation through a supervoxel-based clustering algorithm; and an automated analysis and statistical assessment of the reconstruction results, with the mapping of topological connections. The 3DCADS model's precision was validated on a plant tissue ground-truth dataset, outperforming traditional baseline models and deep learning baselines in overall accuracy. The framework was applied to the reconstruction of early meiosis stages in the anthers of Arabidopsis thaliana, resulting in a topological connectivity network and analysis of morphological parameters and characteristics of cell distribution. The experiment underscores the 3DCADS model's potential for biological tissue identification and its significance in quantitative analysis of plant cell development, crucial for examining samples across different genetic phenotypes and mutations in plant development. Additionally, the paper discusses the regulatory mechanisms of Arabidopsis thaliana's germline cells and the development of stamen cells before meiosis, offering new insights into the transition from somatic to germline cell fate in plants.

PMID:38621330 | DOI:10.1016/j.jplph.2024.154236

Annu Rev Genomics Hum Genet. 2024 Apr 15. doi: 10.1146/annurev-genom-120622-020615. Online ahead of print.

ABSTRACT

The last five years have seen impressive progress in deep learning models applied to protein research. Most notably, sequence-based structure predictions have seen transformative gains in the form of AlphaFold2 and related approaches. Millions of missense protein variants in the human population lack annotations, and these computational methods are a valuable means to prioritize variants for further analysis. Here, we review the recent progress in deep learning models applied to the prediction of protein structure and protein variants, with particular emphasis on their implications for human genetics and health. Improved prediction of protein structures facilitates annotations of the impact of variants on protein stability, protein-protein interaction interfaces, and small-molecule binding pockets. Moreover, it contributes to the study of host-pathogen interactions and the characterization of protein function. As genome sequencing in large cohorts becomes increasingly prevalent, we believe that better integration of state-of-the-art protein informatics technologies into human genetics research is of paramount importance.

PMID:38621234 | DOI:10.1146/annurev-genom-120622-020615

Interact J Med Res. 2024 Apr 15;13:e54490. doi: 10.2196/54490.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) has garnered considerable attention in the context of sepsis research, particularly in personalized diagnosis and treatment. Conducting a bibliometric analysis of existing publications can offer a broad overview of the field and identify current research trends and future research directions.

OBJECTIVE: The objective of this study is to leverage bibliometric data to provide a comprehensive overview of the application of AI in sepsis.

METHODS: We conducted a search in the Web of Science Core Collection database to identify relevant articles published in English until August 31, 2023. A predefined search strategy was used, evaluating titles, abstracts, and full texts as needed. We used the Bibliometrix and VOSviewer tools to visualize networks showcasing the co-occurrence of authors, research institutions, countries, citations, and keywords.

RESULTS: A total of 259 relevant articles published between 2014 and 2023 (until August) were identified. Over the past decade, the annual publication count has consistently risen. Leading journals in this domain include Critical Care Medicine (17/259, 6.6%), Frontiers in Medicine (17/259, 6.6%), and Scientific Reports (11/259, 4.2%). The United States (103/259, 39.8%), China (83/259, 32%), United Kingdom (14/259, 5.4%), and Taiwan (12/259, 4.6%) emerged as the most prolific countries in terms of publications. Notable institutions in this field include the University of California System, Emory University, and Harvard University. The key researchers working in this area include Ritankar Das, Chris Barton, and Rishikesan Kamaleswaran. Although the initial period witnessed a relatively low number of articles focused on AI applications for sepsis, there has been a significant surge in research within this area in recent years (2014-2023).

CONCLUSIONS: This comprehensive analysis provides valuable insights into AI-related research conducted in the field of sepsis, aiding health care policy makers and researchers in understanding the potential of AI and formulating effective research plans. Such analysis serves as a valuable resource for determining the advantages, sustainability, scope, and potential impact of AI models in sepsis.

PMID:38621231 | DOI:10.2196/54490

Opt Lett. 2024 Apr 15;49(8):1993-1996. doi: 10.1364/OL.517007.

ABSTRACT

Unsupervised spectral reconstruction (SR) aims to recover the hyperspectral image (HSI) from corresponding RGB images without annotations. Existing SR methods achieve it from a single RGB image, hindered by the significant spectral distortion. Although several deep learning-based methods increase the SR accuracy by adding RGB images, their networks are always designed for other image recovery tasks, leaving huge room for improvement. To overcome this problem, we propose a novel, to our knowledge, approach that reconstructs the HSI from a pair of RGB images captured under two illuminations, significantly improving reconstruction accuracy. Specifically, an SR iterative model based on two illuminations is constructed at first. By unfolding the proximal gradient algorithm solving this SR model, an interpretable unsupervised deep network is proposed. All the modules in the proposed network have precise physical meanings, which enable our network to have superior performance and good generalization capability. Experimental results on two public datasets and our real-world images show the proposed method significantly improves both visually and quantitatively as compared with state-of-the-art methods.

PMID:38621059 | DOI:10.1364/OL.517007

Opt Lett. 2024 Apr 15;49(8):1957-1960. doi: 10.1364/OL.517164.

ABSTRACT

In the past two decades, photothermal microscopy (PTM) has achieved sensitivity at the level of a single particle or molecule and has found applications in the fields of material science and biology. PTM is a far-field imaging method; its resolution is restricted by the diffraction limits. In our previous work, the modulated difference PTM (MDPTM) was proposed to improve the lateral resolution, but its resolution improvement was seriously constrained by information loss and artifacts. In this Letter, a deep learning approach of the cycle generative adversarial network (Cycle GAN) is employed for further improving the resolution of PTM, called DMDPTM. The point spread functions (PSFs) of both PTM and MDPTM are optimized and act as the second generator of Cycle GAN. Besides, the relationship between the sample's volume and the photothermal signal is utilized during dataset construction. The images of both PTM and MDPTM are utilized as the inputs of the Cycle GAN to incorporate more information. In the simulation, DMDPTM quantitatively distinguishes a distance of 60 nm between two nanoparticles (each with a diameter of 60 nm), demonstrating a 4.4-fold resolution enhancement over the conventional PTM. Experimentally, the super-resolution capability of DMDPTM is verified by restored images of Au nanoparticles, achieving the resolution of 114 nm. Finally, the DMDPTM is successfully employed for the imaging of carbon nanotubes. Therefore, the DMDPTM will serve as a powerful tool to improve the lateral resolution of PTM.

PMID:38621050 | DOI:10.1364/OL.517164

Opt Lett. 2024 Apr 15;49(8):1949-1952. doi: 10.1364/OL.509788.

ABSTRACT

Methods have been proposed in recent years aimed at pushing photoacoustic imaging resolution beyond the acoustic diffraction limit, among which those based on random speckle illumination show particular promise. In this Letter, we propose a data-driven deep learning approach to processing the added spatiotemporal information resulting from speckle illumination, where the neural network learns the distribution of absorbers from a series of different samplings of the imaged area. In ex-vivo experiments based on the tomography configuration with prominent artifacts, our method successfully breaks the acoustic diffraction limit and delivers better results in identifying individual targets when compared against a selection of other leading methods.

PMID:38621048 | DOI:10.1364/OL.509788

Opt Lett. 2024 Apr 15;49(8):1941-1944. doi: 10.1364/OL.517284.

ABSTRACT

Snapshot multispectral imaging (SMSI) has attracted much attention in recent years for its compact structure and superior performance. High-level image analysis based on SMSI, such as object classification and recognition, usually takes the image reconstruction as the first step, which hinders its application in many important real-time scenarios. Here we demonstrate the first, to our knowledge, reconstruction-free strategy for object detection with SMSI in the short-wave infrared (SWIR) band. The implementation of our SMSI is based on a modified 4f system which modulates the light with a random phase mask, and the distinctive point spread function in each narrowband endows the system with spectrum resolving ability. A deep learning network with a CenterNet structure is trained to detect a small object by constructing a dataset with the PSF of our SMSI system and the sky images as background. Our results indicate that a small object with a spectral feature can be detected directly with the compressed image output by our SMSI system. This work paves the way toward the use of SMSI to detect a multispectral object in practical applications.

PMID:38621046 | DOI:10.1364/OL.517284

J King Saud Univ Comput Inf Sci. 2022 Sep;34(8):6199-6207. doi: 10.1016/j.jksuci.2021.07.005. Epub 2021 Jul 15.

ABSTRACT

The Coronavirus disease is quickly spreading all over the world and the emergency situation is still out of control. Latest achievements of deep learning algorithms suggest the use of deep Convolutional Neural Network to implement a computer-aided diagnostic system for automatic classification of COVID-19 CT images. In this paper, we propose to employ a feature-wise attention layer in order to enhance the discriminative features obtained by convolutional networks. Moreover, the original performance of the network has been improved using the mixup data augmentation technique. This work compares the proposed attention-based model against the stacked attention networks, and traditional versus mixup data augmentation approaches. We deduced that feature-wise attention extension, while outperforming the stacked attention variants, achieves remarkable improvements over the baseline convolutional neural networks. That is, ResNet50 architecture extended with a feature-wise attention layer obtained 95.57% accuracy score, which, to best of our knowledge, fixes the state-of-the-art in the challenging COVID-CT dataset.

PMID:38620953 | PMC:PMC8280602 | DOI:10.1016/j.jksuci.2021.07.005

IFAC Pap OnLine. 2021;54(15):358-363. doi: 10.1016/j.ifacol.2021.10.282. Epub 2021 Nov 2.

ABSTRACT

COVID-19 has spread around the world rapidly causing a pandemic. In this research, a set of Deep Learning architectures, for diagnosing the presence or not of the disease have been designed and compared; such as, a CNN with 4 incremental convolutional blocks; a VGG-19 architecture; an Inception network; and, a compact CNN model known as MobileNet. For the analysis and comparison, transfer learning techniques were used in forty-five different experiments. All four models were designed to perform binary classification, reaching an accuracy above 95%. A set of different scores were implemented to compare the performance of all models, showing that the VGG-19 and Inception configurations performed the best.

PMID:38620947 | PMC:PMC8562105 | DOI:10.1016/j.ifacol.2021.10.282

J King Saud Univ Comput Inf Sci. 2022 Oct;34(9):7419-7432. doi: 10.1016/j.jksuci.2021.10.001. Epub 2021 Oct 13.

ABSTRACT

Messenger RNA (mRNA) has emerged as a critical global technology that requires global joint efforts from different entities to develop a COVID-19 vaccine. However, the chemical properties of RNA pose a challenge in utilizing mRNA as a vaccine candidate. For instance, the molecules are prone to degradation, which has a negative impact on the distribution of mRNA among patients. In addition, little is known of the degradation properties of individual RNA bases in a molecule. Therefore, this study aims to investigate whether a hybrid deep learning can predict RNA degradation from RNA sequences. Two deep hybrid neural network models were proposed, namely GCN_GRU and GCN_CNN. The first model is based on graph convolutional neural networks (GCNs) and gated recurrent unit (GRU). The second model is based on GCN and convolutional neural networks (CNNs). Both models were computed over the structural graph of the mRNA molecule. The experimental results showed that GCN_GRU hybrid model outperform GCN_CNN model by a large margin during the test time. Validation of proposed hybrid models is performed by well-known evaluation measures. Among different deep neural networks, GCN_GRU based model achieved best scores on both public and private MCRMSE test scores with 0.22614 and 0.34152, respectively. Finally, GCN_GRU pre-trained model has achieved the highest AuC score of 0.938. Such proven outperformance of GCNs indicates that modeling RNA molecules using graphs is critical in understanding molecule degradation mechanisms, which helps in minimizing the aforementioned issues. To show the importance of the proposed GCN_GRU hybrid model, in silico experiments has been contacted. The in-silico results showed that our model pays local attention when predicting a given position's reactivity and exhibits interesting behavior on neighboring bases in the sequence.

PMID:38620874 | PMC:PMC8513509 | DOI:10.1016/j.jksuci.2021.10.001