Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.

المخرجات

Research outputs

Articles, reviews, conference papers and book chapters, indexed by DOI and linked to University researchers.

40 output Results for «Deep learning»

ArticleClosed2026

Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis

Saudi Journal of Otorhinolaryngology Head and Neck Surgery

Abstract Acute otitis media (AOM) represents a prevalent infection in children globally, leading to considerable morbidity and imposing a substantial burden on healthcare systems. Prompt and precise diagnosis is critical to reducing complications, such as tympanic membrane perforation, hearing impairment, and excessive antibiotic prescribing. Advances in artificial intelligence (AI), particularly deep learning, have created opportunities to enhance diagnostic accuracy and broaden access to care, especially in low-resource settings. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of AI-based systems for detecting AOM compared with conventional clinical diagnosis and to analyze their accuracy relative to human clinicians across different model architectures and diagnostic methods. Following PRISMA-DTA standards and PROSPERO registration, systematic searches were conducted in PubMed, Web of Science, and IEEE Xplore up to July 30, 2025. Eligible studies included human participants with suspected AOM, employed AI-driven diagnostic approaches, and used a clinical reference standard. The Quality Assessment of Diagnostic Accuracy Studies-2 tool assessed bias, and pooled sensitivity and specificity were estimated using a bivariate random-effects model. Nine studies published between 2020 and 2025 met the inclusion criteria. The pooled sensitivity and specificity were 91% (95% confidence interval [CI]: 77%–97%) and 99% (95% CI: 94%–100%), respectively. AI models overall matched or outperformed general practitioners and pediatricians, approaching otolaryngologist-level accuracy. AI-based tools have the potential to improve AOM detection, mitigate inequalities in healthcare access, and promote more effective diagnosis, particularly in underserved regions.

acute otitis mediaartificial intelligencedeep learningdiagnostic accuracy
ArticleClosed2026

Artificial Intelligence in Anatomical Education and Clinical Anatomy: Current Applications and Future Directions

— · vol. 5 (1) · 97-103

Artificial intelligence (AI) is increasingly influencing medical education and clinical practice by providing new approaches to learning, visualization, diagnosis, decision-making, and personalized training. Anatomical education represents an important area for AI integration because conventional teaching methods often depend on cadaveric dissection, two-dimensional illustrations, atlases, and static imaging resources. Recent advances in machine learning, deep learning, computer vision, natural language processing, generative AI, and three-dimensional reconstruction have created opportunities to enhance the teaching and understanding of human anatomy. AI-supported anatomical education can facilitate automated identification of anatomical structures, generation of personalized learning materials, interactive three-dimensional models, intelligent tutoring, image-based assessment, and adaptive learning environments. In clinical anatomy, AI can assist with anatomical segmentation, interpretation of medical images, surgical planning, identification of anatomical variations, and simulation-based training. Nevertheless, the implementation of AI also presents challenges related to accuracy, bias, data privacy, explainability, cost, technological infrastructure, academic integrity, and the potential overreliance of students on automated systems. This review discusses the current applications of AI in anatomical education and clinical anatomy, examines its potential advantages and limitations, and considers future directions for responsible integration into anatomy curricula and healthcare practice. The future of AI-assisted anatomy is likely to involve multimodal learning environments combining three-dimensional visualization, augmented and virtual reality, intelligent tutoring systems, medical imaging, and generative AI. Rather than replacing anatomists and educators, AI is expected to function as an augmentative technology that supports deeper anatomical understanding, individualized learning, and clinically oriented education.

artificial intelligenceanatomy educationclinical anatomygenerative AI
ArticleClosed20258citation· Semantic Scholar

Synergistic Integration of 5G-Enabled Cloud Native Infrastructures With Advanced Technologies for Urban Safety Enhancement

IEEE Transactions on Consumer Electronics · vol. 71 (2) · 5321-5334

Urban safety remains an important concern in modern cities, which makes it necessary for advanced approaches to address the progressing challenge such as fire risk assessment and security enhancement. This study explores the important integration of 5G-enabled cloud-native infrastructures with the Internet of Things (IoT), and Artificial Intelligence (AI) algorithm for empowering urban safety. Kubernetes is used as an essential component of the Cloud Native Computing Foundation (CNCF) ecosystem, for managing scalable and resilient infrastructures. This integration of 5G-enabled systems to cloud-native infrastructures proposes an efficient solution that offers high-speed connectivity, low latency, and the scalability required for real-time data processing and communication. In the proposed work, IoT devices are strategically deployed across urban areas to achieve comprehensive coverage and facilitate real-time data collection and monitoring, ideally integrated with Kubernetes-managed clusters to ensure data transmission and processing. Machine Learning (ML) and Deep Learning (DL) based model is trained on the collected data from the field, using Kubernetes for scalable and automated deployment providing real-time data analysis, accurate prediction, and decision-making. The proposed 5G integrated framework provides proactive risk management and enhanced emergency response strategies. The integration of 5G-enabled systems led to a significant reduction in latency, typically to 20 milliseconds, enhancing real-time performance and decision-making processes. This study introduces a framework designed to reduce latency to 20 ms and improve data transmission rates by 25%. Real-world applications, including fire detection and traffic management, demonstrated the systems effectiveness, achieving sensitivity and recall rates of 97% and 96%, respectively. These results underscore the potential of the proposed framework to enhance urban safety while addressing scalability and integration challenges for future implementations.

urban safety5Gcloud-native infrastructureKubernetes
ArticleClosed20251citation· Semantic Scholar

Optimized Deep Learning for Intrusion Detection in Federated IoT Environments

Journal of Circuits Systems and Computers · vol. 35 (07)

Current developments on the Internet of Things (IoT) have completely changed the landscape of Consumer Electronics (CE), enabling next-generation gadgets to be highly intelligent, networked and capable of utilizing large models. In addition to improving data accessibility, this improved connectivity between sensors, actuators and appliances allows autonomous control inside CE networks. Although deep learning models are highly effective in analyzing large amounts of data, controlling the intricacy of deep learning-based intrusion detection in low-latency IoT networks continues to be a formidable task. This paper presents a deep learning-based intrusion detection technique inspired by federated learning (FL), specifically designed for SDN-enabled CE networks. The application of the approach involves stringent training and testing protocols. In order to improve performance and handle the very complicated training data, the Pearson correlation coefficient (PCC) approach of feature selection (FS) is used in this work. Based on the UNSW-NB15 attack detection dataset, the results show that this approach performs better than other current security solutions, making it a promising option for next-generation smart CE networks. Comprehensive experimental evaluations demonstrated the value of the suggested intrusion detection system (IDS), which demonstrated exceptional intrusion detection accuracy in every domain under investigation.

intrusion detectionfederated learningInternet of Things securitysmart home networks
ArticleClosed20251citation· Semantic Scholar

Deep Learning‐Guided Molecular Docking for Rapid Identification of Novel HER2 Inhibitors in Breast Cancer Therapy

ChemistrySelect · vol. 10 (17)

Abstract This study targeted human epidermal growth factor 2 (HER2) using in silico approaches. The inhibitor library, including 4945 compounds, was screened using in silico approaches. A known inhibitor, SYR127063, was used as a control. Three diverse compounds, 10202642 , 25127414 , and 46911863 , had strong binding affinity with HER2. Further, molecular dynamics simulation showed that 46911863 and 10202642 had stable root mean square deviation (RMSD) with no significant conformational changes during the 100 ns simulation. 10202642 had comparatively the highest number of hydrogen bonds during the 100 ns simulation. 46911863 and 10202642 showed hydrogen bond interaction with critical residues Met801 and Thr862, respectively. Further, the molecular mechanics generalized born surface area (MM/GBSA) technique showed that 10202642 had the highest negative binding free energy of −41.45 kcal/mol and 46911863 had the binding free energy of −30.07 kcal/mol, which was comparable to the control (−39.24 kcal/mol). The 500 ns triplicate MD simulations indicate that 46911863 and 10202642 provide the greatest structural stability to the protein, with consistently low RMSD fluctuations. Steered molecular dynamics simulations reveal that 46911863 and 10202642 demonstrate the highest binding stability, requiring the most force for displacement. Overall, this study identified two possible candidates ( 46911863 and 10202642) as potential inhibitors of HER2 that could be further used for experimental analysis and verification.

HER2 inhibitorsbreast cancervirtual screeningbinding free energy
ArticleClosed2025

Accelerating Prostate Cancer Detection Through Histopathological Image Analysis Using Artificial Intelligence

Microscopy Research and Technique · vol. 89 (5) · 687-704

Prostate cancer is a prevalent and serious health concern, ranking among the most frequently diagnosed cancers and a leading cause of cancer-related deaths in men worldwide. Early detection and accurate diagnosis are crucial for improving patient outcomes by limiting disease progression. Histopathological image analysis remains the gold standard for prostate cancer detection; however, manual interpretation is time-consuming and requires specialized expertise. To address these challenges, this study proposes a hybrid deep learning framework that combines an ensemble of transfer-learned CNNs (VGG-16, DenseNet-121, and AlexNet) with a fine-tuned Vision Transformer (ViT). The CNN ensemble extracts rich local features, while the ViT captures global contextual dependencies through a self-attention mechanism and a multilayer perceptron (MLP). Additionally, a cross-attention fusion (CAF) module integrates local and global features, and knowledge distillation (KD) enables a lightweight student network suitable for efficient clinical deployment. The study utilizes the publicly available PANDA dataset for training and testing. Preprocessing steps, including patch generation, gamma correction, and stain deconvolution, enhance image quality and feature representation. A comprehensive evaluation was conducted using standard performance metrics such as accuracy, true positive rate (TPR), true negative rate (TNR), precision, F1-score, false negative rate (FNR), and false positive rate (FPR). An ablation study confirmed the contribution of each module, highlighting the critical role of ensemble CNNs, CAF, and ViT in improving performance. Experimental results demonstrate that the proposed model outperforms conventional transfer learning models and existing state-of-the-art techniques, achieving 97.91% accuracy, along with significant improvements in TPR, TNR, and reduced FNR/FPR. The computational complexity, evaluated in terms of parameters, FLOPs, GPU memory, and inference time, indicates that the proposed model is more demanding than traditional CNNs. Nevertheless, the architecture strikes a practical balance between predictive accuracy and efficiency, making it suitable for real-world clinical applications. These findings underscore the potential of AI-powered hybrid models in expediting prostate cancer diagnosis and enabling timely intervention for improved patient outcomes.

prostate cancer detectionhistopathology image analysishybrid CNN-ViT modelcross-attention fusion
ArticleClosed2025

MHAOSL ‐Net: A Global Context‐Aware Attention Free Transformer Network With Orthogonal SoftMax Layer to Detect Subtypes of Acute Lymphoblastic Leukemia

International Journal of Imaging Systems and Technology · vol. 35 (5)

ABSTRACT Recent advancements in Deep Learning (DL) have enabled the development of Computer‐Aided Diagnosis (CAD) systems for detecting Acute Lymphoblastic Leukemia (ALL) and its subtypes. However, this field faces challenges, particularly due to limited annotated datasets and a lack of efficient modalities. To address these issues, we propose MHAOSL‐net, a novel hybrid DL model specifically designed for the accurate classification of B‐ALL, T‐ALL, and normal cells in blood smear images. The key contributions lie in the integration of four primary components: (1) lightweight MobileNetV2 for backbone feature extraction, (2) a Global Context Information Convolutional Block Attention Module (GCI‐CBAM) for refined local representation using contextual information, (3) an Attention‐Free Transformer (AFT) that captures global dependencies replacing traditional self‐attention, and (4) an Orthogonal SoftMax Layer (OSL) that improves class separability by enforcing orthogonality in the decision space. This unified architecture not only reduces computational overhead but also improves classification performance and generalizability. To the best of our knowledge, this is the first framework that combines an AFT with an OSL in the context of leukemia subtype detection. The performance analysis of the proposed 3‐class classification scheme has been assessed on two novel datasets, namely BBCI_B&T_ALL_2024 and heterogeneous datasets. The experimental results show that the proposed scheme provides better performance, with 99.52% accuracy, 99.36% average precision, and 99.36% average F1‐score on the BBCI_B&T_ALL_2024. Similarly, it achieves better performance with 99.55% accuracy, 99.40% average precision, and 99.40% average F1‐score on the heterogeneous dataset. The qualitative investigation using Gradient‐weighted Class Activation Mapping (Grad‐CAM) visualization also confirms the efficacy of the proposed model for detecting B‐ALL, T‐ALL, and normal cells. The comparative studies establish the superiority of the proposed scheme over other state‐of‐the‐art approaches. These findings indicate that MHAOSL‐Net offers a promising and efficient solution for reliable ALL subtype detection in clinical settings.

acute lymphoblastic leukemialeukemia subtype classificationB-cell acute lymphoblastic leukemiaT-cell acute lymphoblastic leukemia
Conference paperClosed2025

Novel Hybrid Deep Learning Model for Enhancing Skin Cancer Detection

IEEE International Conference on Image Processing, Applications and Systems (IPAS) · 1-8

Skin Cancer is the most serious form of cancer, often spreading to other parts of the body over time. Early and accurate identification of skin lesions can improve the treatment options and increase the probability of curing the disease before it progresses. However, automatic detection of skin cancer faces difficulties because of the imbalanced datasets, affected areas covered by hair or moles, and other visual obstructions. In recent years, Deep Learning (DL) techniques have been widely used to address these challenges. Despite advancements, achieving consistently high accuracy remains difficult. To tackle these challenges, the research proposes a novel hybrid DL model for efficient skin cancer detection from dermoscopic images. The proposed network consists of three key modules: feature extraction using the Xception network, feature enhancement through the Squeeze and Excitation network (SENet), and final classification using a transformer module. This combination of DL models effectively identifies SC. The proposed network is evaluated using benign and malignant dermoscopic images collected from the Kaggle website. Necessary preprocessing steps, such as resizing, grayscale conversion, hair removal, and data balancing, are applied. The proposed network is compared with popular DL networks such as MobileNet, Xception, and VGG-16. The experimental outcome demonstrates that the proposed network outperforms these models, achieving a higher accuracy, recall, precision, and F1 score of 96.83%, 97%, 96.67%, and 96.83%, respectively. The metrics value shows that the proposed network is promising and can be helpful for dermatologists in identifying skin cancer with minimal effort.

skin cancer detectiondermoscopic imageshybrid deep learning modelXception
OtherClosed2025

GAI and Deep Learning‐Based Medical Sensor Data Relationship Model for Health Informatics

— · 375-400

Disease diagnosis is a hot research area in Health Informatics (Healthcare) record data mining and an important step towards achieving generative intelligence (GAI) medical diagnosis. However, health perception data in Healthcare records come from diverse sources, with complex data structures and potential correlations between different types of data over wireless medical sensor networks. There is a challenge in how to integrate heterogeneous data during feature extraction and mining analysis. Only through comprehensive consideration of medical sensing data, personal constitution records, and inter-disease relationship data can relevant hidden features be mined to achieve more accurate diagnoses of various disease categories over wireless medical sensor networks. Therefore, based on the fusion of dynamic and static relationships in multisource health perception data, the disease diagnosis model (DSRF) first solves the heterogeneity problem of dynamic medical sensing data and static constitution records through a dynamic–static relationships fusion algorithm to explore their correlations. Then, it calculates the correlation matrix of multicategory diseases to extract inter-disease dependency relationships. Finally, based on the architecture of gated recurrent unit networks, it integrates various health perception data to accomplish a comprehensive analysis of multisource heterogeneous data. Experimental results on the MIMIC-III clinical dataset in the United States demonstrate that compared to mainstream models of the same type, this model can more accurately diagnose multiple disease categories jointly.

disease diagnosismedical sensor dataheterogeneous data fusionwireless medical sensor networks