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.

OtherClosed20251citation

Multimodal Imaging: Combining Molecular and Optical Approaches

— · 97-121

The number of mitoses is a key indicator of breast cancer malignancy, crucial for diagnosis, treatment, and prognosis. Currently, pathologists manually count mitotic cells in slides, a subjective and time-consuming process. This chapter introduces a two-stage method for automating mitosis detection in breast pathology images using multimodal imaging and molecular and optical approaches. First, convolutional neural networks with deep supervision and attention mechanisms identify candidate mitotic regions, enhanced by molecular and optical approaches for accuracy. Next, these regions undergo validation using a radial basis function (RBF) network, leveraging multimodal imaging and molecular insights to improve recognition. The method addresses the morphological diversity of mitotic cells by determining RBF centers based on “local response” characteristics. This combination of molecular and optical approaches with multimodal imaging effectively captures the structural complexity of mitotic cells. Evaluations on weakly labeled datasets ICPR 2014 and AMIDA 2013 show the proposed model achieves optimal F -scores, improving by 5.4% and 3.0% compared to alternatives. These results underscore the method's effectiveness, emphasizing the importance of advanced imaging and molecular techniques in enhancing mitosis detection for breast cancer pathology.

mitosis detectionbreast cancermultimodal imagingconvolutional neural networks
OtherClosed2025

Navigating the Generative AI Project Ecosystem with a Focus on Addressing Data Architecture Complexities and Strategic Model Selection for Optimal Outcomes

— · 67-91

This article delves into the generative artificial intelligence (AI) project's complex ecosystem, with an emphasis on data architecture and model selection for optimal outcomes. Integrating generative AI into diverse academic and commercial domains brings unique challenges and opportunities. Navigating the generative AI project's environment is critical for success. The data architecture is complicated, so select your models wisely. This study seeks to provide complete guidelines to help manage these areas and ensure project success. Our technique consists of two fundamental components: a detailed data architecture research project for generative artificial intelligence is the first step toward identifying common problems and developing solutions. The next step is to analyze and contrast many generative models to see which ones work best for certain projects based on complexity, scalability, and ethics. Researchers verified solutions via case studies and expert talks. The findings highlight the need for a well-structured data infrastructure to boost generative AI endeavors. Studies have shown that carefully selecting generative models, taking into consideration project needs and constraints, results in better and more ethical solutions. To traverse the generative artificial intelligence project ecosystem, a comprehensive strategy must encompass ethical and technical data architecture construction as well as model selection. This study underlines the importance of understanding these issues and outlines a path forward for practitioners and researchers seeking to improve generational AI initiatives. To keep up with the fast progress of generative artificial intelligence, the study suggests further research and development in this area.

generative AIdata architecturemodel selectiondata infrastructure
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
OtherOpen (repository)2023

Molecular and Phytochemical features of three Saudi Arabian desert truffles and their extract silver nanoparticles associated with their antimicrobial activities against selected pathogens

Zenodo (CERN European Organization for Nuclear Research)

Figure S1: The Polymerase Chain Reaction (PCR) showed expressed rRNA using ITS1 and ITS4 primers, yielded fragments between 350 to 880 bp long. Lane 1; Table S1: DNA sequence of three thruffle samples with 100% identity in NCBI GenBank database.; Figure S2:Three different truffles were used to prepare bio-nano silver particles: A. Zubaidi (beige colour), B. Khlasi (large size brown colour), C. Khlasi (small size brown colour); Figure S3: Sample (1): (A) EDX spectrum of biosynthesized silver nanoparticles (B) distribution of silver in elemental mapping; Figure S4: Sample (2): (A) EDX spectrum of biosynthesized silver nanoparticles (B) distribution of silver in elemental mapping; Figure S5: Sample (3): (A) EDX spectrum of biosynthesized silver nanopar-ticles (B) distribution of silver in elemental mapping; Table S2: FT-IR analysis of truffle samples nanoparticles; Figure S6: FTIR pattern of Biogenic silver nanoparticles; Figure S7: FTIR pattern of Biogenic AgNPs; Figure S8. Antimicrobial activity of prepared AgNPs from truffles against several clinical microbes.

desert trufflesantimicrobial activityphytochemical screeningelemental mapping