Akram Bennour

Dr. Akram Bennour

Université Larbi Tébessi, Tébessa, Algeria
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
EYElbachir Mohammed Yahiaoui
Elbachir Mohammed Yahiaoui
MDMakhlouf DERDOUR
Makhlouf DERDOUR
RARawad Prof. Dr. Rawad Abdulghafor
Rawad Prof. Dr. Rawad Abdulghafor
Sherzod TuraevSherzod Turaev
Sherzod Turaev
MGMohamed Gasmi
Mohamed Gasmi
Mohammed Al-SaremMohammed Al-Sarem
Mohammed Al-Sarem
Background and Objectives: Brain tumors are complex diseases that require careful diagnosis and treatment. A minor error in the diagnosis may easily lead to significant consequences. Thus, one must place a premium on accurately identifying brain tumors. However, deep learning (DL) models often face challenges in obtaining sufficient medical imaging data due to legal, privacy, and technical barriers hindering data sharing between institutions. This study aims to implement a federated learning (FL) approach with privacy-preserving techniques (PPTs) directed toward segmenting brain tumor lesions in a distributed and privacy-aware manner.Methods: The suggested approach employs a model of 3D U-Net, which is trained using federated learning on the BraTS 2020 dataset. PPTs, such as differential privacy, are included to ensure data confidentiality while managing privacy and heterogeneity challenges with minimal communication overhead. The efficiency of the model is measured in terms of Dice similarity coefficients (DSCs) and 95% Hausdorff distances (HD95) concerning the target areas concerned by tumors, which include the whole tumor (WT), tumor core (TC), and enhancing tumor core (ET). Results: In the validation phase, the partial federated model achieved DSCs of 86.1%, 83.3%, and 79.8%, corresponding to 95% values of 25.3 mm, 8.61 mm, and 9.16 mm for WT, TC, and ET, respectively. On the final test set, the model demonstrated improved performance, achieving DSCs of 89.85%, 87.55%, and 86.6%, with HD95 values of 22.95 mm, 8.68 mm, and 8.32 mm for WT, TC, and ET, respectively, which indicates the effectiveness of the segmentation approach, and its privacy preservation.Conclusion: This study presents a highly competitive, collaborative federated learning model with PPTs that can successfully segment brain tumor lesions without compromising patient data confidentiality. Future work will improve model generalizability and extend the framework to other medical imaging tasks.

6 December 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
YHYousra Hedhoud
Yousra Hedhoud
TMTahar MEKHAZNIA
Tahar MEKHAZNIA
Akram BennourAkram Bennour
Akram Bennour
MAMohamed Amroune
Mohamed Amroune
NKNeesrin Ali Kurdi
Neesrin Ali Kurdi
Mohammed Al-SaremMohammed Al-Sarem
Mohammed Al-Sarem
Background/Objectives: Chest disease identification for Tuberculosis and Pneumonia diseases presents diagnostic challenges due to overlapping radiographic features and the limited availability of expert radiologists, especially in developing countries. The present study aims to address these challenges by developing a Computer-Aided Diagnosis (CAD) system to provide consistent and objective analyses of chest X-ray images, thereby reducing potential human error. By leveraging the complementary strengths of convolutional neural networks (CNNs) and vision transformers (ViTs), we propose a hybrid model for the accurate detection of Tuberculosis and for distinguishing between Tuberculosis and Pneumonia. Methods: We designed a two-step hybrid model that integrates the ResNet-50 CNN with the ViT-b16 architecture. It uses the transfer learning on datasets from Guangzhou Women’s and Children’s Medical Center for Pneumonia cases and datasets from Qatar and Dhaka (Bangladesh) universities for Tuberculosis cases. CNNs capture hierarchical structures in images, while ViTs, with their self-attention mechanisms, excel at identifying relationships between features. Combining these approaches enhances the model’s performance on binary and multi-class classification tasks. Results: Our hybrid CNN-ViT model achieved a binary classification accuracy of 98.97% for Tuberculosis detection. For multi-class classification, distinguishing between Tuberculosis, viral Pneumonia, and bacterial Pneumonia, the model achieved an accuracy of 96.18%. These results underscore the model’s potential in improving diagnostic accuracy and reliability for chest disease classification based on X-ray images. Conclusions: The proposed hybrid CNN-ViT model demonstrates substantial potential in advancing the accuracy and robustness of CAD systems for chest disease diagnosis. By integrating CNN and ViT architectures, our approach enhances the diagnostic precision, which may help to alleviate the burden on healthcare systems in resource-limited settings and improve patient outcomes in chest disease diagnosis.

1 August 2019 in Forensic Science International
Verified
Journal Article
Closed access
Akram BennourAkram Bennour
Akram Bennour
CDChawki Djeddi
Chawki Djeddi
AGAbdeljalil Gattal
Abdeljalil Gattal
ISImran Siddiqi
Imran Siddiqi
TMTahar MEKHAZNIA
Tahar MEKHAZNIA

5 July 2025 in Technology and Disability
Verified
Journal Article
Open access
Cristina DumitruCristina Dumitru
Cristina Dumitru
GAGhaida Muttashar Abdulsahib
Ghaida Muttashar Abdulsahib
Osamah IbrahimOsamah Ibrahim
Osamah Ibrahim
Akram BennourAkram Bennour
Akram Bennour
Artificial intelligence has the potential to significantly enhance accessibility, inclusivity, and academic performance for students with disabilities. This review investigates how AI-driven assistive technologies can support students with disabilities in higher education. Using an integrative review methodology, this study synthesizes peer-reviewed research published between 2020 and 2024 to assess the impact of AI-powered assistive technologies on the academic performance, engagement, and accessibility of students with disabilities in higher education. Thematic synthesis was used to categorize and analyze the data from 27 papers, identifying five major themes: personalized learning, the benefits of AI-driven assistive technology, adoption challenges, institutional barriers, and best practices for AI implementation. The analysis identifies gaps in the current research, including the insufficient evaluation of underrepresented disabilities and the ethical considerations regarding AI usage.

26 April 2024 in Heliyon
Verified
Journal Article
Open access
Akram BennourAkram Bennour
Akram Bennour
Najib Ben AounNajib Ben Aoun
Najib Ben Aoun
Osamah IbrahimOsamah Ibrahim
Osamah Ibrahim
FGFahad Ghabban
Fahad Ghabban
Wing-Keung WongWing-Keung Wong
Wing-Keung Wong
SASameer Algburi
Sameer Algburi
Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. For this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named “CovCXR-Net”, identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named “MDCXR3-Net”, identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named “MDCXR4-Net”, is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09 %, 97.74 %, and 90,37 % respectively with three benchmarks.

24 December 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
SBSabrina Benredjem
Sabrina Benredjem
TMTahar MEKHAZNIA
Tahar MEKHAZNIA
RARawad Prof. Dr. Rawad Abdulghafor
Rawad Prof. Dr. Rawad Abdulghafor
Sherzod TuraevSherzod Turaev
Sherzod Turaev
Akram BennourAkram Bennour
Akram Bennour
Mohammed Al-SaremMohammed Al-Sarem
Mohammed Al-Sarem
Background: Neurodegenerative diseases (NGD) encompass a range of progressive neurological conditions, such as Alzheimer’s disease (AD) and Parkinson’s disease (PD), characterised by the gradual deterioration of neuronal structure and function. This degeneration manifests as cognitive decline, movement impairment, and dementia. Our focus in this investigation is on PD, a neurodegenerative disorder characterized by the loss of dopamine-producing neurons in the brain, leading to motor disturbances. Early detection of PD is paramount for enhancing quality of life through timely intervention and tailored treatment. However, the subtle nature of initial symptoms, like slow movements, tremors, muscle rigidity, and psychological changes, often reduce daily task performance and complicate early diagnosis. Method: To assist medical professionals in timely diagnosis of PD, we introduce a cutting-edge Multimodal Diagnosis framework (PMMD). Based on deep learning techniques, the PMMD framework integrates imaging, handwriting, drawing, and clinical data to accurately detect PD. Notably, it incorporates cross-modal attention, a methodology previously unexplored within the area, which facilitates the modelling of interactions between different data modalities. Results: The proposed method exhibited an accuracy of 96% on the independent tests set. Comparative analysis against state-of-the-art models, along with an in-depth exploration of attention mechanisms, highlights the efficacy of PMMD in PD classification. Conclusions: The obtained results highlight exciting new prospects for the use of handwriting as a biomarker, along with other information, for optimal model performance. PMMD’s success in integrating diverse data sources through cross-modal attention underscores its potential as a robust diagnostic decision support tool for accurately diagnosing PD.