Abdel-Nasser Sharkawy
Qena University

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

A Systematic Review of Machine Learning and Deep Learning Approaches in MRI-Based Brain Tumour Analysis, Detection and Classification Hanan M. Omran; Khalil Ibrahim; Gamal T. Abdel-Jaber; Abdel-Nasser Sharkawy
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 1 (2026): February
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i1.14673

Abstract

A brain tumour develops when abnormal cell growth happens in or near the brain. These tumours can grow slowly and not be cancerous, or they can grow quickly and spread, which is known as malignancy. Brain tumours put pressure on the surrounding brain tissues, causing symptoms like memory loss, migraines, movement dysfunction, and vision impairment. Brain tumours are often divided into two groups: primary tumours, which start in the brain, and secondary tumours, which are caused by cancers that spread to other regions of the body. Although brain tumours provide a significant medical challenge, patient outcomes have improved thanks to recent advancements in diagnostic and treatment methods. Because of its better soft-tissue contrast and noninvasive nature, magnetic resonance imaging (MRI) is one of the most important medical imaging modalities for the early identification and precise localization of brain tumours. Clinical practice also makes use of other imaging methods such as PET-CT and functional MRI (fMRI). Artificial intelligence and deep learning techniques have demonstrated significant promise in automated brain cancer analysis in recent years. These methods enable precise cancer diagnosis, classification, and segmentation by identifying intricate patterns from MRI data that are challenging to recognize through manual examination. A thorough study of current deep learning and machine learning techniques for MRI-based brain tumour analysis is provided in this paper. The current thorough literature search includes papers released between 2019 and 2024. 67 pertinent articles are chosen for in-depth analysis after predetermined inclusion and exclusion criteria is used. Many of these studies make use of publicly accessible datasets like Figshare, TCIA, and BraTS. The results show that deep learning models frequently outperform traditional machine learning methods in terms of accuracy and robustness, especially convolutional neural network-based designs. However, there are still issues with clinical generalisation, model interpretability, and data heterogeneity.
Improved DeepFake Image Generation Using StyleGAN2-ADA with Real-Time Personal Image Projection Ali A. Abed; Doaa Alaa Talib; Abdel-Nasser Sharkawy
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14659

Abstract

This paper presents an improved approach for DeepFake image generation using StyleGAN2-ADA framework. The system is designed to generate high-quality synthetic facial images from a limited dataset of personal photos in real time. By leveraging the Adaptive Discriminator Augmentation (ADA) mechanism, the training process is stabilized without modifying the network architecture, enabling robust image generation even with small-scale datasets. Real-time image capturing and projection techniques are integrated to enhance personalization and identity consistency. The experimental results demonstrate that the proposed method achieve a very high generation performance, significantly outperforming the baseline StyleGAN2 model. The proposed system using StyleGAN2-ADA achieves 99.1% identity similarity, a low Fréchet Inception Distance (FID) of 8.4, and less than 40 ms latency per generated frame. This approach provides a practical solution for dataset augmentation and supports ethical applications in animation, digital avatars, and AI-driven simulations.