Abou-Bakr Mohammed Youssef
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Abou-Bakr Mohammed Youssef has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Abdallah Abdelkader Hussein
Histopathology Dept., Kobri El-Koba Medical Complex, Egyptian Armed Forces, Cairo, Egypt
1 shared publication - Ahmed Elbialy
Systems and Biomedical Engineering, Cairo University; and Shorouk Academy
1 shared publication - Ahmed Hisham Kandil
Cairo University
1 shared publication Ahmed Khandil
Systems and Biomedical Engineering, Cairo University
1 shared publication- Ahmed Mohammed El-Bialy
Cairo University
1 shared publication - Am Ahmed
Department of Mathematics, Faculty of Science, Al-Azhar University, Nasr City 11884, Egypt
1 shared publication
Latest Publications
- Open Access
- 3 February 2025
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 11 (1) , 143-156
A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
To advance the automated interpretation of lung ultrasound (LUS) data, multiple deep learning (DL) models have been introduced to identify LUS patterns for differentiating COVID-19, Pneumonia, and Normal cases. While these models have generally yielded promising outcomes, they have encountered challenges in accurately classifying each pattern across diverse cases. Therefore, this study introduces an ensemble framework that leverages multiple classification models, optimizing their contributions to the final prediction through a majority voting mechanism. After training seven different classification models, the three models with the highest accuracies were selected. The ensemble incorporates these top-performing models: EfficientNetV2-B0, EfficientNetV2-B2, and EfficientNetV2-B3, and utilizes this framework to classify patterns in LUS images. Compared to individual model performance, the ensemble approach significantly enhances classification accuracy, achieving an accuracy of 99.25% and an F1-score of 99%. In contrast, the standalone models attained accuracies of 97.8%, 97.6%, and 98.1%, with F1-score of approximately 98%. This research highlights the potential of ensemble learning for improving the accuracy and robustness of automated LUS analysis, offering a practical and scalable solution for real-world medical diagnostics. By combining the strengths of multiple models, the proposed framework paves the way for more reliable and efficient tools to assist clinicians in diagnosing lung diseases.
- 3 February 2025
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 11 (1) , 143-156
Open AccessA deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
To advance the automated interpretation of lung ultrasound (LUS) data, multiple deep learning (DL) models have been introduced to identify LUS patterns for differentiating COVID-19, Pneumonia, and Normal cases. While these models have generally yielded promising outcomes, they have encountered challenges in accurately classifying each pattern across diverse cases. Therefore, this study introduces an ensemble framework that leverages multiple classification models, optimizing their contributions to the final prediction through a majority voting mechanism. After training seven different classification models, the three models with the highest accuracies were selected. The ensemble incorporates these top-performing models: EfficientNetV2-B0, EfficientNetV2-B2, and EfficientNetV2-B3, and utilizes this framework to classify patterns in LUS images. Compared to individual model performance, the ensemble approach significantly enhances classification accuracy, achieving an accuracy of 99.25% and an F1-score of 99%. In contrast, the standalone models attained accuracies of 97.8%, 97.6%, and 98.1%, with F1-score of approximately 98%. This research highlights the potential of ensemble learning for improving the accuracy and robustness of automated LUS analysis, offering a practical and scalable solution for real-world medical diagnostics. By combining the strengths of multiple models, the proposed framework paves the way for more reliable and efficient tools to assist clinicians in diagnosing lung diseases.
- Open Access
- 1 September 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Advances in Applied Sciences
- Vol. 13 (3) , 566-578
A model for classifying breast masses in ultrasound images
The most frequent type of cancer among women is breast cancer. Artificial intelligence (AI) researchers are developing automated systems to assist in the detection and classification of breast cancer. This study explores machine learning (ML) and deep learning (DL) as two AI methods for identifying benign and malignant breast tumors in ultrasound images. The investigation assesses the performance of various computer-aided detection and diagnosis (CAD) systems, which utilize either handcrafted features or deep features extracted from DL models. Furthermore, three models for CAD deep learning-based systems were implemented using convolutional neural networks (CNN), convolutional autoencoders (CAE), and deep features with CNN models, and compared with three traditional ML models based on handcrafted (texture) features. The results indicate that the deep features of the CNN model are promising, achieving a mean accuracy of 95% with a standard deviation of 1.1%.
- 1 September 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Advances in Applied Sciences
- Vol. 13 (3) , 566-578
Open AccessA model for classifying breast masses in ultrasound images
The most frequent type of cancer among women is breast cancer. Artificial intelligence (AI) researchers are developing automated systems to assist in the detection and classification of breast cancer. This study explores machine learning (ML) and deep learning (DL) as two AI methods for identifying benign and malignant breast tumors in ultrasound images. The investigation assesses the performance of various computer-aided detection and diagnosis (CAD) systems, which utilize either handcrafted features or deep features extracted from DL models. Furthermore, three models for CAD deep learning-based systems were implemented using convolutional neural networks (CNN), convolutional autoencoders (CAE), and deep features with CNN models, and compared with three traditional ML models based on handcrafted (texture) features. The results indicate that the deep features of the CNN model are promising, achieving a mean accuracy of 95% with a standard deviation of 1.1%.
- 22 September 2023
- Published by Elsevier in Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy
- Vol. 305, 123363
Custom Hyperspectral Imaging System Reveals Unique Spectral Signatures of Heart, Kidney, and Liver Tissues
- 22 September 2023
- Published by Elsevier in Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy
- Vol. 305, 123363
Custom Hyperspectral Imaging System Reveals Unique Spectral Signatures of Heart, Kidney, and Liver Tissues
- Open Access
- 1 October 2013
- Published by Egyptian Knowledge Bank in Journal of the Egyptian Mathematical Society
- Vol. 21 (3) , 248-253
A solution form of a class of higher-order rational difference equations
We obtain in this paper the expressions of solutions of the following class of difference equationsxn+1=xn-2k+1±1±Πi=1kxn-2i+1,n=0,1,2,…with conditions posed on the initial values x−j, j=0, 1, 2,…,2k−1, where k∈{1,2,…}
- 1 October 2013
- Published by Egyptian Knowledge Bank in Journal of the Egyptian Mathematical Society
- Vol. 21 (3) , 248-253
Open AccessA solution form of a class of higher-order rational difference equations
We obtain in this paper the expressions of solutions of the following class of difference equationsxn+1=xn-2k+1±1±Πi=1kxn-2i+1,n=0,1,2,…with conditions posed on the initial values x−j, j=0, 1, 2,…,2k−1, where k∈{1,2,…}
- 1 March 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-12
Novel Multi-Tensor Estimation for High-Resolution Diffusion Tensor Magnetic Resonance Imaging
The estimation of diffusion tensors in diffusion tensor imaging (DTI) is based on the assumption that each voxel is homogeneous and can be represented by a single tensor. As a result, estimation errors arise particularly in voxels with partial voluming of white matter or gray matter with cerebrospinal fluid (CSF) and voxels where fibers cross. Several authors have explored the possibility of solving for multiple tensors. Several authors analyzed the problem from the point of view of the number of unknowns and concluded that the solution is rather difficult due to the large number of unknowns and the nonlinearity of the equations. However, their approach was only helpful in eliminating some of the sources of artifacts in the DTI data but offered only a qualitative description of the model components. We implemented three strategies gradient, differentiation and exhaustive algorithms to solve and compare between their estimations at various conditions of signal to noise ratios (SNR)
- 1 March 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-12
Novel Multi-Tensor Estimation for High-Resolution Diffusion Tensor Magnetic Resonance Imaging
The estimation of diffusion tensors in diffusion tensor imaging (DTI) is based on the assumption that each voxel is homogeneous and can be represented by a single tensor. As a result, estimation errors arise particularly in voxels with partial voluming of white matter or gray matter with cerebrospinal fluid (CSF) and voxels where fibers cross. Several authors have explored the possibility of solving for multiple tensors. Several authors analyzed the problem from the point of view of the number of unknowns and concluded that the solution is rather difficult due to the large number of unknowns and the nonlinearity of the equations. However, their approach was only helpful in eliminating some of the sources of artifacts in the DTI data but offered only a qualitative description of the model components. We implemented three strategies gradient, differentiation and exhaustive algorithms to solve and compare between their estimations at various conditions of signal to noise ratios (SNR)
- 7 December 1995
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 31 (25) , 2165-2166
Linear approximation of injective s-boxes
Nonlinearity is a crucial requirement for the substitution boxes in secure block ciphers. The authors derive an estimate for the expected nonlinearity of a randomly selected injective substitution box.
- 7 December 1995
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 31 (25) , 2165-2166
Linear approximation of injective s-boxes
Nonlinearity is a crucial requirement for the substitution boxes in secure block ciphers. The authors derive an estimate for the expected nonlinearity of a randomly selected injective substitution box.