Abeer Saber
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Abeer Saber has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Samar Elbedwehy
Department of Data Science, Faculty of Artifcial Intelligence, Kafrelsheikh University, Kafrelsheikh, 33511, Egypt
3 shared publicationsEsraa Hassan
Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh, 33511, Egypt
2 shared publicationsWael A. Awad
Computer Science Department, Faculty of Computers and Artificial Intelligence, Damietta University, Damietta, Egypt
2 shared publicationsAhmed Makram
Military Academy Air Defense College
1 shared publication- Balakrishnan Baranitharan
Department of Civil Engineering, Kalasalingam Academy of Research and Education (Deemed to Be University), Srivilliputhur, India
1 shared publication - Deema Mohammed Alsekait
Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 4 December 2025
- Published by Springer Nature in Research Square
A Robust Hybrid Framework for Image Security using Chaotic Maps, Steganography, and Convolutional Neural Networks
Safeguarding sensitive visual data against unauthorized access and disclosure is critical, making robust image encryption a paramount necessity for ensuring privacy. This paper presents a novel hybrid framework for secure image coding that significantly enhances both security and privacy by integrating chaotic map-based encryption with steganography. The proposed system utilizes a sophisticated two-phase data concealment and encryption process. Initially, the sensitive image is covertly embedded within a designated cover image using the Discrete Cosine Transform (DCT) domain to achieve high imperceptibility. The resulting transformed image is then subjected to a robust encryption mechanism. This mechanism features a dynamically generated chaotic map, which is constructed by integrating multiple chaotic systems, specifically leveraging a cosine-square logistic map to produce a variable key for initiating new chaotic sequences. These highly randomized sequences are subsequently applied to encrypt the DCT coefficients of the hidden image. Furthermore, to optimize the quality and fidelity of the decrypted image, Convolutional Neural Networks (CNNs), employing diverse filter sets, are incorporated into the decryption pipeline. The efficacy of this new approach is validated through comprehensive numerical experiments conducted on standard gray-scale images. Comparative analysis against established techniques, including circular mapping, S-box implementations, and the S-box combined with the Arnold Transform, demonstrates the superior performance of our methodology. The results confirm that the suggested hybrid scheme achieves higher security metrics, including lower correlation coefficients, and excellent information entropy, significantly outperforming existing image security solutions.
- 4 December 2025
- Published by Springer Nature in Research Square
Open AccessA Robust Hybrid Framework for Image Security using Chaotic Maps, Steganography, and Convolutional Neural Networks
Safeguarding sensitive visual data against unauthorized access and disclosure is critical, making robust image encryption a paramount necessity for ensuring privacy. This paper presents a novel hybrid framework for secure image coding that significantly enhances both security and privacy by integrating chaotic map-based encryption with steganography. The proposed system utilizes a sophisticated two-phase data concealment and encryption process. Initially, the sensitive image is covertly embedded within a designated cover image using the Discrete Cosine Transform (DCT) domain to achieve high imperceptibility. The resulting transformed image is then subjected to a robust encryption mechanism. This mechanism features a dynamically generated chaotic map, which is constructed by integrating multiple chaotic systems, specifically leveraging a cosine-square logistic map to produce a variable key for initiating new chaotic sequences. These highly randomized sequences are subsequently applied to encrypt the DCT coefficients of the hidden image. Furthermore, to optimize the quality and fidelity of the decrypted image, Convolutional Neural Networks (CNNs), employing diverse filter sets, are incorporated into the decryption pipeline. The efficacy of this new approach is validated through comprehensive numerical experiments conducted on standard gray-scale images. Comparative analysis against established techniques, including circular mapping, S-box implementations, and the S-box combined with the Arnold Transform, demonstrates the superior performance of our methodology. The results confirm that the suggested hybrid scheme achieves higher security metrics, including lower correlation coefficients, and excellent information entropy, significantly outperforming existing image security solutions.
- Open Access
- 25 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 27065
A novel approach for breast cancer detection using a Nesterov accelerated adam optimizer with an attention mechanism
Image-based automatic breast tumor detection has become a significant research focus, driven by recent advancements in machine learning (ML) algorithms. Traditional disease detection methods often involve manual feature extraction from images, a process requiring extensive expertise from specialists and pathologists. This labor-intensive approach is not only time-consuming but also impractical for widespread application. However, advancements in digital technologies and computer vision have enabled convolutional neural networks (CNNs) to learn features automatically, thereby overcoming these challenges. This paper presents a deep neural network model based on the MobileNet-V2 architecture, enhanced with a convolutional block attention mechanism for identifying tumor types in ultrasound images. The attention module improves the MobileNet-V2 model’s performance by highlighting disease-affected areas within the images. The proposed model refines features extracted by MobileNet-V2 using the Nesterov-accelerated Adaptive Moment Estimation (Nadam) optimizer. This integration enhances convergence and stability, leading to improved classification accuracy. The proposed approach was evaluated on the BUSI ultrasound image dataset. Experimental results demonstrated strong performance, achieving an accuracy of 99.1%, sensitivity of 99.7%, specificity of 99.5%, precision of 97.7%, and an area under the curve (AUC) of 1.0 using an 80–20 data split. Additionally, under 10-fold cross-validation, the model achieved an accuracy of 98.7%, sensitivity of 99.1%, specificity of 98.3%, precision of 98.4%, F1-score of 98.04%, and an AUC of 0.99.
- 25 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 27065
Open AccessA novel approach for breast cancer detection using a Nesterov accelerated adam optimizer with an attention mechanism
Image-based automatic breast tumor detection has become a significant research focus, driven by recent advancements in machine learning (ML) algorithms. Traditional disease detection methods often involve manual feature extraction from images, a process requiring extensive expertise from specialists and pathologists. This labor-intensive approach is not only time-consuming but also impractical for widespread application. However, advancements in digital technologies and computer vision have enabled convolutional neural networks (CNNs) to learn features automatically, thereby overcoming these challenges. This paper presents a deep neural network model based on the MobileNet-V2 architecture, enhanced with a convolutional block attention mechanism for identifying tumor types in ultrasound images. The attention module improves the MobileNet-V2 model’s performance by highlighting disease-affected areas within the images. The proposed model refines features extracted by MobileNet-V2 using the Nesterov-accelerated Adaptive Moment Estimation (Nadam) optimizer. This integration enhances convergence and stability, leading to improved classification accuracy. The proposed approach was evaluated on the BUSI ultrasound image dataset. Experimental results demonstrated strong performance, achieving an accuracy of 99.1%, sensitivity of 99.7%, specificity of 99.5%, precision of 97.7%, and an area under the curve (AUC) of 1.0 using an 80–20 data split. Additionally, under 10-fold cross-validation, the model achieved an accuracy of 98.7%, sensitivity of 99.1%, specificity of 98.3%, precision of 98.4%, F1-score of 98.04%, and an AUC of 0.99.
- Top Cited PapersOpen Access
- 11 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-15
Leveraging ensemble convolutional neural networks and metaheuristic strategies for advanced kidney disease screening and classification
To address the public health issue of renal failure and the global shortage of nephrologists, an AI-based system has been developed to automatically identify kidney diseases. Recent advancements in machine learning, deep learning (DL), and artificial intelligence (AI) have unlocked new possibilities in healthcare. By harnessing these technologies, we can analyze data to gain insights into symptoms and patterns, ultimately facilitating remote patient care. To create an AI-based diagnosis system for kidney disease, this paper focused on the three major categories of kidney diseases: stones, cysts, and tumors, which were collected and annotated on 12,446 computed tomography (CT) whole abdomen and urogram images. To effectively aid in the automatic identification and diagnosis of kidney diseases, a novel DL model built on the transfer-learning (TL) technology is implemented in this work. DL models are designed to focus on problems, whereas TL uses the knowledge acquired while resolving one issue to another pertinent issue. The proposed model combines multiple DL models to improve overall performance by leveraging the strengths of different architectures, ensembles can enhance accuracy, robustness, and generalization. It enhances the features extracted from MobileNet-V2, ResNet50, and EfficientNet-B0 networks using metaheuristic algorithms and bidirectional long-short-term memory (Bi-LSTM) from the CT image. MobileNetV2, ResNet50, and EfficientNet-B0 hyperparameters have been optimized using a modified grey wolf optimization (GWO) approach for better performance. The suggested model’s performance has been measured using five assessment metrics: accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) and achieved 99.85% accuracy, 99.8% sensitivity, 99.3% specificity, 98.1% precision, and 1.0 AUC.
- 11 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-15
Top Cited PapersOpen AccessLeveraging ensemble convolutional neural networks and metaheuristic strategies for advanced kidney disease screening and classification
To address the public health issue of renal failure and the global shortage of nephrologists, an AI-based system has been developed to automatically identify kidney diseases. Recent advancements in machine learning, deep learning (DL), and artificial intelligence (AI) have unlocked new possibilities in healthcare. By harnessing these technologies, we can analyze data to gain insights into symptoms and patterns, ultimately facilitating remote patient care. To create an AI-based diagnosis system for kidney disease, this paper focused on the three major categories of kidney diseases: stones, cysts, and tumors, which were collected and annotated on 12,446 computed tomography (CT) whole abdomen and urogram images. To effectively aid in the automatic identification and diagnosis of kidney diseases, a novel DL model built on the transfer-learning (TL) technology is implemented in this work. DL models are designed to focus on problems, whereas TL uses the knowledge acquired while resolving one issue to another pertinent issue. The proposed model combines multiple DL models to improve overall performance by leveraging the strengths of different architectures, ensembles can enhance accuracy, robustness, and generalization. It enhances the features extracted from MobileNet-V2, ResNet50, and EfficientNet-B0 networks using metaheuristic algorithms and bidirectional long-short-term memory (Bi-LSTM) from the CT image. MobileNetV2, ResNet50, and EfficientNet-B0 hyperparameters have been optimized using a modified grey wolf optimization (GWO) approach for better performance. The suggested model’s performance has been measured using five assessment metrics: accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) and achieved 99.85% accuracy, 99.8% sensitivity, 99.3% specificity, 98.1% precision, and 1.0 AUC.
- Open Access
- 27 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (6) , 4881-4894
An optimized ensemble model based on meta-heuristic algorithms for effective detection and classification of breast tumors
One of the most common cancers among women worldwide is breast cancer (BC), and early diagnosis can save lives. Early detection of BC increases the likelihood of a successful outcome by enabling treatment to start sooner. Even in areas without access to a specialist physician, machine learning (ML) aids in early BC detection. The medical imaging community is becoming more interested in using ML, and deep learning (DL) to increase the accuracy of cancer screening. Many disease-related data are sparse. However, for DL models to perform well, a large amount of data is required. Because of this, the DL models that are currently in use on medical images are not as effective as they could be. Convolutional neural network (CNN) models have recently gained popularity in the medical industry, and they perform admirably in terms of high performance and robustness at image classification. The proposed method classifies data using ensemble pre-trained models such as the dense convolutional network (DenseNet)-121 and EfficientNet-B5 feature extractor networks, as well as the support vector machine for classification. Using a modified meta-heuristic optimizer, the selected pre-trained CNN hyperparameters were optimized to improve the performance. The experimental results for the presented model on the INbreast dataset show that the EfficientNet-B5 model is effective for BC classification, with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) values of 99.9%, 99.9%, 99.8%, 99.1%, 1.0, respectively.
- 27 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (6) , 4881-4894
Open AccessAn optimized ensemble model based on meta-heuristic algorithms for effective detection and classification of breast tumors
One of the most common cancers among women worldwide is breast cancer (BC), and early diagnosis can save lives. Early detection of BC increases the likelihood of a successful outcome by enabling treatment to start sooner. Even in areas without access to a specialist physician, machine learning (ML) aids in early BC detection. The medical imaging community is becoming more interested in using ML, and deep learning (DL) to increase the accuracy of cancer screening. Many disease-related data are sparse. However, for DL models to perform well, a large amount of data is required. Because of this, the DL models that are currently in use on medical images are not as effective as they could be. Convolutional neural network (CNN) models have recently gained popularity in the medical industry, and they perform admirably in terms of high performance and robustness at image classification. The proposed method classifies data using ensemble pre-trained models such as the dense convolutional network (DenseNet)-121 and EfficientNet-B5 feature extractor networks, as well as the support vector machine for classification. Using a modified meta-heuristic optimizer, the selected pre-trained CNN hyperparameters were optimized to improve the performance. The experimental results for the presented model on the INbreast dataset show that the EfficientNet-B5 model is effective for BC classification, with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) values of 99.9%, 99.9%, 99.8%, 99.1%, 1.0, respectively.
- Open Access
- 14 February 2024
- Published by Springer Nature in Research Square
A novel multi class disease detection of chest x-ray images using deep learning with pre trained transfer learning models for medical imaging applications
Images from chest X-rays (CXR) are thought to help observe and research various kinds of pulmonary illnesses. Several works were suggested in the literature for recognizing unique lung diseases, and only a few studies were focused on developing a model to identify joint classes of lung diseases. A patient with a negative diagnosis for one condition may have the other disease, and vice versa. However, since many illnesses are lung-related, a patient can have multiple illnesses simultaneously. This paper proposes a deep learning (DL)-based pre-trained transfer learning (TL) model for effectively detecting and classifying the multiclass diseases of lung CXR images. The system involves five phases: preprocessing, dataset balancing, feature learning, feature selection, and multiclass classification. Firstly, the CXR images are preprocessed by performing filtering, contrast enhancement, and data augmentation. After that, the dataset balancing is performed using the Synthetic Minority Oversampling Technique (SMOTE). Next, the features are learned using a spatial and channel-attention-based Xception Network (SCAXN). The optimal features are selected using nonlinear decreasing inertia weight-based rock hyraxes swarm optimization (NIWRHSO). Finally, the multiclass classification uses a soft sign-incorporated bidirectional gated recurrent unit (SBIGRU). Two public datasets, COVID-19 Radiography (C19RY) and Tuberculosis CXR (TB-CXR), have been obtained from Kaggle, and the outcomes confirmed that the proposed system attains superior results to prevailing methods.
- 14 February 2024
- Published by Springer Nature in Research Square
Open AccessA novel multi class disease detection of chest x-ray images using deep learning with pre trained transfer learning models for medical imaging applications
Images from chest X-rays (CXR) are thought to help observe and research various kinds of pulmonary illnesses. Several works were suggested in the literature for recognizing unique lung diseases, and only a few studies were focused on developing a model to identify joint classes of lung diseases. A patient with a negative diagnosis for one condition may have the other disease, and vice versa. However, since many illnesses are lung-related, a patient can have multiple illnesses simultaneously. This paper proposes a deep learning (DL)-based pre-trained transfer learning (TL) model for effectively detecting and classifying the multiclass diseases of lung CXR images. The system involves five phases: preprocessing, dataset balancing, feature learning, feature selection, and multiclass classification. Firstly, the CXR images are preprocessed by performing filtering, contrast enhancement, and data augmentation. After that, the dataset balancing is performed using the Synthetic Minority Oversampling Technique (SMOTE). Next, the features are learned using a spatial and channel-attention-based Xception Network (SCAXN). The optimal features are selected using nonlinear decreasing inertia weight-based rock hyraxes swarm optimization (NIWRHSO). Finally, the multiclass classification uses a soft sign-incorporated bidirectional gated recurrent unit (SBIGRU). Two public datasets, COVID-19 Radiography (C19RY) and Tuberculosis CXR (TB-CXR), have been obtained from Kaggle, and the outcomes confirmed that the proposed system attains superior results to prevailing methods.