Emre Altinkaya
Emre Altinkaya has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Burhan Barakli
Sakarya University
2 shared publications - Elif Gündoğdu
Eskişehir Osmangazi University, Turkey
1 shared publication - Elif Zoroğlu Altinkaya
Eskişehir Osmangazi Üniversitesi
1 shared publication - Emre Emekli
Faculty of Medicine, Department of Radiology, Eskisehir Osmangazi University, Eskisehir, Turkey
1 shared publication
Latest Publications
- Open Access
- 15 January 2026
- Published by Termedia Sp. z.o.o. in Polish Journal of Radiology
- Vol. 91 (1) , e1-e10
Chronic liver disease detection using deep convolutional neural networks with MRI data: a deep learning approach
Purpose: Chronic liver disease (CLD) is a significant health issue, and detection is crucial for effective treatment. This study aimed to develop a deep learning based convolutional neural network (DeepCNN) to differentiate CLD from non-CLD patients using magnetic resonance imaging (MRI) images without segmentation, enhancing diagnostic accuracy and supporting timely intervention. Material and methods: A retrospective study was conducted using MRI data from 184 patients collected between 2018 and 2024, totaling 1112 images (460 normal, 652 CLD). Various MRI sequences, including axial T1, T2, and coronal, were used. The images were preprocessed with resizing, augmentation, and normalization techniques. The DeepCNN model was trained and compared against traditional machine learning (ML) algorithms, including logistic regression, k-nearest neighbor, support vector machines, and random forest. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. Results: The DeepCNN model achieved a 93% accuracy and an F1-score of 0.939. Precision and recall for CLD classification were 97% and 98%, respectively. In comparison, traditional ML algorithms performed with accuracies ranging from 72.31% to 83.16%, with random forest achieving the highest. The DeepCNN model significantly outperformed these methods, demonstrating its strength in medical image classification. Using axial-only images reduced accuracy to 86%, showing that coronal views contribute valuable information. Limitation of data constrained learning. Conclusions: The DeepCNN model provides superior accuracy in diagnosing CLD compared to traditional ML methods, using MRI images without segmentation. This approach offers a practical solution for improving CLD detection and paves the way for future enhancements using attention mechanisms and advanced deep learning architectures.
- 15 January 2026
- Published by Termedia Sp. z.o.o. in Polish Journal of Radiology
- Vol. 91 (1) , e1-e10
Open AccessChronic liver disease detection using deep convolutional neural networks with MRI data: a deep learning approach
Purpose: Chronic liver disease (CLD) is a significant health issue, and detection is crucial for effective treatment. This study aimed to develop a deep learning based convolutional neural network (DeepCNN) to differentiate CLD from non-CLD patients using magnetic resonance imaging (MRI) images without segmentation, enhancing diagnostic accuracy and supporting timely intervention. Material and methods: A retrospective study was conducted using MRI data from 184 patients collected between 2018 and 2024, totaling 1112 images (460 normal, 652 CLD). Various MRI sequences, including axial T1, T2, and coronal, were used. The images were preprocessed with resizing, augmentation, and normalization techniques. The DeepCNN model was trained and compared against traditional machine learning (ML) algorithms, including logistic regression, k-nearest neighbor, support vector machines, and random forest. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. Results: The DeepCNN model achieved a 93% accuracy and an F1-score of 0.939. Precision and recall for CLD classification were 97% and 98%, respectively. In comparison, traditional ML algorithms performed with accuracies ranging from 72.31% to 83.16%, with random forest achieving the highest. The DeepCNN model significantly outperformed these methods, demonstrating its strength in medical image classification. Using axial-only images reduced accuracy to 86%, showing that coronal views contribute valuable information. Limitation of data constrained learning. Conclusions: The DeepCNN model provides superior accuracy in diagnosing CLD compared to traditional ML methods, using MRI images without segmentation. This approach offers a practical solution for improving CLD detection and paves the way for future enhancements using attention mechanisms and advanced deep learning architectures.
- Open Access
- 27 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 120142-120164
Enhancing Face Image Quality: Strategic Patch Selection With Deep Reinforcement Learning and Super-Resolution Boost via RRDB
Facial super-resolution (FSR) is a critical research area whose goal is to improve visual quality by converting low-resolution facial images to high resolution ones. Research in FSR has come a long way thanks to advances in deep learning technologies. However, there is still a need to develop effective methods for revealing facial details and preserving the overall appearance. For this purpose, a new approach called Deep Reinforcement Learning Based Super Resolution of Face Regions (DRL-SRFR) is proposed. It is based on Deep Reinforcement Learning (DRL) and Deep Residual Dense Block (RRDB) architectures. In the DRL part of the method, new regions that need attention are identified at each step using the repeated visual attention methodology. The details in different parts of the face image are iteratively improved to produce more natural and high-quality face images. In addition, with the stochastic action-taking process, the decision-making process is made flexible by focusing on important facial regions. The focused region is improved with the RRDB structure using dense connections and residual learning. Experiments and ablation studies show that the developed model provides a significant advantage over existing methods in improving local details and preserving appearance integrity.
- 27 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 120142-120164
Open AccessEnhancing Face Image Quality: Strategic Patch Selection With Deep Reinforcement Learning and Super-Resolution Boost via RRDB
Facial super-resolution (FSR) is a critical research area whose goal is to improve visual quality by converting low-resolution facial images to high resolution ones. Research in FSR has come a long way thanks to advances in deep learning technologies. However, there is still a need to develop effective methods for revealing facial details and preserving the overall appearance. For this purpose, a new approach called Deep Reinforcement Learning Based Super Resolution of Face Regions (DRL-SRFR) is proposed. It is based on Deep Reinforcement Learning (DRL) and Deep Residual Dense Block (RRDB) architectures. In the DRL part of the method, new regions that need attention are identified at each step using the repeated visual attention methodology. The details in different parts of the face image are iteratively improved to produce more natural and high-quality face images. In addition, with the stochastic action-taking process, the decision-making process is made flexible by focusing on important facial regions. The focused region is improved with the RRDB structure using dense connections and residual learning. Experiments and ablation studies show that the developed model provides a significant advantage over existing methods in improving local details and preserving appearance integrity.
- 1 August 2019
- Published by Sakarya University Journal of Science in Sakarya University Journal of Science
- Vol. 23 (4) , 493-500
Comparison Of Reversible Image Watermarking Methods Based On Prediction-Errors
This study compares two reversible image watermarking algorithms applied to a digital image. The first algorithm is a method based on adaptive watermarking of prediction-errors. With this method, as in the existing reversible image watermarking methods, pixels are embedded in two different ways according to the values of prediction-errors instead of applying the same watermarking algorithm to all pixels in the imageAccordingly, the image pixels are divided into two blocks as uniform and non-uniform. The watermarking capacity has been increased by embedding 2-bit to specific pixels of uniform blocks and 1-bit to specific pixels of non-uniform blocks. The second algorithm is a method based on interpolation errors. In this method, interpolation error is utilized. The two methods compared with each other were compared with the existing methods in the literature by using computer simulations, and superior and weak aspects of the methods were determined.
- 1 August 2019
- Published by Sakarya University Journal of Science in Sakarya University Journal of Science
- Vol. 23 (4) , 493-500
Comparison Of Reversible Image Watermarking Methods Based On Prediction-Errors
This study compares two reversible image watermarking algorithms applied to a digital image. The first algorithm is a method based on adaptive watermarking of prediction-errors. With this method, as in the existing reversible image watermarking methods, pixels are embedded in two different ways according to the values of prediction-errors instead of applying the same watermarking algorithm to all pixels in the imageAccordingly, the image pixels are divided into two blocks as uniform and non-uniform. The watermarking capacity has been increased by embedding 2-bit to specific pixels of uniform blocks and 1-bit to specific pixels of non-uniform blocks. The second algorithm is a method based on interpolation errors. In this method, interpolation error is utilized. The two methods compared with each other were compared with the existing methods in the literature by using computer simulations, and superior and weak aspects of the methods were determined.