Yazar "Uzen, Huseyin" seçeneğine göre listele
Listeleniyor 1 - 18 / 18
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Comprehensive CNN Model for Age-Related Macular Degeneration Classification Using OCT: Integrating Inception Modules, SE Blocks, and ConvMixer(Mdpi, 2024) Yusufoglu, Elif; Firat, Huseyin; Uzen, Huseyin; Ozcelik, Salih Taha Alperen; Cicek, Ipek Balikci; Sengur, Abdulkadir; Atila, OrhanBackground/Objectives: Age-related macular degeneration (AMD) is a significant cause of vision loss in older adults, often progressing without early noticeable symptoms. Deep learning (DL) models, particularly convolutional neural networks (CNNs), demonstrate potential in accurately diagnosing and classifying AMD using medical imaging technologies like optical coherence to-mography (OCT) scans. This study introduces a novel CNN-based DL method for AMD diagnosis, aiming to enhance computational efficiency and classification accuracy. Methods: The proposed method (PM) combines modified Inception modules, Depthwise Squeeze-and-Excitation Blocks, and ConvMixer architecture. Its effectiveness was evaluated on two datasets: a private dataset with 2316 images and the public Noor dataset. Key performance metrics, including accuracy, precision, recall, and F1 score, were calculated to assess the method's diagnostic performance. Results: On the private dataset, the PM achieved outstanding performance: 97.98% accuracy, 97.95% precision, 97.77% recall, and 97.86% F1 score. When tested on the public Noor dataset, the method reached 100% across all evaluation metrics, outperforming existing DL approaches. Conclusions: These results highlight the promising role of AI-based systems in AMD diagnosis, of-fering advanced feature extraction capabilities that can potentially enable early detection and in-tervention, ultimately improving patient care and outcomes. While the proposed model demon-strates promising performance on the datasets tested, the study is limited by the size and diversity of the datasets. Future work will focus on external clinical validation to address these limita-tions.Öğe Accurate Segmentation of Brain Tumors in Magnetic Resonance Images with Pyramid Stage Decomposition Network Approach(Ieee, 2024) Ari, Berna Gurler; Uzen, Huseyin; Sengur, AbdulkadirThis study explores the utilization of the Pyramid Scene Parsing Network (PSPNet) architecture to achieve accurate segmentation of brain tumors in magnetic resonance (MR) images. Experimental evaluations were conducted on different pre-trained backbone network models, including Vgg16, Inceptionv3, Mobilenetv2, Efficientnetb0, Resnet18, Resnet34, Resnet50, Resnet101, Resnext50, and Resnext101, assessing the performance of each model in brain tumor segmentation. The results highlight the VGG16-PSPNet model as the most successful, showcasing high F1-score, mIoU, precision, recall, and accuracy values.Öğe Automatic Thresholding Method Developed With Entropy For Fabric Defect Detection(Ieee, 2019) Uzen, Huseyin; Firat, Huseyin; Karci, Ali; Hanbay, DavutFabric defect detection is one of the most important areas for quality control of products in the textile industry. Many different studies have developed methods for this problem. In this study, an automatic thresholding method developed with entropy has been proposed. Due to the low cost of calculation, the proposed automatic thresholding method will be very suitable for real-time applications. In this study, automatic thresholding method which is supported by 4 different entropy method was compared with otsu method which is one of automatic thresholding methods. Various tests have been made on different fabric types for comparisons. As a result of experimental studies, successful results of automatic thresholding methods supported with entropy were obtained for fabric defect detection. Renyi entropy method was the most successful result among the proposed methods.Öğe Central serous retinopathy classification with deep learning-based multilevel feature extraction from optical coherence tomography images(Elsevier Sci Ltd, 2025) Uzen, Huseyin; Firat, Huseyin; Ozcelik, Salih Taha Alperen; Yusufoglu, Elif; Cicek, Ipek Balikci; Sengur, AbdulkadirCentral Serous Chorioretinopathy (CSCR) is an ocular disease characterized by fluid accumulation under the retina, which can lead to permanent visual impairment if not diagnosed early. This study presents a deep learning-based Convolutional Neural Network (CNN) model designed to automatically diagnose acute and chronic CSCR from Optical Coherence Tomography (OCT) images through multi-level feature extraction. The proposed CNN architecture consists of consecutive layers like a traditional CNN. However, it also extracts various features by creating feature maps at four different levels (F1, F2, F3, F4) for the final feature map. The model processes information using group-wise convolution and Pointwise Convolution Block (PCB) at each level. In this way, each feature group is further processed to obtain more representative features, enabling more independent learning. After the PCB outputs, the 4 feature maps are vectorized and combined, thus creating the final feature map. Finally, classification prediction scores are obtained by applying a fully connected layer and softmax function to this feature map. The experimental study utilized two datasets obtained from Elazig Ophthalmology Polyclinic. The dataset includes 3860 OCT images from 488 individuals, with images categorized into acute CSCR, chronic CSCR, wet AMD, dry AMD, and healthy controls. Our proposed method achieves an increase in accuracy of 0.77%, attaining 96.40% compared to the highest previous accuracy of 95.73% by ResNet101. Precision is enhanced by 0.95%, reaching 95.16% over ResNet101 ' s 94.21%. The sensitivity (recall) is improved by 0.90%, achieving 95.65% versus ResNet101 ' s 94.75%. Additionally, the F1 score is increased by 0.93%, attaining 95.38% compared to ResNet101 ' s 94.45%. These results illustrate the effectiveness of our method, offering more precise and reliable diagnostic capabilities in OCT image classification. In conclusion, this study demonstrates the potential of artificial intelligence-supported diagnostic tools in the analysis of OCT images and contributes significantly to the development of early diagnosis and treatment strategies.Öğe Channel-boosted multi-scale R-CNN for accurate and real-time ship and land detection in complex SAR scenes(Elsevier Sci Ltd, 2026) Hanbay, Kazim; Ozcelik, Salih Taha Alperen; Altin, Mustafa; Uzen, HuseyinAccurate ship detection in Synthetic Aperture Radar (SAR) imagery is crucial for maritime surveillance but remains challenging due to small target sizes, speckle noise, and complex sea-surface backgrounds. While most existing methods focus exclusively on identifying ships, our approach also achieves reliable detection of land areas, providing an additional contribution to the literature. This study introduces CBM-RCNN (Channel-Boosted Multi-Scale R-CNN), a novel deep learning architecture that integrates Convolutional Block Attention Modules (CBAM) and a Bidirectional Feature Pyramid Network (BiFPN) on a ResNet50 backbone. CBAM enhances both spatial and channel-level feature representation, enabling reliable detection of small vessels, while BiFPN fuses multi-scale features bidirectionally, improving accuracy across vessels of different sizes and positions. CBM-RCNN was evaluated against standard Faster R-CNN and YOLOv8 models across diverse maritime scenes, including simple, densely populated, and visually complex scenarios. The model demonstrated superior detection accuracy, balanced class-specific performance, and strong generalization. It effectively resolves overlapping vessels, distinguishes ships from coastal structures, and maintains robustness under challenging SAR-specific noise conditions. Importantly, it achieves inference speeds suitable for near-real-time applications, highlighting practical applicability. By combining attention-driven refinement with multi-scale feature aggregation, CBM-RCNN addresses limitations of prior methods, particularly in small object recognition, complex scene generalization, and simultaneous land detection. This architecture provides a robust framework for automated maritime monitoring and offers a foundation for future improvements in large-scale SAR-based ship detection and environmental surveillance.Öğe A deep feature extractor approach for the recognition of pollen-bearing bees(Ieee, 2020) Turkoglu, Muammer; Uzen, Huseyin; Hanbay, DavutIn this study, a convolutional neural network (ESA) based feature extracting hybrid model was proposed for the identification of bees carrying pollen or not. The fc6 and fc7 layers of AlexNet and VGG16 which a pre-trained ESA architecture, were used as feature extractors. The performances of the different combinations of the deep properties obtained using the SVM classifier were calculated. The PollenDataset dataset was used to test the proposed model. According to the experimental results, an accuracy score of 97.20% was obtained. As a result, the obtained accuracy score was compared with the state-of-the-art accuracy scores and the proposed model provided better performance than the compared methods.Öğe Deep Learning-Assisted Detection and Classification of Thymoma Tumors in CT Scans(Mdpi, 2025) Kilic, Murat; Biyikli, Merve; Ozcelik, Salih Taha Alperen; Uzen, Huseyin; Firat, HuseyinBackground/Objectives: Thymoma is a rare epithelial neoplasm originating from the thymus gland, and its accurate detection and classification using computed tomography (CT) images remain diagnostically challenging due to subtle morphological similarities with other mediastinal pathologies. This study presents a deep learning (DL)-based model designed to improve diagnostic accuracy for both thymoma detection and subtype classification (benign vs. malignant). Methods: The proposed approach integrates a pre-trained VGG16 network for efficient feature extraction-capitalizing on its capacity to capture hierarchical spatial features-and an MLP-Mixer-based feature enhancement module, which effectively models both local and global feature dependencies without relying on conventional convolutional mechanisms. Additionally, customized preprocessing and post-processing methods are employed to enhance image quality and suppress redundant data. The model's performance was evaluated on two classification tasks: distinguishing thymoma from healthy cases and discriminating between benign and malignant thymoma. Comparative analysis was conducted against state-of-the-art DL models including ResNet50, ResNet34, SEResNeXt50, InceptionResNetV2, MobileNetV2, VGG16, InceptionV3, and DenseNet121 using metrics such as F1 score, accuracy, recall, and precision. Results: The model proposed in this study obtained its best performance in thymoma vs. healthy classification, with an accuracy of 97.15% and F1 score of 80.99%. In the benign vs. malignant task, it attained an accuracy of 79.20% and an F1 score of 78.51%, outperforming all baseline methods. Conclusions: The integration of VGG16's robust spatial feature extraction and the MLP-Mixer's effective feature mixing demonstrates superior and balanced performance, highlighting the model's potential for clinical decision support in thymoma diagnosis.Öğe Depth-wise Squeeze and Excitation Block-based Efficient-Unet model for surface defect detection(Springer, 2023) Uzen, Huseyin; Turkoglu, Muammer; Aslan, Muzaffer; Hanbay, DavutDetection of surface defects in manufacturing systems is crucial for product quality. Detection of surface defects with high accuracy can prevent financial and time losses. Recently, efforts to develop high-performance automatic surface defect detection systems using computer vision and machine-learning methods have become prominent. In line with this purpose, this paper proposed a novel approach based on Depth-wise Squeeze and Excitation Block-based Efficient-Unet (DSEB-EUNet) for automatic surface defect detection. The proposed model consists of an encoder-decoder, the basic structure of the Unet architecture, and a Depth-wise Squeeze and Excitation Block added to the skip-connection of Unet. First, in the encoder part of the proposed model, low-level and high-level features were obtained by the EfficientNet network. Then, these features were transferred to the Depth-wise Squeeze and Excitation Block. The proposed DSEB based on the combination of Squeeze-Excitation and Depth-wise Separable Convolution enabled to reveal of critical information by weighting the features with a lightweight gating mechanism for surface defect detection. Besides, in the decoder part of the proposed model, the structure called Multi-level Feature Concatenated Block (MFCB) transferred the weighted features to the last layers without losing spatial detail. Finally, pixel-level defect detection was performed using the sigmoid function. The proposed model was tested using three general datasets for surface defect detection. In experimental works, the best F1-scores for MT, DAGM, and AITEX datasets using the proposed DSEB-EUNet architecture were 89.20%, 85.97%, and 90.39%, respectively. These results showed the proposed model outperforms higher performance compared to state-of-the-art approaches.Öğe Development of CNN architecture for Honey Bees Disease Condition(Ieee, 2019) Uzen, Huseyin; Yeroglu, Celaleddin; Hanbay, DavutHoney bees are one of the most important pollinators for a wide range of products in the food chain. Today, with the help of developing technology, observing bees healthy controls is a very important field of study. In this study, the images taken in the natural environment of the bees were processed with Convolutional Neural Network (CNN) architecture and the health status of the bees were classified The results obtained were promising for the studies to be carried out in this area. In addition, the structure of the CNN architectures was studied and the CNN architectures with different types and number of layers were compared with each other. As a result of the comparison, using the ideal number of convolution layers instead of using a great number of convolution layers for CNN architectures, increases the success. In addition, the use of normalization layers that serve as supporters in CNN architectures has been found to be very important for increasing success. In this study, 5 different CNN architectures were developed and the classification results obtained with these architectures were analyzed Among the architectures developed, KM_1 network architecture has achieved the best results with a success rate of 92,42.Öğe Grad-CAM Enhanced Explainable Deep Learning for Multi-Class Lung Cancer Classification Using DE-SAMNet Model(Mdpi, 2026) Kilic, Murat; Biyikli, Merve; Yelman, Abdulkadir; Firat, Huseyin; Uzen, Huseyin; Cicek, Ipek Balikci; Sengur, AbdulkadirBackground/Objectives: Lung cancer (LC) is the leading cause of cancer-related mortality worldwide, making early and accurate diagnosis crucial for improving patient outcomes. Although chest computed tomography (CT) enables detailed assessment of lung abnormalities, manual interpretation is time-consuming, requires expert expertise, and is prone to diagnostic variability. To address these challenges, this study proposes DE-SAMNet, a hybrid deep learning framework for automated multi-class LC classification from CT scans. Methods: The model integrates two pre-trained convolutional neural networks-DenseNet121 and EfficientNetB0-operating in parallel to extract complementary multi-scale features. A Spatial Attention Module (SAM) is applied to each feature stream to emphasize clinically important regions. Final classification is performed through a compact fusion mechanism involving global average pooling, batch normalization, and a fully connected layer. DE-SAMNet was evaluated on two datasets: a public dataset (IQ-OTH/NCCD) with benign, malignant, and normal cases, and a private clinical dataset including benign, malignant, cystic, and healthy cases. Results: On the public dataset, the model achieved a 99.00% F1-score, 98.41% recall, 99.64% precision, and 99.54% accuracy. On the private dataset, it obtained 95.96% accuracy, 95.99% precision, 96.04% F1-score, and 96.21% recall, outperforming existing approaches. To enhance reliability, explainable AI (XAI) techniques such as Grad-CAM were used to visualize the model's decision rationale. The resulting heatmaps effectively highlight lesion-specific regions, offering transparency and supporting clinical interpretability. Conclusions: This explainability strengthens trust in automated predictions and demonstrates the clinical potential of the proposed system. Overall, DE-SAMNet delivers a highly accurate and interpretable solution for early LC detection.Öğe InceptionV3 based enriched feature integration network architecture for pixel-level surface defect detection(Gazi Univ, Fac Engineering Architecture, 2023) Uzen, Huseyin; Turkoglu, Muammer; Ari, Ali; Hanbay, DavutIn this study, InceptionV3 based Enriched Feature Integration Network (Inc-EFIN) architecture was developed for automatic detection of surface defects. In the proposed architecture, features of all levels of the InceptionV3 architecture are extracted and the features with the same height and width are combined. As a result of merging, 5 feature maps were obtained. Channel-Based Squeeze and Excitation block has been applied to reveal important details in these feature maps. In Feature Pyramid Network module, information from low-level feature maps containing spatial details were transferred to high-level feature maps containing semantic details. Then, for the final feature map, features were combined using the Feature Integration and Signification (FIS) module. The feature map combined in the FIS module was passed through the Spatial and Channel-based Squeeze and Excitation block. Defect detection results were obtained by using convolution and sigmoid layers in the last layer of the Inc-EFIN architecture. MT, MVTec-Texture, and DAGM datasets were used to calculate the pixel-level defect detection success of the Inc-EFIN architecture. In experimental studies, Inc-EFIN architecture achieved higher performance than the latest technologies in the literature with 77.44% mIoU, 81.2% mIoU and 79.46% mIoU performance results in MT, MVTec-Texture and DAGM datasets, respectively.Öğe Maxillary sinus detection on cone beam computed tomography images using ResNet and Swin Transformer-based UNet(Elsevier Science Inc, 2024) Celebi, Adalet; Imak, Andac; Uzen, Huseyin; Budak, Umit; Turkoglu, Muammer; Hanbay, Davut; Sengur, AbdulkadirObjectives. This study, which uses artificial intelligence-based methods, aimed to determine the limits of pathologic conditions and infections related to the maxillary sinus in cone beam computed tomography (CBCT) images to facilitate the work of dentists. Methods. A new UNet architecture based on a state-of-the-art Swin transformer called Res-Swin-UNet was developed to detect the sinus. The encoder part of the proposed network model consists of a pre-trained ResNet architecture, and the decoder part consists of Swin transformer blocks. Swin transformers achieve powerful global context properties with self-attention mechanisms. Because the output of the Swin transformer generates sectorized features, the patch expanding layer was used in this section instead of the traditional upsampling layer. In the last layer of the decoder, sinus diagnosis was conducted through classical convolution and sigmoid function. In experimental works, we used a data set including 298 CBCT images. Results. The Res-Swin-UNet model achieved more success, with a 91.72% F1-score, 99% accuracy, and 84.71% IoU, outperforming the state-of-the-art models. Conclusions. The deep learning-based model proposed in the present study can assist dentists in automatically detecting the boundaries of pathologic conditions and infections within the maxillary sinus based on CBCT images. (Oral Surg Oral Med OralÖğe Multi-dimensional feature extraction-based deep encoder-decoder network for automatic surface defect detection(Springer London Ltd, 2023) Uzen, Huseyin; Turkoglu, Muammer; Hanbay, DavutThe control of surface defects is of critical importance in manufacturing quality control systems. Today, automatic defects detection using imaging and deep learning algorithms has produced more successful results than manual inspections. Thanks to these automatic applications, manufacturing systems will increase the production quality, and thus financial losses will be prevented. However, since the appearance and dimensions of the defects on the surface are very variable, automatic surface defect detection is a complex problem. In this study, multi-dimensional feature extraction-based deep encoder-decoder network (MFE-DEDNet) network developed to solve such problems. An effective encoder-decoder model with lower parameters compared to the state-of-the-art methods is developed using the depthwise separable convolutions (DSC) layers in the proposed model. In addition, the 3D spectral and spatial features extract (3DFE) module of the proposed model is developed to extract deep spectral and spatial features, as well as deep semantic features. During the combination of these features, the multi-input attention gate (MIAG) module is used so that important details are not lost. As a result, the proposed MFE-DEDNet model based on these structures enabled the extraction of powerful and effective features for defect detection in surface datasets containing few images. In experimental studies, MVTec and MT datasets were used to evaluate the performance of the MFE-DEDNet. The experimental results achieved 80.01% and 56% mean intersection-over-union (mIoU) scores for the MT and MVTec datasets, respectively. In these results, it was observed that the proposed model produced higher success compared to other state-of-the-art methods.Öğe Noise Reduced SAR Ship Database(Institute of Electrical and Electronics Engineers Inc., 2024) Hanbay, Kazim; Uzen, Huseyin; Ozdemir, Taha Burak; Ercelik, CetinSynthetic aperture radar (SAR) images are used extensively in agricultural applications, coastal boundary detection and object recognition. This imaging technology provides desired results in many challenging applications due to its ability to provide images with appropriate resolution in harsh weather and climate conditions. In this study, an image database was created to detect ships from SAR images. The images were preprocessed in accordance with the literature and made suitable for ship detection methods. The noise in the images was reduced with a deep learning-based architecture. Using this database, image processing and machine learning methods were used to develop ship detection methods. © 2024 IEEE.Öğe A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs(Mdpi, 2023) Dayi, Burak; Uzen, Huseyin; Cicek, Ipek Balikci; Duman, Suayip BurakThe study aims to evaluate the diagnostic performance of an artificial intelligence system based on deep learning for the segmentation of occlusal, proximal and cervical caries lesions on panoramic radiographs. The study included 504 anonymous panoramic radiographs obtained from the radiology archive of Inonu University Faculty of Dentistry's Department of Oral and Maxillofacial Radiology from January 2018 to January 2020. This study proposes Dental Caries Detection Network (DCDNet) architecture for dental caries segmentation. The main difference between DCDNet and other segmentation architecture is that the last part of DCDNet contains a Multi-Predicted Output (MPO) structure. In MPO, the final feature map split into three different paths for detecting occlusal, proximal and cervical caries. Extensive experimental analyses were executed to analyze the DCDNet network architecture performance. In these comparison results, while the proposed model achieved an average F1-score of 62.79%, the highest average F1-score of 15.69% was achieved with the state-of-the-art segmentation models. These results show that the proposed artificial intelligence-based model can be one of the indispensable auxiliary tools of dentists in the diagnosis and treatment planning of carious lesions by enabling their detection in different locations with high success.Öğe Surface Defect Detection Using Deep U-Net Network Architectures(Ieee, 2021) Uzen, Huseyin; Turkoglu, Muammer; Hanbay, DavutSurface defects detection in products used in industry such as steel, fabric and marble is very important in terms of increasing product quality and preventing financial losses. However, automatic surface defects detection is a very difficult problem due to the complexity and diversity of surface defects. In this study, U-net based VGG16-Unet and Resnet34-Unet network models are proposed for Surface defects detection. The proposed model used spatial features in the first layers together with deep semantic features. In the proposed network models, the trained weights of the VGG16 and Resnet34 network architectures were used for the input parameters of the Unet architecture. In experimental studies, the highest F1-score value for MT and AITEX data sets was obtained as 91.07% and 94.67%, respectively, with the proposed Resnet34-Unet model. According to the results, it was observed that the defective areas showing similarity with the background were successfully separated by using the proposed model.Öğe Swin-MFINet: Swin transformer based multi-feature integration network for detection of pixel-level surface defects(Pergamon-Elsevier Science Ltd, 2022) Uzen, Huseyin; Turkoglu, Muammer; Yanikoglu, Berrin; Hanbay, DavutAutomatic surface defect detection is critical for manufacturing industries, such as steel, fabric, and marble industries. This study proposes a Swin transformer-based model called Multi-Feature Integration Network (Swin-MFINet) for pixel-level surface defect detection. The proposed model consists of an encoder, a Swin transformer-based decoder, and Multi-Feature Integration (MFI) modules. In the encoder module of the proposed model, a pre-trained Inception network is used to extract key features from small-size datasets. In the decoder section, global semantic features are obtained from the initial features by using the Swin-transformer block, which is the newest transformer technology of today. In addition, the convolution layer is used in the last step of the decoder, since transformers are limited in acquiring small spatial details such as edges, colors, and textures, which are important in detecting some small defects. In the last module called MFI, feature maps from different decoder stages are combined, and the channel squeeze-spatial excitation block is applied to reveal important features. Finally, a prediction map is obtained by applying a convolution layer and sigmoid activation function to the MFI module output, respectively. The performance of proposed model is analyzed over MT and MVTec datasets containing surface defect images. The proposed model obtained mIoU scores of 81.37%, and 77.07% respectively, for these two datasets These results outperform the state-of-the-art for the surface defect detection problem.Öğe Texture defect classification with multiple pooling and filter ensemble based on deep neural network(Pergamon-Elsevier Science Ltd, 2021) Uzen, Huseyin; Turkoglu, Muammer; Hanbay, DavutFabric quality control is one of the most important phases of production in order to ensure high-quality standards in the fabric production sector. For this reason, the development of successful automatic quality control systems has been a very important research subject. In this study, we propose a Multiple Pooling and Filter approach based on a Deep Neural Network (MPF-DNN) for the classification of texture defects. This model consists of three basic stages: preprocessing, feature extraction, and classification. In the preprocessing stage, the texture images were first divided into n x n equal parts. Then, median filtering and pooling processes were applied to each piece prior to performing image merging. In the proposed pre-treatment stage, it is aimed to clarify fabric errors and increase performance. For the feature extraction stage, deep features were extracted from the texture images using the pretrained ResNet101 model based on the transfer learning approach. Finally, classification and testing procedures were conducted on the obtained deep-effective properties using the SVM method. The multiclass TILDA dataset was used in order to test the proposed model. In experimental work, the MPF-DNN model for all four classes achieved a significant overall accuracy score of 95.82%. In the results obtained from extensive experimental studies, it was observed that the proposed MPF-DNN model was more successful than previous studies that used pretrained deep architectures.
