Yazar "Sengur, Abdulkadir" seçeneğine göre listele
Listeleniyor 1 - 14 / 14
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 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 ConvNext Mixer-Based Encoder Decoder Method for Nuclei Segmentation in Histopathology Images(Wiley, 2024) Firat, Hueseyin; Uzen, Hueseyin; Hanbay, Davut; Sengur, AbdulkadirHistopathology, vital in diagnosing medical conditions, especially in cancer research, relies on analyzing histopathology images (HIs). Nuclei segmentation, a key task, involves precisely identifying cell nuclei boundaries. Manual segmentation by pathologists is time-consuming, prompting the need for robust automated methods. Challenges in segmentation arise from HI complexities, necessitating advanced techniques. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs), have transformed nuclei segmentation. This study emphasizes feature extraction, introducing the ConvNext Mixer-based Encoder-Decoder (CNM-ED) model. Unlike traditional CNN based models, the proposed CNM-ED model enables the extraction of spatial and long context features to address the inherent complexities of histopathology images. This method leverages a multi-path strategy using a traditional CNN architecture as well as different paths focused on obtaining customized long context features using the ConvNext Mixer block structure that combines ConvMixer and ConvNext blocks. The fusion of these diverse features in the final segmentation output enables improved accuracy and performance, surpassing existing state-of-the-art segmentation models. Moreover, our multi-level feature extraction strategy is more effective than models using self-attention mechanisms such as SwinUnet and TransUnet, which have been frequently used in recent years. Experimental studies were conducted using five different datasets (TNBC, MoNuSeg, CoNSeP, CPM17, and CryoNuSeg) to analyze the performance of the proposed CNM-ED model. Comparisons were made with various CNN based models in the literature using evaluation metrics such as accuracy, AJI, macro F1 score, macro intersection over union, macro precision, and macro recall. It was observed that the proposed CNM-ED model achieved highly successful results across all metrics. Through comparisons with state-art-of models from the literature, the proposed CNM-ED model stands out as a promising advancement in nuclei segmentation, addressing the intricacies of histopathological images. The model demonstrates enhanced diagnostic capabilities and holds the potential for significant progress in medical research.Öğe Efficient approach for digitization of the cardiotocography signals(Elsevier, 2020) Comert, Zafer; Sengur, Abdulkadir; Akbulut, Yaman; Budak, Umit; Kocamaz, Adnan Fatih; Bajaj, VarunCardiotocography (CTG) is generally provided on printed traces, and digitization of CTG signal is important for forthcoming assessments. In this paper, a new algorithm relies on the box-counting method is offered for the digitization of the CTG signals from CTG printed traces. The introduced algorithm inputs the CTG printed traces and outputs the digital fetal heart rate (FHR) and uterine contraction (UC) signals. The proposed method initially extracts the CTG signal image and gridded background image. Retrieving of the FHR and UC signals on the gridded background disrupts the background grids. So, we employ an algorithm to fix the degraded lines in the gridded background. After the line fixing operation, the boxes in the horizontal and vertical axes are counted for determining the calibration parameters. A set of specific equations are used to determine the calibration parameters. The signal extraction is performed on by red channel thresholding of input CTG printing images. An open-access CTG intrapartum database comprises 552 samples is used in the experiment. As a result, the average correlation coefficients of FHR and UC signals are 0.9811 +/- 0.0251 and 0.9905 +/- 0.0126, respectively. (C) 2019 Elsevier B.V. All rights reserved.Öğe Feature Mapping and Deep Long Short Term Memory Network-Based Efficient Approach for Parkinson's Disease Diagnosis(Ieee-Inst Electrical Electronics Engineers Inc, 2021) Demir, Fatih; Sengur, Abdulkadir; Ari, Ali; Siddique, Kamran; Alswaitti, MohammedIn this paper, a novel approach was developed for Parkinson's disease (PD) diagnosis based on speech disorders. When the literature about the speech disorders-based PD diagnosis was reviewed, it was seen that the most of approaches were concentrated on the feature selection as the datasets contained a huge number of features. In contrast, in the proposed approach, instead of eliminating some of the features by using any feature selection method, all features were initially used for forming a mapping procedure where the input feature vectors were converted to the input images. Then, a deep Long Short Term Memory (LSTM) network was employed for PD detection where the obtained images were used. The deep LSTM network carried out both feature extraction and classification processes and its training was carried out in an end-to-end fashion. The activations in the convolutional layer were converted to sequence data through the sequence-folding and sequence-unfolding layers. The activations in the LSTM output with learning parameters were conveyed to the Softmax layer for the classification process. A publically available PD dataset was used in the experimental works and classification accuracy, sensitivity, specificity, precision, and F-score metrics were used for performance evaluation. The obtained accuracy, sensitivity, specificity, precision and F-score values were 94.27%, 0.960, 0.960, 0.910 and 0.930, respectively. The obtained results were also compared with some of the published results and it had seen that most of the achievements of the proposed method are better than the compared methods.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 Iterative Hard Thresholding Based Extreme Learning Machine(Ieee, 2015) Alcin, Omer Faruk; Ari, Ali; Sengur, Abdulkadir; Ince, Melih CevdetExtreme Learning Machines (ELM) is a new learning algorithm for Single hidden Layer Feed-forward Networks (SLFNs). The ELM has better generalization, rapid training and lower complexity, however, the method suffer from singularity problem and obtaining optimum number of neurons in the hidden layer. In this paper, we considered an IHT for sparse approximation of the output weights vector of the ELM network. The performance evaluation of the proposed method which is called IHT-ELM, was chosen out on four commonly used medical dataset for prediction purposes. The results showed that IHT-ELM has several advantages against the original ELM methods such as obtaining optimum number of neurons and low complexity.Öğe LSGP-USFNet: Automated Attention Deficit Hyperactivity Disorder Detection Using Locations of Sophie Germain's Primes on Ulam's Spiral-Based Features with Electroencephalogram Signals(Mdpi, 2023) Atila, Orhan; Deniz, Erkan; Ari, Ali; Sengur, Abdulkadir; Chakraborty, Subrata; Barua, Prabal Datta; Acharya, U. RajendraAnxiety, learning disabilities, and depression are the symptoms of attention deficit hyperactivity disorder (ADHD), an isogenous pattern of hyperactivity, impulsivity, and inattention. For the early diagnosis of ADHD, electroencephalogram (EEG) signals are widely used. However, the direct analysis of an EEG is highly challenging as it is time-consuming, nonlinear, and nonstationary in nature. Thus, in this paper, a novel approach (LSGP-USFNet) is developed based on the patterns obtained from Ulam's spiral and Sophia Germain's prime numbers. The EEG signals are initially filtered to remove the noise and segmented with a non-overlapping sliding window of a length of 512 samples. Then, a time-frequency analysis approach, namely continuous wavelet transform, is applied to each channel of the segmented EEG signal to interpret it in the time and frequency domain. The obtained time-frequency representation is saved as a time-frequency image, and a non-overlapping n x n sliding window is applied to this image for patch extraction. An n x n Ulam's spiral is localized on each patch, and the gray levels are acquired from this patch as features where Sophie Germain's primes are located in Ulam's spiral. All gray tones from all patches are concatenated to construct the features for ADHD and normal classes. A gray tone selection algorithm, namely ReliefF, is employed on the representative features to acquire the final most important gray tones. The support vector machine classifier is used with a 10-fold cross-validation criteria. Our proposed approach, LSGP-USFNet, was developed using a publicly available dataset and obtained an accuracy of 97.46% in detecting ADHD automatically. Our generated model is ready to be validated using a bigger database and it can also be used to detect other children's neurological disorders.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-model LSTM-based convolutional neural networks for detection of apple diseases and pests(Springer Heidelberg, 2019) Turkoglu, Muammer; Hanbay, Davut; Sengur, AbdulkadirIn this paper, we proposed Multi-model LSTM-based Pre-trained Convolutional Neural Networks (MLP-CNNs) as an ensemble majority voting classifier for the detection of plant diseases and pests. The proposed hybrid model is based on the combination of LSTM network with pre-trained CNN models. Specifically, in transfer learning, we adopted deep feature extraction from various fully connected layers of these pre-trained deep models. AlexNet, GoogleNet and DenseNet201 models are used in this work for feature extraction. The extracted deep features are then fed into the LSTM layer in order to construct a robust hybrid model for apple disease and pest detection. Later, the output predictions of three LSTM layers determined the class labels of the input images by majority voting classifier. In addition, we use an automatic scheme for determining the best choice of the network parameters of the LSTM layer. The experiments are carried out using data consisting of real-time apple disease and pest images from Turkey and the accuracy rates are calculated for performance evaluation. The experimental results show that by using the proposed ensemble combination structure, the results are comparable to, or better than, the pre-trained deep architectures.Öğe Nesne Algılama ve Semantik Bölütleme Yontemleri Kullanılarak Lateral Sefalometrik Radyografilerde Servikal Vertebra Analizi(2025) Sengur, Abdulkadir; Bor, Sabahattin; Ciğerim, Saadet Çınarsoy; Kayaoğlu, MazharBu çalışmada, lateral sefalometrik radyografilerde C2, C3 ve C4 servikal vertebralarının tespiti ve semantik segmentasyonu için yapay zeka tabanlı bir yöntem önerilmektedir. Araştırmada kullanılan veri seti, Van Yüzüncü Yıl Üniversitesi Diş Hekimliği Fakültesi Ortodonti Anabilim Dalı tarafından sağlanan 3085 lateral sefalometrik radyografiden oluşmaktadır. Uzman hekimler tarafından yapılan değerlendirme sonucunda, tanısal doğruluk ve klinik uygunluk kriterlerini karşılayan 2520 radyografi seçilerek çalışmaya dahil edilmiştir. İlk aşamada YOLOv8 ve YOLOv11 nesne algılama modelleri kullanılarak vertebra bölgeleri tespit edilmiş ve ardından bu alanlar QuPath yazılımı ile detaylı şekilde anotasyonlanmıştır. Etiketlenen veriler, Attention-UNet, Attention-ResUNet, SEEA-UNet ve ResAt-UNet gibi ileri seviye derin öğrenme modelleri kullanılarak segmentasyon işlemlerine tabi tutulmuştur. Çalışma, nesne algılama modellerinin %99,8 doğruluk oranıyla yüksek performans sergilediğini ortaya koymuştur. Segmentasyon modelleri arasında en iyi performansı %99,25 doğruluk oranı ile Attention-ResUNet gösterirken, ResAt-UNet modeli genelleme kapasitesindeki dengesiyle dikkat çekmiştir. Elde edilen ikili maskeler, kemik yaşı tahmini ve iskeletsel olgunluk analizi için güvenilir bir veri seti oluşturmuştur. Bu çalışma, ek görüntüleme ihtiyacını ortadan kaldırarak radyasyon maruziyetini azaltmayı ve klinik süreçleri hızlandırmayı amaçlamaktadır. Sonuçlar, yapay zeka destekli yöntemlerin manuel değerlendirme kaynaklı hataları en aza indirdiğini ve iskeletsel analizde standardizasyon sağladığını göstermektedir. Gelecekte, bu yöntemlerin ortodonti ve pediatrik tıbbi uygulamalarda yaygın olarak kullanılabileceği öngörülmektedir.Öğe Prediction of intrapartum fetal hypoxia considering feature selection algorithms and machine learning models(Springer, 2019) Comert, Zafer; Sengur, Abdulkadir; Budak, Umit; Kocamaz, Adnan FatihIntroduction Cardiotocography (CTG) consists of two biophysical signals that are fetal heart rate (FHR) and uterine contraction (UC). In this research area, the computerized systems are usually utilized to provide more objective and repeatable results. Materials and Methods Feature selection algorithms are of great importance regarding the computerized systems to not only reduce the dimension of feature set but also to reveal the most relevant features without losing too much information. In this paper, three filters and two wrappers feature selection methods and machine learning models, which are artificial neural network (ANN), k-nearest neighbor (kNN), decision tree (DT), and support vector machine (SVM), are evaluated on a high dimensional feature set obtained from an open-access CTU-UHB intrapartum CTG database. The signals are divided into two classes as normal and hypoxic considering umbilical artery pH value (pH < 7.20) measured after delivery. A comprehensive diagnostic feature set forming the features obtained from morphological, linear, nonlinear, time-frequency and image-based time-frequency domains is generated first. Then, combinations of the feature selection algorithms and machine learning models are evaluated to achieve the most effective features as well as high classification performance. Results The experimental results show that it is possible to achieve better classification performance using lower dimensional feature set that comprises of more related features, instead of the high-dimensional feature set. The most informative feature subset was generated by considering the frequency of selection of the features by feature selection algorithms. As a result, the most efficient results were produced by selected only 12 relevant features instead of a full feature set consisting of 30 diagnostic indices and SVM model. Sensitivity and specificity were achieved as 77.40% and 93.86%, respectively. Conclusion Consequently, the evaluation of multiple feature selection algorithms resulted in achieving the best results.Öğe Transfer Öğrenme Tabanlı Derin Öğrenme Yaklaşımlarıyla Servikal Vertebra Matürasyon Safhalarının Sınıflandırılması ve Kemik Yaşı Değerlendirilmesi(2025) Sengur, Abdulkadir; Bor, Sabahattin; Kotan, Seda; Kayaoğlu, MazharBu çalışmada, büyüme ve gelişimi değerlendirmek amacıyla lateral sefalometrik radyografiler kullanılarak servikal vertebra maturasyon (CVM) evrelerinin otomatik sınıflandırılması gerçekleştirilmiştir. Van Yüzüncü Yıl Üniversitesi Diş Hekimliği Fakültesi Ortodonti Anabilim Dalı tarafından sağlanan toplam 4285 radyografi kullanılmıştır. Uzman hekimler tarafından yapılan detaylı değerlendirmeler sonucunda, tanısal doğruluk ve klinik uygunluk kriterlerini karşılayan 3750 görüntü çalışmaya dâhil edilmiştir. Seçilen görüntüler, altı sınıfa (CVMS 1– 6) ayrılarak dengeli bir veri seti oluşturulmuş ve NFNet, ConvNeXt V2, EfficientNet V2 ve DeiT3 modelleri kullanılarak sınıflandırma işlemleri gerçekleştirilmiştir. NFNet modeli, %96 eğitim doğruluğu ve %85,7 test doğruluğu ile en yüksek genel performansı sergilemiştir. %95 eğitim doğruluğu ve %86,9 test doğruluğu elde eden ConvNeXt V2, genelleme açısından en dengeli model olarak öne çıkmıştır. EfficientNet V2, %94 eğitim doğruluğuna ulaşmasına rağmen %80,7 test doğruluğu ile sınırlı bir genelleme kapasitesi göstermiştir. DeiT3 modeli ise %93 eğitim doğruluğu ve %77,6 test doğruluğu ile en düşük genelleme kapasitesine sahip olmuştur. NFNet ve ConvNeXt V2, yüksek doğruluk oranları ve dengeli performansları sayesinde güçlü sınıflandırma adayları olarak öne çıkmıştır. NFNet’in eğitim ve test doğruluğu arasındaki %10,3’lük fark genelleme kapasitesinde bir miktar azalmaya işaret ederken, ConvNeXt V2’nin daha dar olan %8,1’lik farkı daha istikrarlı bir performans göstermiştir. Sonuç olarak, NFNet ve ConvNeXt V2, CVM sınıflandırması için umut vadeden modeller olarak belirlenmiştir. Gelecekteki çalışmalarda, bu modellerin performansını artırmak ve klinik uygulanabilirliklerini güçlendirmek için daha büyük veri setleri kullanılması ve hiperparametre optimizasyonunun gerçekleştirilmesi önerilmektedir.
