Yazarlar
- Duru, Nevcihan(9)
- Eker, Ayse Gul(8)
- Pehlivanoglu, Meltem Kurt(6)
- Adali, E.(4)
- Dundar, Tolga Turan(3)
- Eker, Kadir(3)
- Ince, Ibrahim(2)
- Karaduman, Ismet(2)
- Serdar Mutluer, Ahmet(2)
- Akdeniz, Canberk(1)
- Aldemir, Osman(1)
- Boztepe, Handan(1)
- Bulut, Oktay(1)
- Dogan, Ihsan(1)
- Doğu, Nilgün(1)
- Erdem, Duygu(1)
- Ericek, Omer Burak(1)
- Gençbaş, Dercan(1)
- Karhan, Deniz(1)
- Kurt Pehlivanoglu, Meltem(1)
- Mandal, Dilek(1)
- Mutluer, Ahmet Serdar(1)
- Olcer, Ercan(1)
- Olcer, Uyesi Ercan(1)
- Ozturk, Candide(1)
- Pehlivanoǧlu, Meltem Kurt(1)
- Salici, Mustafa(1)
- Solhan, Resul(1)
- Syakura, Muhammad Abdan(1)
- Terzioğlu, Füsun(1)
- Uncu, Ata Emir(1)
- Varol, Onur(1)
- Yalçın, Suna Uysal(1)
- Yüceer, Buğse(1)
- Şevik Eliçora, Sultan(1)
Yayınlar
- MakaleYalnız künye2026Scopus SJRQ2Clinical Characteristics and Management Outcomes of Pediatric Temporal Bone Fractures: A Retrospective Cohort Study
Bulut, Oktay; Şevik Eliçora, Sultan; Erdem, Duygu
Background: – Pediatric temporal bone fractures may lead to facial paralysis, hearing loss, and cerebrospinal fluid (CSF) leakage. Understanding their clinical and radiologic characteristics is essential for effective management. Methods: – This retrospective, single-center descriptive study included 50 pediatric patients diagnosed with temporal bone fractures between 2013 and 2020. Demographic data, mechanisms of injury, fracture types, facial nerve function, CSF leakage, and audiological findings were analyzed. Fractures were classified according to the McHugh system (longitudinal, transverse, and mixed) and the Kelly-Tami classification [otic capsule sparing (OCS) versus otic capsule violating (OCV)]. Hearing was evaluated using auditory brainstem response (ABR) in children under 6 years and pure-tone audiometry (PTA) with age-appropriate behavioral techniques in older children. Results: – The cohort included 50 patients (mean age: 7.8±3.8 years; 64% boys). Falls were the leading cause of injury, while high-energy traumas such as gunshot and penetrating orbital injuries were rare but associated with complete facial paralysis and total hearing loss. Most fractures were longitudinal and OCS, showing favorable recovery, whereas OCV fractures caused irreversible deficits. CSF leakage occurred in 4 patients, all resolving spontaneously. Surgery was required only for persistent conductive hearing loss, and ossicular reconstruction restored normal hearing. Conclusion: – Pediatric temporal bone fractures are mostly OCS and longitudinal, typically caused by falls. OCV fractures are uncommon but linked to irreversible facial nerve and cochlear injury.
- MakaleYayıncıda açık erişim2026Investigation of the Relationship Between Artificial Intelligence Readiness and Artificial Intelligence Anxiety Levels in Nursing Students; [Hemşirelik Öğrencilerinde Yapay Zeka Hazırbulunuşluk ve Yapay Zeka Kaygı Düzeyleri Arasındaki İlişkinin İncelenmesi]
Yalçın, Suna Uysal; Solhan, Resul
Background: Artificial intelligence and robot technologies in the field of health and nursing practices are a new concept and it is known to have a high potential. For this reason, it is important for nursing students to be prepared for artificial intelligence and not to have problems in their education. In our study, it was aimed to examine the relationship between artificial intelligence readiness and artificial intelligence anxiety levels in nursing students. Methods: This study was descriptive-correlational in nature and was carried out with 176 students between May-June 2024 with a face-to-face questionnaire. “Demographic data Collection Form”, “Artificial Intelligence (AI) Anxiety Scale” and “Medical Artificial Intelligence (MAI) Readiness Scale” were used in the study. Descriptive statistical methods (frequency, mean, percentage analyses), Pearson correlation and linear regression analyses were used in data analysis. Results: 69.3% of the participants were female and 30.7% were male, and the AI anxiety score of female students (45.336 ± 13.747) was higher than that of male students (38.019 ± 16.203). This difference was statistically significant (t = 3.079, p = .002). According to the regression analysis results, medical AI readiness significantly and negatively affects AI anxiety (β = -.150, p .05). This finding indicates that asMAI readiness increases, AI anxiety decreases. Conclusion: In our study, artificial intelligence anxiety and artificial intelligence readiness levels of nursing students were found to be moderate. Nursing undergraduate education curriculum should be updated and courses such as technology/ artificial intelligence in health should be added to the curriculum; students should be informed about the use, positive aspects and advantages of artificial intelligence and their concerns about this issue should be eliminated.
- BildiriYalnız künye2025Brain Tissue Classification from Hyperspectral Images Using Convolutional Neural Networks
Karaduman, Ismet; Pehlivanoglu, Meltem Kurt; Eker, Ayse Gul; Duru, Nevcihan; Dundar, Tolga Turan; Serdar Mutluer, Ahmet; Adali, E.
Many of the decisions made and taken in the field of health are important for human life to be sufficient. In such an important area where human transactions are concerned, artificial intelligence-supported studies have a very important place, especially in recent years. This is the correct classification of four classes (Normal Tissue, Tumor Tissue, Hypervascularized Tissue and Background) separately with the 3D-CNN based deep learning model on the In-vivo Hyperspectral Human Brain Image dataset. For this purpose, firstly, three different data settings with 128 spectral bands were obtained from raw images, each containing 826 spectral bands, with dimension reduction methods. In this way, each data setting was made with the designs used in the 3D-CNN based deep learning model. As a result of the experimental studies, the highest F1 score of 99.69% was achieved with the 3D-CNN-based deep learning model.
AtıfScopus1
İncele - BildiriYalnız künye2025A Review of Hyperspectral Imaging in Neurosurgery: Datasets and Computational Approaches
Ozturk, Candide; Eker, Ayse Gul; Pehlivanoglu, Meltem Kurt; Karaduman, Ismet; Olcer, Ercan; Duru, Nevcihan; Dundar, Tolga Turan; Mutluer, Ahmet Serdar; Dogan, Ihsan; Ericek, Omer Burak
Hyperspectral imaging (HSI) is an imaging method that differs from traditional methods by recording the light reflection and absorption properties of each point across a wide color range. HSI enables the non-invasive determination of chemical and structural differences in tissues with high accuracy. In the domain of medicine, hyperspectral imaging represents a novel methodology that facilitates novel approaches in brain surgery, including the distinction of tumors and blood vessels, cancer diagnosis, and the monitoring of tissue oxygen levels and blood flow during surgical procedures. Additionally, hyperspectral imaging has a wide range of applications in various fields, including agriculture, food, environment, geology, and defense.This review comprehensively examines current datasets, application areas, and computational approaches related to the use of hyperspectral imaging technology in brain surgery. HSI enables the precise differentiation of different brain tissues such as tumors, vessels, functional areas, and the spine by collecting data across a wide spectral band range for each pixel. Recent studies in the literature demonstrate that machine learning and deep learning-based methods can achieve high accuracy rates in tissue segmentation and the detection of pathological structures in brain surgery. Additionally, datasets developed at different centers and involving various patient groups provide an important foundation for enhancing the clinical efficacy of HSI.While HSI boasts significant advantages in terms of its non-invasiveness and real-time analysis potential, which benefit surgeons during intraoperative decision-making processes, challenges such as data size, computational costs, and device integration pose barriers to its routine use. In the future, it is anticipated that these limitations will be overcome through the development of efficient algorithms, AI-supported systems, and multi-center validation studies. In conclusion, HSI technology exhibits considerable potential to become a standard intraoperative instrument in neurosurgery, driven by advancing computational methods and increasing clinical validation.
AtıfScopus1İncele - BildiriYalnız künye2025Calculating Brain Shift in Brain Tumor Surgeries: Integration of MR and Ultrasound Imaging Methods and Comparison of Feature Extraction Algorithms
Eker, Ayse Gul; Kurt Pehlivanoglu, Meltem; Duru, Nevcihan; Dundar, Tolga Turan; Serdar Mutluer, Ahmet; Adali, E.
Brain tumors are abnormal tissue masses formed as a result of uncontrolled cell proliferation in the brain, and surgery is the most common treatment method. During surgery, changes in the position of brain tissue are referred to as 'brain shift,' which prevents preoperative MR images from accurately reflecting the intraoperative situation and reduces surgical success. This study addresses the integration of MR and ultrasound (US) imaging methods to calculate brain shift and improve surgical accuracy in brain tumor surgeries. Different feature extraction algorithms such as SIFT, ORB, AKAZE, and BRISK were used to solve the alignment problem between MR and US images. Using an adaptive search strategy and 3D coordinate transformation, the amount of brain shift was calculated and real-time information was provided to surgeons. The use of the adaptive search strategy dynamically adjusted the search area according to the degree of brain shift, eliminating unnecessary regions and significantly increasing processing speed. Experimental results showed that the ORB algorithm performed best for small and moderate shifts (e.g., 3.78 ± 1.65 mm error for small shifts), while the SIFT algorithm was more successful for large shifts (9.91 ± 2.30 mm error). This method aims to enable surgeons to make more accurate decisions during surgery and to increase patient safety. In the future, it is planned to improve the accuracy of the method by using deep learning-based approaches and larger datasets.
- BildiriYalnız künye2024Dementia Classification from MR Images Using Machine Learning and Deep Learning Models; [Makine Öǧrenmesi ve Derin Öǧrenme Modelleri Kullanilarak MR Görüntülerinden Demans Siniflandirma]
Pehlivanoǧlu, Meltem Kurt; Varol, Onur; Aldemir, Osman; Uncu, Ata Emir; Duru, Nevcihan; Adali, E.
The classification of dementia levels in Alzheimer's disease is divided based on various characteristics of the disease. In this study, for the purpose of classifying dementia levels in Alzheimer's disease using MRI images, various Convolutional Neural Network (CNN)-based deep learning models, as well as machine learning and Artificial Neural Network (ANN) models, were trained. Various image manipulation and augmentation techniques were applied to create new datasets, and model performances were observed on these datasets. As a different approach, numerical features were extracted from MRI images, and models were built using these extracted features. Fusion hybrid models were produced by combining the most successful models trained with the images and their numerical representations. Experimental results have proven that hybrid models outperform other models in terms of performance in the classification of Alzheimer's disease.
AtıfScopus1İncele - BildiriYalnız künye2024Impact of Transformer-Based Models in NLP: An In-Depth Study on BERT and GPT; [Transformer Tabanlı Modellerin NLP'deki Etkisi: BERT ve GPT Üzerine Derinlemesine İnceleme]
Salici, Mustafa; Olcer, Uyesi Ercan
This article examines in depth the effects of BERT (Bidirectional Encoder Representations from Transformers) and GPT (Generative Pretrained Transformer) models in the field of natural language processing (NLP). NLP, as a sub-branch of computer science and artificial intelligence, has an important place in the processes of understanding, processing and producing human language. Transformer-based models have provided revolutionary advances in many NLP tasks, especially language modeling, sentiment analysis, machine translation and question answering. In this article, the technical structures of BERT and GPT models, their performance in low-resource languages such as Turkish and the difficulties encountered in these languages are discussed in detail. The BERT model stands out with its ability to evaluate the contextual meaning of the language from both directions using bidirectional context and offers high success rates especially in tasks such as text classification, named entity recognition (NER) and sentiment analysis. The GPT model, on the other hand, provides superiority in text production with its autoregressive structure and gives successful results in tasks such as creative writing and chatbots. However, the application of these models to morphologically rich and agglutinative languages such as Turkish poses certain challenges. These challenges arise due to the structural features of the language and the limitations of the datasets. The article also discusses the development of Turkish-specific models such as BERTurk, data augmentation techniques, and the success of modifications appropriate to the characteristics of the language in overcoming these challenges. In conclusion, the development of BERT and GPT models in the field of NLP has been a major step in terms of natural language processing and modeling. However, further research and development is required for these models to perform better in languages such as Turkish. The article predicts that future developments of these models will enable language technologies to reach wider audiences and be used in various applications.
AtıfScopus20İncele - BildiriYalnız künye2023Deep Learning and Transfer Learning Based Brain Tumor Segmentation; [Derin Ogrenme ve Transfer Ogrenme Tabanli Beyin Tumoru Segmentasyonu]
Eker, Ayse Gul; Pehlivanoglu, Meltem Kurt; Ince, Ibrahim; Duru, Nevcihan
In brain tumors, which are formed by the abnormal growth of cells in brain tissue, early diagnosis, and accurate treatment are crucial. Brain tumor segmentation provides experts with the ability to accurately identify brain tumors and determine their location. Through segmentation, the type, size, and shape of tumors can be determined, enabling the application of appropriate treatment. In this study, the aim was to perform brain tumor segmentation on the Brain Tumor Figshare (BTF) dataset, which includes diverse images in terms of structural complexity, viewing angles, different device usage, noise, and bias field effects, without applying any preprocessing. Basic models such as U-Net and FCN were utilized, along with transfer learning-based approaches using VGG, XceptionNet, InceptionNet, and ResNet architectures as the underlying structures in these models. According to the experimental results, the 16-layer FCN architecture with VGG- 19 as the underlying structure achieved the highest score with a dice score of 0.9169.
AtıfScopus12İncele - BildiriYalnız künye2023Brain Tumor Classification Using Deep Learning Algorithms; [Derin Ogrenme Algoritmalan ile Beyin Tiimoru Siniflandirma]
Pehlivanoglu, Meltem Kurt; Eker, Ayse Gul; Ince, Ibrahim; Karhan, Deniz; Duru, Nevcihan
Brain tumor classification categorizes brain tumors based on their various characteristics. It aids in determining suitable treatment strategies and predicting patient outcomes. Therefore, the objective of this study is to identify the optimal tumor classification model by utilizing various Convolutional Neural Network (CNN)-based deep learning models (including combined models) on a recently published tumor classification dataset. Furthermore, diverse image manipulation and augmentation techniques were applied and their impact on model performance was evaluated. The experimental results prove that the combined deep learning models outperform other approaches in terms of performance in multi-class brain tumor classification.
AtıfScopus3İncele - BildiriYalnız künye2023A Comparison of Grammatical Error Correction Models in English Writing; [Ingilizce Yaziminda Dil Bilgisel Hata Duzeltme Modellerinin Karsilastinlmasi]
Eker, Kadir; Pehlivanoglu, Meltem Kurt; Eker, Ayse Gul; Syakura, Muhammad Abdan; Duru, Nevcihan
Grammatical error correction (GEC) is the task of correcting grammatical, spelling, and word usage errors in texts. Detecting and correcting these errors makes it difficult for the reader to understand the text and negatively affects communication. Editors and proofreaders can identify and correct grammatical errors while reading texts. However, this manual correction takes a long time. With the development of technology, artificial intelligence-supported tools have been developed that automatically correct errors. In artificial intelligence-supported systems, this task is usually performed using natural language processing methods. In this study, a traditional neural network architecture (Attention BiLSTM) and a transformer-based language model (T5) were trained. Then, the success of these trained models and Large Language Models (LLMs) (ChatGPT, Google Bard, LanguageTool) in English grammatical error correction has been compared on the JFLEG dataset. According to experimental results, the pre-trained T5 language model beats others in all evaluation metrics for grammatical error correction.
AtıfScopus6İncele - BildiriYalnız künye2022Network Traffic Classification with Machine Learning Approaches; [Makine Ogrenmesi Yaklaimlan ile Ag Trafik Siniflandirilmasi]
Eker, Kadir; Eker, Ayse Gul; Mandal, Dilek; Pehlivanoglu, Meltem Kurt; Duru, Nevcihan
Today, detection of malware is often done automatically with artificial intelligence supported systems. In this way, this task, which was previously done manually, can be performed more precisely and more quickly. Darknet traffic is an internet network with many different cybercrime threats. It is also fake traffic observed in empty address space. A globally valid set of Internet Protocol (IP) addresses that are not assigned to any host or device. In this study, a deep learning model and pervasive machine learning classification algorithms are compared using the CIC-Darknet2020 dataset to describe Darknet traffic. The 'Tor' and 'Vpn' classes in the dataset, 'Darknet', 'Non-Tor' and 'Non-Vpn' classes are also specified as harmless. Various adjustments have been made for the unbalanced dataset, which has been performed with multiple classification, various machine learning algorithms. Random Forest Algorithm, Decision Trees and Deep Learning Model were the algorithms with the most successful accuracy values with %97.3, %97.4 %98.2values respectively.
AtıfScopus2İncele - BildiriYalnız künye2022EEG Signals and Spectrogram with Deep Learning Approaches Emotion Analysis with Images; [Derin Ogrenme Yaklaimlanyla EEG Sinyalleri ve Spektrogram Goruntuleri ile Duygu Analizi]
Eker, Ayse Gul; Duru, Nevcihan; Eker, Kadir
EEG signals are one of the most basic methods used in identifying and analyzing brain activities. Visual representation of EEG signals can be achieved with spectrograms. Spectrograms represent a visual representation of a signal's signal strength over time. In this study, the signals in an EEG dataset containing 'positive', 'negative' and 'neutral' emotion classes were classified with a deep learning model, and then these signals were transformed into a spectrogram image in the dataset with convolutional network model and also with transfer learning (EfficientNet and XceptionNet). Multiple classification was performed with pre-trained models. The success value obtained by the classification of the EEG signals and the success of the visualization in this classification were measured and presented by comparison. While higher accuracy values were achieved in the classification of signals with the deep network model, in metrics such as precision and F1-score, the classification of images with the proposed convolutional network model achieved much higher performance.
AtıfScopus8İncele - MakaleYayıncıda açık erişim2022Anxiety and Depression After Cesarean: Non-pharmacological Evidence Based Practices; [Sezaryen Sonrası Kaygı ve Depresyon: Non-Farmakolojik Kanıt Temelli Uygulamalar]
Terzioğlu, Füsun; Gençbaş, Dercan; Boztepe, Handan; Doğu, Nilgün; Akdeniz, Canberk; Yüceer, Buğse
The purpose of this review is to examine the non-pharmacological evidence-based practices of anxiety and depression after a cesarean section delivery. Postpartum anxiety and depression have increased in the last decade, the rates of postpartum depression are around 13% worldwide. In the postpartum period, women may experience anxiety and depression due to the operation they have undergone; such as being in an unfamiliar environment, facing new technological equipment and encounters with the medical teams, the post-operative pain, the new roles women undertake as mothers. One of the factors that increase anxiety and depression in the postpartum period is the type of delivery. In Turkey, the rate of cesarean delivery is comparatively high, which is approximately 52%. Anxiety and depression after cesarean section develop due to fear and concern such as the complications that may occur during and after the mother's anesthesia, the possibility delaying breastfeeding her baby, and experiencing pain. Non-pharmacological evidence-based applications such as reiki, acupressure, hand and foot massage, yoga, reflexology, aromatherapy, skin to skin care, nursing care protocols were found to be effective in studies conducted to reduce anxiety and depression after cesarean-section. Nurses who have critical roles and responsibilities in pre-and post-cesarean care practices are recommended to include these evidence-based non-pharmacological practices in routine care practices.
AtıfScopus2İncele