AOAlper Odabaş

Alper Odabaş

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alper Odabaş has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Segmentation of honeycomb cysts, traction bronchiectasis and emphysematous lung parenchyma using the deep learning method

    by Nevin Aydin, Hüseyin Yildirim, Füsun Alataş, Büşra Sariay, Burcu Mert, Serhat Demi̇r, Özer Çeli̇k, Ahmet Faruk Aslan, Alper Odabaş

    This study aimed to perform the segmentation of honeycomb cysts, traction bronchiectasis, and emphysematous lung parenchyma in highresolution computed tomography (HRCT) examinations using the deep learning method of artificial intelligence. The study included the cross-sectional images of 265 patients diagnosed with usual interstitial pneumonia between 2017 and 2021. Minimum intensity projection (MinIP) was performed on axial sections in the parenchymal window. Emphysema areas, traction bronchiectasis, and honeycomb cysts were segmented and labeled on the axial HRCT images. The dataset was divided into three parts, namely training, validation, and testing, at a ratio of 80, 10, and 10%, respectively. The results were calculated by selecting 50% as the threshold value for the intersection over union (Jaccard index) statistic. Of the 265 patients included in the study, 184 (69.4%) were male and 81 (30.6%) were female. Mean age of the patients was 73 ± 10 years. In the test group segmented as emphysema, the sensitivity, precision, F1 score, area under the curve (AUC), and accuracy values were calculated as 0.81, 0.90, 0.85, 0.86, and 0.75, respectively. In the test group segmented as traction bronchiectasis, the sensitivity, precision, F1 score, AUC, and accuracy values were found to be 0.95, 0.76, 0.85, 0.80, and 0.75, respectively. In the test group segmented as honeycomb cysts, the sensitivity, precision, F1 score, AUC, and accuracy values were 0.96, 0.92, 0.94, 0.88, and 0.90, respectively. In this study, we successfully utilized the U-Net architecture, a deep learning technology, to accurately segment honeycomb cysts in MinIP images, one of the parameters that will help classify interstitial lung diseases (ILDs). We anticipate that our study will guide future studies on the classification of ILDs.

  • Open Access

    Computing exterior isoclinism of crossed modules

    by Zekeri̇yA Arvasi̇, Alper Odabaş

    In this paper, we introduce exterior isoclinism for crossed modules, extending the concept of isoclinism from groups to these 2-dimensional algebraic structures. Motivated by work on tensor and exterior products of non-abelian groups, we utilize non-abelian exterior products, exterior squares, and exterior centers to define this new equivalence relation. Additionally, we provide computational tools implemented in the GAP system to identify exterior isoclinism families of small groups and crossed modules.


  • Open Access

    BİST-Çimento Şirketlerinin Finansal Performanslarının TOPSIS ve ELECTRE Yöntemleriyle Analizi

    by Tunga Bozdoğan, Alper Odabas, Ömer Orbay Çeti̇n

    In the scope of this study, the financial performance of companies in the cement sector listed on BIST (Borsa Istanbul) has been measured using two different methods. A comprehensive literature review was conducted to determine the financial ratios used in the analysis, and commonly used financial ratios in the literature were identified. The research included fifteen companies for which financial data spanning the period from 2013 to 2022 was available, and the CRITIC-based TOPSIS and ELECTRE methods, which are multi-criteria decision-making methods, were used for data analysis to measure their financial performance. As a result of the analysis, three separate performance groups were identified for the 15 companies: good, moderate, and poor. According to the findings of the analysis, in both methods, OYAK, NUHCM, and KONYA companies were the most successful in terms of financial performance, while BTCIM company was the least successful. It is recommended that the cement sector, which is expected to become even more important after the earthquake disaster in our country, should be continuously analyzed in the future with different data periods and different methods, and suggestions have been made for implementing corrective innovations in the sector.


  • Open Access

    Segmentation of acute pulmonary embolism in computed tomography pulmonary angiography using the deep learning method

    by Nevin Aydın, Çağatay Cihan, Özer Çelik, Ahmet Faruk Aslan, Alper Odabaş, Füsun Alataş, Hüseyin Yıldırım

    Pulmonary embolism is a type of thromboembolism seen in the main pulmonary artery and its branches. This study aimed to diagnose acute pulmonary embolism using the deep learning method in computed tomographic pulmonary angiography (CTPA) and perform the segmentation of pulmonary embolism data. The CTPA images of patients diagnosed with pulmonary embolism who underwent scheduled imaging were retrospectively evaluated. After data collection, the areas that were diagnosed as embolisms in the axial section images were segmented. The dataset was divided into three parts: training, validation, and testing. The results were calculated by selecting 50% as the cut-off value for the intersection over the union. Images were obtained from 1.550 patients. The mean age of the patients was 64.23 ± 15.45 years. A total of 2.339 axial computed tomography images obtained from the 1.550 patients were used. The PyTorch U-Net was used to train 400 epochs, and the best model, epoch 178, was recorded. In the testing group, the number of true positives was determined as 471, the number of false positives as 35, and 27 cases were not detected. The sensitivity of CTPA segmentation was 0.95, the precision value was 0.93, and the F1 score value was 0.94. The area under the curve value obtained in the receiver operating characteristic analysis was calculated as 0.88. In this study, the deep learning method was successfully employed for the segmentation of acute pulmonary embolism in CTPA, yielding positive outcomes.


  • Covid-19 Pandemisinde Bankaların Finansal Performanslarının ELECTRE ve TOPSIS Yöntemleriyle Değerlendirilmesi

    by Gürkan Kaplan, Alper Odabas, Tunga Bozdoğan

    Bu çalışmanın amacı pandemi döneminde bankaların finansal performanslarını değerlendirmektir. Çalışmanın kapsamını ülkemizde aktif büyüklükleri bakımından 3’ü kamu sermayeli olmak üzere en büyük 7 bankası oluşturmaktadır. Çalışmada bankaların 2019-2021 yılları mali verileri hem yıl bazında hem de 3 yıllık ortalama değerleri dikkate alınarak çok kriterli karar verme yöntemlerinden ELECTRE ve TOPSIS yöntemleriyle değerlendirilmeye çalışılmıştır. Analiz sonucunda özel sermayeli bankalarının kamu bankalarına oranla daha iyi bir performans sergilediği görülmüştür. Bu performans farkının temel sebebinin kamu bankalarının Covid-19 pandemi sürecinde hem hane halkını hem de başta KOBİ’ler olmak üzere işletmeleri düşük faizli kredilerle sübvanse etmeye çalışmasından dolayı kredi miktarları aynı düzeylerde artış gösterirken karlarının aynı düzeyde artmaması şeklinde ifade edilebilir.


  • Open Access

    Segmentation of orbital and periorbital lesions detected in orbital magnetic resonance imaging by deep learning method

    by Nevin Aydın, Suzan Saylısoy, Ozer Celik, Ahmet Faruk Aslan, Alper Odabas

    Introduction: Magnetic resonance imaging (MRI) has a special place in the evaluation of orbital and periorbital lesions. Segmentation is one of the deep learning methods. In this study, we aimed to perform segmentation in orbital and periorbital lesions.Material and methods: Contrast-enhanced orbital MRIs performed between 2010 and 2019 were retrospectively screened, and 302 cross-sections of contrast-enhanced, fat-suppressed, T1-weighted, axial MRI images of 95 patients obtained using 3 T and 1.5 T devices were included in the study. The dataset was divided into 3: training, test, and validation. The number of training and validation data was increased 4 times by applying data augmentation (horizontal, vertical, and both). Pytorch UNet was used for training, with 100 epochs. The intersection over union (IOU) statistic (the Jaccard index) was selected as 50%, and the results were calculated.Results: The 77th epoch model provided the best results: true positives, 23; false positives, 4; and false negatives, 8. The pre­cision, sensitivity, and F1 score were determined as 0.85, 0.74, and 0.79, respectively.Conclusions: Our study proved to be successful in segmentation by deep learning method. It is one of the pioneering studies on this subject and will shed light on further segmentation studies to be performed in orbital MR images.


  • Machine Learning Model to Diagnose Diabetes Type 2 Based on Health Behavior

    by Haithm Alshari̇, Alper Odabas

    Diabetes, in 2016, was the 7th death-causing disease in the world. It was the direct cause of 1.6 million deaths. In 2019, the number of adults (20-79 years) that were living with diabetes was approximately 463 million and is expected to rise to 700 million in 2045. The early diagnosis of diabetes will help treat it and prevent its complications. The need for an easy and fast way to diagnose diabetes is crucial. In this study, we are proposing a method to diagnose diabetes with the help of machine learning algorithms and tools. The proposed method utilizes the power of machine learning to create a model that can predict diabetes based on the health behavior of the patient. The model uses the relationship between a healthy lifestyle and diabetes. Our goal is to build a reliable machine learning model to predict diabetes, which will help significantly in easing and speeding up the diagnosing procedure of diabetes. We used modern machine learning algorithms like XGBoost, LightGBM, CatBoost, and artificial neural networks, and the dataset was obtained from the National Health and Nutrition Examination Survey (NHANES). In our study, the XGBoost algorithm performed the best with a Cross-Validation (10-fold) score of 0.864, and an overall accuracy of 87.7% for the validation dataset and 84.96% for the test dataset.


  • Performance of a convolutional neural network algorithm for tooth detection and numbering on periapical radiographs

    by Cansu Görürgöz, Kaan Orhan, Ibrahim Sevki Bayrakdar, Özer Çelik, Elif Bilgir, Alper Odabaş, Ahmet Faruk Aslan, Rohan Jagtap

    Objectives: The present study aimed to evaluate the performance of a Faster Region-based Convolutional Neural Network (R-CNN) algorithm for tooth detection and numbering on periapical images. Methods: The data sets of 1686 randomly selected periapical radiographs of patients were collected retrospectively. A pre-trained model (GoogLeNet Inception v3 CNN) was employed for pre-processing, and transfer learning techniques were applied for data set training. The algorithm consisted of: (1) the Jaw classification model, (2) Region detection models, and (3) the Final algorithm using all models. Finally, an analysis of the latest model has been integrated alongside the others. The sensitivity, precision, true-positive rate, and false-positive/negative rate were computed to analyze the performance of the algorithm using a confusion matrix. Results: An artificial intelligence algorithm (CranioCatch, Eskisehir-Turkey) was designed based on R-CNN inception architecture to automatically detect and number the teeth on periapical images. Of 864 teeth in 156 periapical radiographs, 668 were correctly numbered in the test data set. The F1 score, precision, and sensitivity were 0.8720, 0.7812, and 0.9867, respectively. Conclusion: The study demonstrated the potential accuracy and efficiency of the CNN algorithm for detecting and numbering teeth. The deep learning-based methods can help clinicians reduce workloads, improve dental records, and reduce turnaround time for urgent cases. This architecture might also contribute to forensic science.


  • Top Cited Papers
    Open Access

    A U‐Net Approach to Apical Lesion Segmentation on Panoramic Radiographs

    by Ibrahim S. Bayrakdar, Kaan Orhan, Özer Çelik, Elif Bilgir, Hande Sağlam, Fatma Akkoca Kaplan, Sinem Atay Görür, Alper Odabaş, Ahmet Faruk Aslan, Ingrid Różyło-Kalinowska

    The purpose of the paper was the assessment of the success of an artificial intelligence (AI) algorithm formed on a deep‐convolutional neural network (D‐CNN) model for the segmentation of apical lesions on dental panoramic radiographs. A total of 470 anonymized panoramic radiographs were used to progress the D‐CNN AI model based on the U‐Net algorithm (CranioCatch, Eskisehir, Turkey) for the segmentation of apical lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Eskisehir Osmangazi University. A U‐Net implemented with PyTorch model (version 1.4.0) was used for the segmentation of apical lesions. In the test data set, the AI model segmented 63 periapical lesions on 47 panoramic radiographs. The sensitivity, precision, and F1‐score for segmentation of periapical lesions at 70% IoU values were 0.92, 0.84, and 0.88, respectively. AI systems have the potential to overcome clinical problems. AI may facilitate the assessment of periapical pathology based on panoramic radiographs.


  • Top Cited Papers

    Deep-learning approach for caries detection and segmentation on dental bitewing radiographs

    by Ibrahim Sevki Bayrakdar, Kaan Orhan, Serdar Akarsu, Özer Çelik, Samet Atasoy, Adem Pekince, Yasin Yasa, Elif Bilgir, Hande Sağlam, Ahmet Faruk Aslan, et al.

    Objectives The aim of this study is to recommend an automatic caries detection and segmentation model based on the Convolutional Neural Network (CNN) algorithms in dental bitewing radiographs using VGG-16 and U-Net architecture and evaluate the clinical performance of the model comparing to human observer. Methods A total of 621 anonymized bitewing radiographs were used to progress the Artificial Intelligence (AI) system (CranioCatch, Eskisehir, Turkey) for the detection and segmentation of caries lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Ordu University. VGG-16 and U-Net implemented with PyTorch models were used for the detection and segmentation of caries lesions, respectively. Results The sensitivity, precision, and F-measure rates for caries detection and caries segmentation were 0.84, 0.81; 0.84, 0.86; and 0.84, 0.84, respectively. Comparing to 5 different experienced observers and AI models on external radiographic dataset, AI models showed superiority to assistant specialists. Conclusion CNN-based AI algorithms can have the potential to detect and segmentation of dental caries accurately and effectively in bitewing radiographs. AI algorithms based on the deep-learning method have the potential to assist clinicians in routine clinical practice for quickly and reliably detecting the tooth caries. The use of these algorithms in clinical practice can provide to important benefit to physicians as a clinical decision support system in dentistry.