Browsing by Author "Koplay, Mustafa"

Now showing 1 - 12 of 12

Adrenal Lesion Classification on T1-Weighted Abdomen Images With Convolutional Neural Networks
(2022) Solak, Ahmet; Ceylan, Rahime; Bozkurt, Mustafa Alper; Cebeci, Hakan; Koplay, Mustafa
Adrenal lesions are usually discovered incidentally during other health screenings and are usually benign. However, it is vital to take precautions when a malignant adrenal lesion is detected. Especially deep learning models developed in the last ten years give successful results on medical images. In this paper, adrenal lesion characterization on T1-weighted magnetic resonance abdomen images was aimed using convolutional neural network (CNN) which is one of the deep learning methods. Firstly, effects of important model parameters are assessed on performance of CNN, so optimum CNN model is obtained for classification of adrenal lesions. For a fixed number of convolution filters determined in the first stage of the study, CNN model implemented by different kernel sizes were trained. According to the best result obtained, this time the kernel size was kept constant, and experiments were made for different filter numbers. Finally, studies were carried out with CNN structures of different depths and the results were compared. As a result of the studies, when filter is selected as [5 20], the best results in the trainings conducted with a single-block CNN structure are obtained 0.97, 0.90, 0.98, 0.90, 0.90, and 0.94, for accuracy, sensitivity, specificity, precision, F1-score, and AUC score, respectively. The study was compared with the studies in the literature, and it was seen that it was superior to them.
Citation - WoS: 2
Citation - Scopus: 2
Adrenal Lesion Classification With Abdomen Caps and the Effect of Roi Size
(Springer, 2023) Solak, Ahmet; Ceylan, Rahime; Bozkurt, Mustafa Alper; Cebeci, Hakan; Koplay, Mustafa
Accurate classification of adrenal lesions on magnetic resonance (MR) images are very important for diagnosis and treatment planning. The detection and classification of lesions in medical imaging heavily rely on several key factors, including the specialist's level of experience, work intensity, and fatigue of the clinician. These factors are critical determinants of the accuracy and effectiveness of the diagnostic process, which in turn has a direct impact on patient health outcomes. With the spread of artificial intelligence, the use of computer-aided diagnosis (CAD) systems in disease diagnosis has also increased. In this study, adrenal lesion classification was performed using deep learning on MR images. The data set used was obtained from the Department of Radiology, Faculty of Medicine, Selcuk University, and all adrenal lesions were identified and reviewed in consensus by two radiologists experienced with abdominal MR. Studies were carried out on two different data sets created by T1- and T2-weighted MR images. The data set consisted of 112 benign and 10 malignant lesions for each mode. Experiments were performed with regions of interest (ROIs) of different sizes to increase the working performance. Thus, the effect of the selected ROI size on the classification performance was assessed. In addition, instead of the convolutional neural network (CNN) models used in deep learning, a unique classification model structure called Abdomen Caps was proposed. When the data sets used in classification studies are manually separated for training, validation, and testing, different results are obtained with different data sets for each stage. To eliminate this imbalance, tenfold cross-validation was used in this study. The best results obtained were 0.982, 0.999, 0.969, 0.983, 0.998, and 0.964 for accuracy, precision, recall, F1-score, area under the curve (AUC) score, and kappa score, respectively.
Citation - WoS: 5
Citation - Scopus: 6
Adrenal Tumor Characterization on Magnetic Resonance Images
(WILEY, 2020) Barstuğan, Mücahid; Ceylan, Rahime; Asoğlu, Semih; Cebeci, Hakan; Koplay, Mustafa
Adrenal tumors occur on adrenal glands and are generally detected on abdominal area scans. Adrenal tumors, which are incidentally detected, release vital hormones. These types of tumors that can be malignant affect body metabolism. Both of benign and malign adrenal tumors can have a similar size, intensity, and shape, this situation may lead to wrong decision during diagnosis and characterization of tumors. Thus, biopsy is done to confirm diagnosis of tumor types. In this study, adrenal tumor characterization is handled by using magnetic resonance images. In this way, it is wanted that patient can be disentangled from one or more imaging modalities (some of them can includes X-ray) and biopsy. An adrenal tumor image set, which includes five types of adrenal tumors and has 112 benign tumors and 10 malign tumors, was used in this study. Two data sets were created from the adrenal tumor image set by manually/semiautomatically segmented adrenal tumors and feature sets of these data sets are constituted by different methods. Two-dimensional gray-level co-occurrence matrix (2D-GLCM), gray-level run-length matrix (GLRLM), and two-dimensional discrete wavelet transform (2D-DWT) methods were analyzed to reveal the most effective features on adrenal tumor characterization. Feature sets were classified in two ways: benign/malign (binary classification) and type characterization (multiclass classification). Support vector machine and artificial neural network classified feature sets. The best performance on benign/malign classification was obtained by the 2D-GLCM feature set. The best results were assessed with sensitivity, specificity, accuracy, precision, and F-score metrics and they were 99.17%, 90%, 98.4%, 99.17%, and 99.13%, respectively. The highest classification performance on type characterization was obtained by the 2D-DWT feature set as 59.62%, 96.17%, 93.19%, 54.69%, and 54.94% for sensitivity, specificity, accuracy, precision, and F-score metrics, respectively.
Adrenal Tumor Classification on T1 and T2-Weighted Abdominal Mr Images
(Institute of Electrical and Electronics Engineers Inc., 2019) Barstuğan, Mücahid; Ceylan, Rahime; Asoğlu, Semih; Cebeci, Hakan; Koplay, Mustafa
Adrenal tumors occur on adrenal glands and can be malignant. Adrenal glands consist of cortex and medulla. If cortex or medulla produce hormones extremely, the hormonal unbalance situation arises. This situation causes adrenal tumor occurrence on adrenal glands. In this study, adrenal tumors on T1 and T2-weighted MR images were classified by the SVM algorithm. Before the classification stage, different feature extraction algorithms and filtering methods were used for preprocessing. The classification results that were obtained by four different methods were evaluated on five different evaluation metrics as sensitivity, specificity, accuracy, precision, and F-score. The best classification performance was obtained with Method 2 on T1-weighted MR (Magnetic Resonance) images where the sensitivity, specificity, accuracy, precision, and F-score metrics were obtained as 99.17%, 90%, 98.4%, 99.17%, and 99.13%, respectively. © 2019 IEEE.
Citation - WoS: 9
Citation - Scopus: 11
Adrenal Tumor Segmentation Method for Mr Images
(ELSEVIER IRELAND LTD, 2018) Barstuğan, Mücahid; Ceylan, Rahime; Asoğlu, Semih; Cebeci, Hakan; Koplay, Mustafa
Background and objective: Adrenal tumors, which occur on adrenal glands, are incidentally determined. The liver, spleen, spinal cord, and kidney surround the adrenal glands. Therefore, tumors on the adrenal glands can be adherent to other organs. This is a problem in adrenal tumor segmentation. In addition, low contrast, non-standardized shape and size, homogeneity, and heterogeneity of the tumors are considered as problems in segmentation. Methods: This study proposes a computer-aided diagnosis (CAD) system to segment adrenal tumors by eliminating the above problems. The proposed hybrid method incorporates many image processing methods, which include active contour, adaptive thresholding, contrast limited adaptive histogram equalization (CLAHE), image erosion, and region growing. Results: The performance of the proposed method was assessed on 113 Magnetic Resonance (MR) images using seven metrics: sensitivity, specificity, accuracy, precision, Dice Coefficient, Jaccard Rate, and structural similarity index (SSIM). The proposed method eliminates some of the discussed problems with success rates of 74.84%, 99.99%, 99.84%, 93.49%, 82.09%, 71.24%, 99.48% for the metrics, respectively. Conclusions: This study presents a new method for adrenal tumor segmentation, and avoids some of the problems preventing accurate segmentation, especially for cyst-based tumors. (C) 2018 Elsevier B.V. All rights reserved.
Citation - Scopus: 1
Adrenal Tumor Segmentation on U-Net: a Study About Effect of Different Parameters in Deep Learning
(World Scientific Publ Co Pte Ltd, 2023) Solak, Ahmet; Ceylan, Rahime; Bozkurt, Mustafa Alper; Cebeci, Hakan; Koplay, Mustafa
Adrenal lesions refer to abnormalities or growths that occur in the adrenal glands, which are located on top of each kidney. These lesions can be benign or malignant and can affect the function of the adrenal glands. This paper presents a study on adrenal tumor segmentation using a modified U-Net model with various parameter selection strategies. The study investigates the effect of fine-tuning parameters, including k-fold values and batch sizes, on segmentation performance. Additionally, the study evaluates the effectiveness of different preprocessing techniques, such as Discrete Wavelet Transform (DWT), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Image Fusion, in enhancing segmentation accuracy. The results show that the proposed model outperforms the original U-Net model, achieving the highest scores for Dice, Jaccard, sensitivity, and specificity scores of 0.631, 0.533, 0.579, and 0.998, respectively, on the T1-weighted dataset with DWT applied. These results highlight the importance of parameter selection and preprocessing techniques in improving the accuracy of adrenal tumor segmentation using deep learning.
Citation - WoS: 11
Citation - Scopus: 10
An Extensive Study for Binary Characterisation of Adrenal Tumours
(SPRINGER HEIDELBERG, 2019) Koyuncu, Hasan; Ceylan, Rahime; Asoğlu, Semih; Cebeci, Hakan; Koplay, Mustafa
On adrenal glands, benign tumours generally change the hormone equilibrium, and malign tumours usually tend to spread to the nearby tissues and to the organs of the immune system. These features can give a trace about the type of adrenal tumours; however, they cannot be observed all the time. Different tumour types can be confused in terms of having a similar shape, size and intensity features on scans. To support the evaluation process, biopsy process is applied that includes injury and complication risks. In this study, we handle the binary characterisation of adrenal tumours by using dynamic computed tomography images. Concerning this, the usage of one more imaging modalities and biopsy process is wanted to be excluded. The used dataset consists of 8 subtypes of adrenal tumours, and it seemed as the worst-case scenario in which all handicaps are available against tumour classification. Histogram, grey level co-occurrence matrix and wavelet-based features are investigated to reveal the most effective one on the identification of adrenal tumours. Binary classification is proposed utilising four-promising algorithms that have proven oneself on the task of binary-medical pattern classification. For this purpose, optimised neural networks are examined using six dataset inspired by the aforementioned features, and an efficient framework is offered before the use of a biopsy. Accuracy, sensitivity, specificity, and AUC are used to evaluate the performance of classifiers. Consequently, malign/benign characterisation is performed by proposed framework, with success rates of 80.7%, 75%, 82.22% and 78.61% for the metrics, respectively.
Citation - Scopus: 1
Full-Automatic Liver Segmentation on Abdominal Mr Images
(IEEE, 2018) Barstuğan, Mücahid; Ceylan, Rahime; Asoğlu, Semih; Cebeci, Hakan; Koplay, Mustafa
Liver segmentation process is a challenging field in computer-aided medical image analysis. This study implemented liver segmentation on Abdominal MR images. The liver was automatically segmented from images by morphological methods with high performance. Liver segmentation process was implemented on 56 MR images and the segmentation results were examined. In this study, an effective and fast method was proposed. Seven evaluation metrics (sensitivity, specificity, accuracy, precision, Dice coefficient, Jaccard rate, Structural Similarity Index (SSIM)) were used to test the performance of the proposed method. Mean Dice coefficient value was obtained as 91.701%, mean Jaccard rate value was obtained as 85.052% on 56 images. Segmentation duration for an image (T1 and T2 phases) was found as 2.828 seconds with the proposed method.
Citation - WoS: 1
Citation - Scopus: 1
A Novel Deep Learning Model for Pancreas Segmentation: Pascal U-Net
(Asoc Espanola Inteligencia Artificial, 2024) Kurnaz, Ender; Ceylan, Rahime; Bozkurt, Mustafa Alper; Cebeci, Hakan; Koplay, Mustafa
A robust and reliable automated organ segmentation from abdomen images is a crucial problem in both quantitative imaging analysis and computer-aided diagnosis. In particular, automatic pancreas segmentation from abdomen CT images is the most challenging task based on two main aspects (1) high variability in anatomy (like as shape, size, etc.) and location across different patients and (2) low contrast with neighbouring tissues. Due to these reasons, the achievement of high accuracies in pancreas segmentation is a hard image segmentation problem. In this paper, we propose a novel deep learning model which is a convolutional neural network-based model called Pascal U-Net for pancreas segmentation. The performance of the proposed model is evaluated on The Cancer Imaging Archive (TCIA) Pancreas CT database and abdomen CT dataset which is taken from Selcuk University Medicine Faculty Radiology Department. During the experimental studies, the k-fold cross-validation method is used. Furthermore, the results of the proposed model are compared with the results of traditional U-Net. If results obtained by Pascal U-Net and traditional U-Net for different batch sizes and fold number is compared, it can be seen that experiments on both datasets validate the effectiveness of the Pascal U-Net model for pancreas segmentation.
Citation - WoS: 2
Citation - Scopus: 2
A Novel Study for Automatic Two-Class and Three-Class Covid-19 Severity Classification of Ct Images Using Eight Different Cnns and Pipeline Algorithm
(Ediciones Univ Salamanca, 2023) Yaşar, Hüseyin; Ceylan, Murat; Cebeci, Hakan; Kılınçer, Abidin; Seher, Nusret; Kanat, Fikret; Koplay, Mustafa
SARS-CoV-2 has caused a severe pandemic worldwide. This virus appeared at the end of 2019. This virus causes respiratory distress syndrome. Computed tomography (CT) imaging provides important radiological information in the diagnosis and clinical evaluation of pneumonia caused by bacteria or a virus. CT imaging is widely utilized in the identification and evaluation of COVID-19. It is an important requirement to establish diagnostic support systems using artificial intelligence methods to alleviate the workload of healthcare systems and radiologists due to the disease. In this context, an important study goal is to determine the clinical severity of the pneumonia caused by the disease. This is important for determining treatment procedures and the follow-up of a patient's condition. In the study, automatic COVID-19 severity classification was performed using three -class (mild, moderate, and severe) and two -class (nonsevere and severe). In the study, deep learning models were used for classification. Also, CT images were utilized as radiological images.
Citation - WoS: 3
Citation - Scopus: 2
A Novel Study To Increase the Classification Parameters on Automatic Three-Class Covid-19 Classification From Ct Images, Including Cases From Turkey
(Taylor & Francis Ltd, 2022) Yaşar, Hüseyin; Ceylan, Murat; Cebeci, Hakan; Kılınçer, Abidin; Kanat, Fikret; Koplay, Mustafa
A computed tomography (CT) scan is an important radiological imaging method in diagnosing pneumonia caused by SARS-CoV-2. Within the scope of the study, three classes of automatic classification - COVID-19 pneumonia, healthy, and other pneumonia - were carried out. Using deep learning as a classifier, a total of 6,377 CT images were used, including 3,364 COVID-19 pneumonia, 1,766 healthy, and 1,247 other pneumonia images. A total of seven architectures, including the most recent convolutional neural network (CNN) architectures, MobileNetV2, ResNet-101, Xception, Inceptionv3, GoogLeNet, EfficientNetB0, and DenseNet201, were used in the study. The classification results were obtained using the CT images, and they were calculated using the feature images obtained by applying local binary patterns on the CT images. The results were then combined with the help of a pipeline algorithm. The results revealed that the best overall accuracy result obtained by using CNN architectures could be improved by 4.87% with a two-step pipeline algorithm. In addition, significant improvements were achieved in all other measurement parameters within the scope of the study. At the end of the study, the highest sensitivity, specificity, accuracy, F-1 score, and Area under the Receiver Operating Characteristic Curve (AUC) values obtained for the COVID-19 pneumonia class were 0.9004, 0.8901, 0.8956, 0.9010, and 0.9600, respectively. The highest overall accuracy value was 0.8332. The most important output of the work carried out is the demonstration that the results obtained with the most successful CNN architectures used in previous studies can be significantly improved thanks to pipeline algorithms.
Perkütan Böbrek Taşı Operasyonunda Artırılmış Gerçeklik Yöntemi Kullanan ve Hesaplanan Giriş Noktası, Yönelim & Giriş Açısına Göre Pozisyon Alan Elektromekanik Manipülatör Kollu Cihazın Geliştirilmesi
(2021) Kılıç, Özcan; Önen, Ümit; Koplay, Mustafa; Kocer, Hasan Erdinc; Civcik, Levent
Üriner sistem taş hastalığı hem ülkemiz hem de dünya için önemli bir halk sağlığı problemi olup prevelansı giderek artmaktadır. Günümüzde daha çok endoskopik yöntemlerle tedavi edilmektedir ve perkütan nefrolitotripsi (PCNL) büyük (özellikle ?2 cm) taşlar, çok sayıda veya kompleks yapıda (koraliform) taşlar ve taş kırmaya dirençli daha küçük boyuttaki taşların tedavisinde ilk sırada önerilmektedir. Yüksek başarı oranı olan bu minimal invazif yöntemin ne yazık ki renal vasküler ve komşu organ yaralanması gibi ciddi sonuçlar doğurabilecek komplikasyonları mevcuttur. Bu projede PCNL operasyonunda hem ameliyatın ilk ve en önemli aşaması olan toplayıcı sistemin içine girişi kolaylaştıracak hem de buna bağlı olarak komplikasyonları azaltabilecek, geliştirilen yazılım ile hesaplanan giriş noktası, yönelim açısı ve giriş açısına göre pozisyon alan elektromekanik manipülatör kollu bir cihaz geliştirilmiştir. Bunun için önce kliniğimizde PCNL uygulanacak hastaların bilgisayarlı tomografi (BT) görüntülerinden elde edilen data ile giriş açısı, yönelim açısı ve giriş noktasını hesaplamaya yönelik matematiksel formül ve yazılım geliştirilmiştir. Daha sonra iki boyutlu (2B) BT görüntüleri üç boyutlu (3B) formata çevrilmiş olup giriş noktası, giriş açısı ve yönelim açısı hesaplanıp 3B modellemede yerlerine yerleştirilmiştir. Üç mafsal ve iki açı konumlanması şeklinde yapılan tasarımda dairesel hareket yapan step motorlu 2 ana kol, dikey yönde yukarı aşağı hareketi sağlayan step motorlu dişli mil mekanizması ve açısal konumlanmayı sağlayacak olan 2 adet servo motorlu mekanizma yer almıştır. Manipülatör kolun uç kısmı için servo motorların tümleşik kullanımına yönelik özel tutucu tasarımı yapılmış ve 3B yazıcıda bastırılmıştır. Geliştirilen sistem insan maketi içine yerleştirilen gerçek böbrek taşı üzerinde test edilmiştir. BT görüntülerinden elde edilen bilgiler ile giriş noktası, giriş açısı ve yönelim açısı matematiksel hesaplama yazılımında hesaplanıp bu bilgiler robotik kola iletilmiştir. Gelen bilgilere göre robotik sıfır noktasından ciltten giriş yapılması gereken noktaya konumlanmıştır. Bu noktadan giriş iğnesi hesaplanan açıya göre ilerletilip maketin tekrar BT?si çekilmiştir. Yapılan hesaplamada taş ile iğne ucu arasında 2.9 mm?lik bir sapma olduğu belirlenmiştir. Yeni elektromekanik manipülatör kol ile daha önce geliştirilen robotik kollara benzer sonuç elde edilmiştir. Bu ümit vaat edici sonuçlar ışığında geliştirilen sistemin yapılması planlanan iyileştirmeler ile hayvan ve insan deneylerine hazır olacağı kanaatindeyiz.