Yazar "Urhan, Oğuzhan" seçeneğine göre listele
Listeleniyor 1 - 6 / 6
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Two-Headed Deep Learning Framework for Predicting Severity of COVID-19 Disease(2021) Öksüz, Çoşku; Urhan, Oğuzhan; Güllü, Mehmet KemalIntroduction-Objectives: The high contagiousness of the SARS-COV-2 virus has resulted in many people being infected worldwide. In many countries, the capacity of intensive care units has been insufficient and has become unable to accept new patients. Imaging-based non-invasive methods developed as an alternative to the RT-PCR technique to control the spread of the virus during the pandemic process generally focus on the presence or absence of the disease. However, these methods do not provide information about how severe the disease is and how it progresses. Therefore, in this study, a deep learning-based estimation framework with low computational load is proposed to predict severity scores using chest radiographs. Materials-Methods: The pre-trained ImageNet models are used as feature extraction networks to extract generic features. A two-headed estimation subnetwork each with the same number of layers is created to learn taskspecific features. Eventually, an end-to-end trainable lightweight deep model is created by connecting the estimation subnetwork to the feature extraction network. Results: The proposed model is evaluated on a publicly available Cohen’s covid-chestxray-data set. The best cross-validation performance in terms of RMSE, MAE, and R2 in the prediction of lung involvement and opacity is obtained as 1.39/0.98, 1.1/0.81, 0.65/0.66, respectively. Conclusions: Although the model has been trained with limited data, promising results are achieved with an end-to-end framework for estimating the severity of the COVID-19 disease.Öğe Brain tumor classification using the fused features extracted from expanded tumor region(Elsevier Sci Ltd, 2022) Öksüz, Coşku; Urhan, Oğuzhan; Güllü, Mehmet KemalIn this study, a brain tumor classification method using the fusion of deep and shallow features is proposed to distinguish between meningioma, glioma, pituitary tumor types and to predict the 1p/19q co-deletion status of LGG tumors. Brain tumors can be located in a different region of the brain, and the texture of the surrounding tissues may also vary. Therefore, the inclusion of surrounding tissues into the tumor region (ROI expansion) can make the features more distinctive. In this work, pre-trained AlexNet, ResNet-18, GoogLeNet, and ShuffleNet networks are used to extract deep features from the tumor regions including its surrounding tissues. Even though the deep features are extremely important in classification, some low-level information regarding tumors may be lost as the network deepens. Accordingly, a shallow network is designed to learn low-level information. Next, in order to compensate the information loss, deep features and shallow features are fused. SVM and k-NN classifiers are trained using the fused feature sets. Experimental results achieved on two publicly available data sets demonstrate that using the feature fusion and the ROI expansion at the same time improves the average sensitivity by about 11.72% (ROI expansion: 8.97%, feature fusion: 2.75%). These results confirm the assumption that the tissues surrounding the tumor region carry distinctive information. Not only that, the missing low-level information can be compensated thanks to the feature fusion. Moreover, competitive results are achieved against state-of-the-art studies when the ResNet-18 is used as the deep feature extractor of our classification framework.Öğe COVID-19 detection with severity level analysis using the deep features, and wrapper-based selection of ranked features(Wiley, 2021) Öksüz, Coşku; Urhan, Oğuzhan; Güllü, Mehmet KemalThe SARS-COV-2 virus, which causes COVID-19 disease, continues to threaten the whole world with its mutations. Many methods developed for COVID-19 detection are validated on the data sets generally including severe forms of the disease. Since the severe forms of the disease have prominent signatures on X-ray images, the performance to be achieved is high. To slow the spread of the disease, effective computer-assisted screening tools with the ability to detect the mild and the moderate forms of the disease that do not have prominent signatures are needed. In this work, various pretrained networks, namely GoogLeNet, ResNet18, SqueezeNet, ShuffleNet, EfficientNetB0, and Xception, are used as feature extractors for the COVID-19 detection with severity level analysis. The best feature extraction layer for each pre-trained network is determined to optimize the performance. After that, features obtained by the best layer are selected by following a wrapper-based feature selection strategy using the features ranked based on Laplacian scores. The experimental results achieved on two publicly available data sets including all the forms of COVID-19 disease reveal that the method generalized well on unseen data. Moreover, 66.67%, 90.32%, and 100% sensitivity are obtained in the detection of mild, moderate, and severe cases, respectively.Öğe Ensemble-LungMaskNet: Automated lung segmentation using ensembled deep encoders(Institute of Electrical and Electronics Engineers Inc., 2021) Öksüz, Coşku; Urhan, Oğuzhan; Güllü, Mehmet KemalAutomated lung segmentation has importance because it gives clues about several diseases to the experts. It is the step that comes before further detailed analyses of the lungs. However, segmentation of the lungs is a challenging task since the opacities and consolidations are caused by various lung diseases. As a result, the clarity of the borders of the lungs may be lost which makes the segmentation task difficult. The presence of various medical equipment such as cables in the image is another factor that makes segmentation difficult. Therefore, it is a necessity to develop methods that can handle such situations. Learning the most useful patterns related to various diseases is possible with deep learning methods. Unlike conventional methods, learning the patterns improves the generalization ability of the models on unseen data. For this purpose, a deep segmentation framework including ensembles of pre-trained lightweight networks is proposed for lung region segmentation in this work. The experimental results achieved on two publicly available data sets demonstrate the effectiveness of the proposed framework. © 2021 IEEE.Öğe Hiperspektral Görüntülerin Alt-Örnekleme, Katışım Analizi Ve Bölütleme Temelli Yaklaşımlarla Sıkıştırılması(2019) Güllü, Mehmet Kemal; Urhan, Oğuzhan; Can, Ergün; Ertem, AdemHiperspektral görüntüler, elektromanyetik spektrumun mor üstünden kızılötesine kadar yüzlerce dar spektral banttan oluşan yüksek boyutlu verilerdir. Bu eşsiz yüksek spektral bant çözünürlüğü sayesinde, arazi sınıflandırma, maden haritalama, tarımsal görüntüleme, malzeme sınıflandırma, hedef tespiti, değişim tespiti gibi geniş araştırma alanları ve gerçek hayat uygulamaları gibi alanlarda üstünlükler oluşturmaktadır. Hiperspektral görüntünün boyutu, uzamsal olarak taranan alanın kaç piksel üzerinden temsil edildiğine, bit derinliğine ve algılayıcının sağladığı spektral bant sayısına bağlı olarak değişmektedir. Örneğin, NASA?nın görünür/kızılötesi görüntüleme spektrometresinde (AVIRIS) 224 spektral bant içermekte ve görüntünün uzamsal çözünürlüğü düşük olmasına rağmen, alınan görüntünün boyutu gigabaytlar mertebesine erişebilmektedir. Bu durum, veri iletiminde daha yüksek bant genişliği ihtiyacı doğurmaktadır. Ayrıca, verinin saklanmasında daha fazla bellek ihtiyacı anlamına gelmektedir. Bu nedenlerden dolayı, hiperspektral görüntülerin sıkıştırılması son yıllarda önemli araştırma alanlarından biri halini almıştır. Hiperspektral görüntü sıkıştırma kayıplı ya da kayıpsız yapılabileceği gibi, bu yöntemler temelde tahmin, vektör nicemleme ve dönüşüm kodlama yöntemleri olmak üzere üç ayrı gruba ayrılmaktadır. Bu proje kapsamında, hiperspektral görüntülerin kayıplı ve kayıpsız sıkıştırılması için özgün yaklaşımların geliştirilmesi ile sıkıştırma verimliliğinin arttırılması amaçlanmaktadır. Bu amaç doğrultusunda, (i) uzamsal/spektral alt-örnekleme, (ii) spektral karışım analizi, (iii) süperpiksel bölütleme temelli ve (iv) tahmin temelli olmak üzere dört farklı sıkıştırma yaklaşımları bu proje kapsamında ele alınmıştır. Bu yaklaşımlar için oran?bozunum ve sıkıştırma oranı gibi ölçütlerin yanında, sıkıştırılan hiperspektral görüntüler üzerinden gerçekleştirilecek sınıflandırma, bölütleme ve anomali tespiti gibi işlemler ile geliştirilecek sıkıştırma yöntemlerinin performansları incelenmiştir.Öğe Technology Trends in Building a Data-Driven Smart City(Kocaeli Büyükşehir Belediyesi, 2023) Urhan, Oğuzhan; Güllü, KemalIn this study, the concept of smart city, whose applications have been increasing day by day in the last 20 years with the developing technology, has been assessed in a comprehensive way. In this framework, starting from the definition of smart city, the need for this scope has been examined. Technologies that can be used for this purpose and their possible usage scenarios are discussed. Finally, by evaluating smart city applications in our country and abroad, suggestions have been made for data-based city management and increasing the efficiency of these applications.
