Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleAçık Erişim2023Detection of COVID-19 infection from CT images using the medical photogrammetry technique
Çatal Reis, Hatice; Türk, Veysel; Kaya, Serhat
Medical data such as computed tomography (CT), magnetic resonance imaging (MRI), and Ultrasound images are used in medical photogrammetry. CT images have been used frequently in recent years for the diagnosis of COVID-19 disease, which has contagious and fatal symptoms. CT is an effective method for early detection of lung anomalies due to COVID-19 infection. Machine learning (ML) techniques can be used to detect and diagnose medical diseases. In particular, classification methods are applied for disease diagnosis and diagnosis. This study proposes traditional machine learning algorithms Random Forest, Logistic Regression, K-Nearest Neighbor and Naive Bayes, and an ensemble learning model to detect COVID-19 anomalies using CT images. According to the experimental findings, the proposed ensemble learning model produced an accuracy of 96.71%. This study can help identify the fastest and most accurate algorithm that predicts CT images with Covid-19 during the epidemic process. In addition, machine learning-based approaches can support healthcare professionals and radiologists in the diagnostic phase.
- MakaleYalnız künye2021Determination of Land Use Change using Support Vector Machines: A Case Study of Arnavutkoy, Istanbul
Çatal Reis, Hatice; Yılancı, Gulsena
As a result of the development of cities and inclination towards urbanization, natural areas decreased while urban areas increased. In this respect, determination of impermeable surfaces is important for the problems covering; effects of urbanization on natural environment, global environmental variation, urban atmospheric process, human activities and the effects of urbanization on the environment. Remote sensing images are used to examine and classify land cover/uses. Traditional classification methods are mainly divided into supervised classification and unsupervised classification. The aim of this study is to classify land cover/use and to state temporal change using the Support Vector Machines (SVM) approach, which is a supervised classification method. Arnavutkoy district of Istanbul was chosen as the study area for land use and change detection analysis. Landsat 5/7/8 satellite images of Arnavutkoy district were obtained and SVM process was applied to obtain these images. Firstly, four classes were created for each image: urban areas, vegetation, bare soils and wetlands SVM was applied and accuracy analysis was performed to the images classes of which were created before. CAD software and GIS software were used for image processing. The classification accuracy for SVM was found to be 98.66%, 98.31%, 98.95%, 97.99%, 96.37%, 97.90% (from 1995 to 2019). In addition, ROC analysis was used for comparison of accuracy analysis. As a result of this study, land cover/use change of Arnavutkoy district in the last 20 years has been determined. The urban area of the district was 40.99 km2in 1995 and 93.76 km2in 2019. In addition, the impact of the Europe's largest airport on land cover / use has been examined. The results showed that the accuracy of using SVM to classify land use/cover is high. Therefore, it has been proposed that this algorithm is used as an optimal classifier for land use/cover maps.
- MakaleAçık Erişim2020Comparison of two plain radiographic and 3D-based measurement methods for posterior malleolar fragment size in trimalleol ankle fractures
Altun, Güray; Çatal Reis, Hatice; Bayram, Bülent; Saka, Gursel
Aim: The aim of this study is, to compare the posterior malleolar fragment (PMF) sizing between lateral ankleradiography measurement and computer assistted 3D modelling (CA3DM) methodsMethods: Fifty-one patients between january 2015 and november 2018 with posterior malleolar fractured wereincluded in this study. The rate of PMF to the articular surface at the distal end of the tibia was calculated by twodifferent imaging methods by two surgeons. According to posterior fragment size, patients were separated intotwo groups. Group 1 was consisted of posterior fragment size smaller than 15% and group 2 was bigger than15% due to CA3DM.Results: The interobserver correlation (IOC) between two observers and CA3DM was 44.3%. Also the IOCbetween first observer and CA3DM was 35.7% (p<0.05), second observer and CA3DM were 46.6% (p<0.01)and observers was 51.6% (p<0.01). For group 1, IOC between two observers and CA3DM was 41.2% (p<0.05),first observer and CA3DM was 30.6% (p>0.05), second observer and CA3DM was 51.6% (p<0.05) and twoobservers were 45.8% (p<0.05). For group 2, IOC between two observers and CA3DM was 27.9% (p>0.05),first and CA3DM was 18.6% (p>0.05), second observer and CA3DM was 7.1% (p>0.05) and two observers was49% (p<0.05).Conclusion: Our study shows that posterior malleolar fragment size measuring on plain radiography is not a safemethod for bigger fragments and CA3DM method may be a more reliable to assess correct fragment size andalso to analyze fracture morphology. But for fragments ≤15% CA3DM and plain radiographic measures are notstatistically different.