3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Yayın Developing an efficient deep neural network for automatic detection of COVID-19 using chest X-ray images(Elsevier B.V., 2021-06) Sheykhivand, Sobhan; Mousavi, Zohreh; Mojtahedi, Sina; Yousefi Rezaii, Tohid; Farzamnia, Ali; Meshgini, Saeed; Saad, IsmailThe novel coronavirus (COVID-19) could be described as the greatest human challenge of the 21st century. The development and transmission of the disease have increased mortality in all countries. Therefore, a rapid diagnosis of COVID-19 is necessary to treat and control the disease. In this paper, a new method for the automatic identification of pneumonia (including COVID-19) is presented using a proposed deep neural network. In the proposed method, the chest X-ray images are used to separate 2–4 classes in 7 different and functional scenarios according to healthy, viral, bacterial, and COVID-19 classes. In the proposed architecture, Generative Adversarial Networks (GANs) are used together with a fusion of the deep transfer learning and LSTM networks, without involving feature extraction/selection for classification of pneumonia. We have achieved more than 90% accuracy for all scenarios except one and also achieved 99% accuracy for separating COVID-19 from healthy group. We also compared our deep proposed network with other deep transfer learning networks (including Inception-ResNet V2, Inception V4, VGG16 and MobileNet) that have been recently widely used in pneumonia detection studies. The results based on the proposed network were very promising in terms of accuracy, precision, sensitivity, and specificity compared to the other deep transfer learning approaches. Depending on the high performance of the proposed method, it can be used during the treatment of patients.Yayın Surface modification of titanium using BSA-Loaded chitosan and chitosan/gelatin polymers(Springer Berlin Heidelberg, 2016-10) Önder, SakipThe integration of titanium-based implants with the surrounding bone tissue needs to be improved to increase their service life. This work presents a surface modification technique to increase the osteointegration of titanium implants. The studies were conducted in three main steps: (i) surface modification of titanium using bovine serum albumin (BSA)-loaded chitosan and chitosan/gelatin polymers, (ii) studies of BSA release from these surfaces, (iii) effect of porosity and polymer composition on osteoblast cell proliferation. TiO2 and COOH groups were formed on titanium surfaces. Then, chitosan and chitosan (C)/gelatin (G) with various ratios (G:C = 0.5:1, 1:1, 1:0.5) were mixed with BSA and fixed to the surface via carbodiimide chemistry (EDC/NHS). After the immobilization process, samples were exposed to either air or freeze-drying. Characterization studies were conducted using Fourier transform-infrared spectroscopy and scanning electron microscopy. Finally, BSA release studies in phosphate-buffered saline (0.1 M, 37 °C) and cell (osteoblast) proliferation studies using MTS assay were conducted. BSA-loaded porous structures were obtained on chitosan- and chitosan/gelatin-containing surfaces after freeze-drying, while smooth surfaces were obtained after air-drying. The BSA release rate was directly correlated with increasing gelatin amount in the chitosan/gelatin coatings. MTS analysis was not conclusive because of the absorption properties of polymer coatings. However, absorbed color density in chitosan/gelatin (G:C = 1:1) polymers under freeze-drying conditions was more dominant, indicating better cell proliferation. This method may be used to release growth factors for controlled cell proliferation and differentiation or for the local delivery of antimicrobial drugs to prevent contamination during implementation in hard tissue applications.Yayın Effect of magnesium and osteoblast cell presence on hydroxyapatite formation on (Ti,Mg)N thin film coatings(Springer, 2016-07-19) Önder, Sakip; Çalıkoğlu Koyuncu, Ayşe Ceren Eren; Köse, Gamze Torun; Kazmanlı, Kürşat Muhammet; Kök, Fatma Neşe; Ürgen, MustafaTiN and (Ti,Mg)N thin film coatings were deposited on Ti substrates by an arc-physical vapor deposition technique. The effect of cell presence on hydroxyapatite (HA) formation was investigated using surfaces with four different Mg contents (0, 8.1, 11.31, and 28.49 at.%). Accelerated corrosion above 10 at.% Mg had a negative effect on the performance in terms of both cell proliferation and mineralization. In the absence of cells, Mg-free TiN coatings and low-Mg (8.1 at.%)-doped (Ti,Mg)N surfaces led to an early HA deposition (after 7 days and 14 days, respectively) in cell culture medium (DMEM), but the crystallinity was low. More crystalline HA structures were obtained in the presence of the cells. HA deposits with an ideal Ca/P ratio were obtained at least a week earlier, at day 14, in TiN and low-Mg (8.1 at.%)-doped (Ti,Mg)N compared with that of high-Mg-containing surfaces (>10 at.%). A thicker mineralized matrix was formed on low-Mg (8.1 at.%)-doped (Ti,Mg)N relative to that of the TiN sample. Low-Mg doping (<10 at.%) into TiN coatings resulted in better cell proliferation and thicker mineralized matrix formation, so it could be a promising alternative for hard tissue applications.
