Browsing by Author "Oksuz C., Urhan O., Gullu M.K."

Now showing 1 - 2 of 2

A lightweight deep model for brain tumor segmentation
(2021-06-09) Oksuz C., Urhan O., Gullu M.K.; Oksuz, C, Urhan, O, Gullu, MK
Brain tumors are one of the major causes of increasing deaths worldwide. It is important to correctly identify cancerous tissues by experts in order to make correct treatment planning and to increase patient survival rates. However, manually tracking and segmentation of cancerous tissues in many sections of volumetric MR data is an error-prone and time-consuming process. Developments in the field of deep learning in recent years allow the tasks performed by humans to be performed with higher accuracy and speeds through the developed automatic systems. In this study, a deep learning-based light-weighted model with 6.78M parameters is proposed for the classification of cancerous tissues in the brain. Cross-validation of the proposed method on a public data set results in 84.61%, 82.54%, and 87.15% Boundary F1, mean IoU, and mean accuracy, respectively, shows the robustness of the proposed model.
Ensemble-LungMaskNet: Automated lung segmentation using ensembled deep encoders
(2021-08-25) Oksuz C., Urhan O., Gullu M.K.
Automated 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.