Akademik Veri Yönetim Sistemi
2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024, Suzhou, Çin, 22 - 23 Ağustos 2024, cilt.1316 LNNS, ss.287-294, (Tam Metin Bildiri)
Lung segmentation has become a bedrock in the effective diagnosis, and classification of coronavirus (COVID-19) from radiological images such as computed tomography (CT) and X-ray images. Since the coronavirus (COVID-19) discovery, several methods have been employed to segment the COVID-19-infected areas from lung CT images. One of the most popular segmentation methods is the U-Net model. U-Net is a convolutional neural network used for medical image segmentation. U-Net and its variants have become a more reliable architecture used for medical image segmentation. U-Net models have produced outstanding results in segmenting diseases such as COVID-19 from lung CT images. The exceptional results produced by the U-Net model have inspired various researchers to explore the potential of U-Net for various segmentation tasks. This study compares the performances of recently used state-of-the-art U-Net models on lung CT images for tuberculosis segmentation.