Semi-Automatic Segmentation of Paranasal Sinus from CT images Using Fully Convolutional Networks

In this paper, we present a novel image representation approach for paranasal sinus segmentation in computed tomography (CT) images of the brain. Our proposed method is based on a fully convolutional network (FCN), which is extensively used in a variety of computer vision applications. Experimental results demonstrate that our proposed method is efficient and effective for paranasal sinus segmentation.