CT Field of View Extension Using Combined Channels Extension and Deep Learning Methods

Abstract: This paper proposes a method to extend the field of view of computed tomography images. In a first step, the field of view is increased by extrapolating linearly the outer channels in the sinogram space. The modified sinogram is then used to reconstruct extended field of view (EFoV) images containing artifacts due to the channels extension. In a second step, those artifacts are reduced by a deep learning network in image space. The proposed method has been evaluated on a collection of clinical scans. The resulting volumes have been checked for consistency and plausibility and compared to an existing state of the art EFoV method.