Comparison of CT noise reduction performances with deep learning-based, conventional, and combined denoising algorithms.

Conventional noise reduction algorithms have been used in image processing for a very long time, but recently, deep learning-based algorithms have been shown to significantly reduce the noise in CT images. In this paper, a comparison of CT noise reduction of a deep learning-based, a conventional, and their combined denoising algorithms is presented. A conventional adaptive 3D bilateral filter and a 2D deep learning-based noise reduction algorithm and a combination of these are compared.

Iterative Ring Artifact Removal Method for Helical Computed Tomography Scans.

Objective: In this article, a statistical-based iterative ring removal (IRR) algorithm that effectively removes ring artifacts generated by defective detector cells is proposed.

Methods: The physical state of computed tomography (CT) detector elements can change dynamically owing to their temperature dependence and the varying irradiation caused by focal spot movements. This variation in the properties of cells may cause false pixel values in sinograms, resulting in rings or segments of rings in reconstructed images.

Single-energy material decomposition using X-ray path length estimation.

Objective: Clinical computed tomographies (CTs) can typically use only a single energy at a time. The main purpose of the present paper was to study whether the calculated x-ray path lengths can help replace one of the 2 dual-energy measurements by 2-material decomposition.

Method: The proposed single-energy material decomposition method (SEMD) is based on the evaluation of a single CT scan.