Advertisement

403 Comparison Of Iterative Reconstruction And Post Reconstruction Deep Learning Noise Reduction Methods Utilizing Philips Brilliance CT 256 Phantom Data And Clinical Images

      Introduction: The quality of coronary computed tomographic angiography (CCTA) post processing is dependent on special noise reduction (NR) techniques, such as Iterative Reconstruction (IR). While IR lowers noise amplitude, it also lowers central noise frequency (CNF), distorting margins and adding a waxy quality to CCTA images. Fortunately, new deep learning (DL) NR algorithms preserve CNF maintaining sharp image features without distortion. The most versatile of these new NR techniques is applicable after filtered back projection (FBP) and is thus vendor agnostic. In this presentation, we validate the relative CNF stability of an FDA-approved DL algorithm (PixelShine, AlgoMedica Inc) through Noise Power Spectrum (NPS) analysis, comparing its performance to that of the IR NR methods of a major CT vendor. We also provide a gallery of clinical comparisons.
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      Full access to the journal is a member benefit for SCCT Members, Login via the SCCT website to access all journal content.

      Subscribe:

      Subscribe to Journal of Cardiovascular Computed Tomography
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect