Blur and noise corrupting Computed Tomography (CT) images can hide or distort small but important details, negatively affecting the consequent diagnosis. In this paper, we present a novel gradient-based Plug-and-Play (PnP) algorithm and we apply it to restore CT im- ages. The plugged denoiser is implemented as a deep Convolutional Neural Network (CNN) trained on the gradient domain (and not on the image one, as in state-of-the-art works) and it induces an external prior onto the restoration model. We further consider a hy- brid scheme which combines the gradient-based external denoiser with an internal one, obtained from the Total Variation functional. The proposed frameworks rely on the Half- Quadratic Splitting scheme and we prove a general fixed-point convergence theorem, un- der weak assumptions on both the denoisers. The experiments confirm the effectiveness of the proposed gradient-based approach in restoring blurred noisy CT images, both in simulated and real medical settings. The obtained performances outperform the achievements of many state-of-the-art methods

Plug-and-Play gradient-based denoisers applied to CT image enhancement

Pasquale Cascarano;Elena Loli Piccolomini;Elena Morotti;Andrea Sebastiani
2022

Abstract

Blur and noise corrupting Computed Tomography (CT) images can hide or distort small but important details, negatively affecting the consequent diagnosis. In this paper, we present a novel gradient-based Plug-and-Play (PnP) algorithm and we apply it to restore CT im- ages. The plugged denoiser is implemented as a deep Convolutional Neural Network (CNN) trained on the gradient domain (and not on the image one, as in state-of-the-art works) and it induces an external prior onto the restoration model. We further consider a hy- brid scheme which combines the gradient-based external denoiser with an internal one, obtained from the Total Variation functional. The proposed frameworks rely on the Half- Quadratic Splitting scheme and we prove a general fixed-point convergence theorem, un- der weak assumptions on both the denoisers. The experiments confirm the effectiveness of the proposed gradient-based approach in restoring blurred noisy CT images, both in simulated and real medical settings. The obtained performances outperform the achievements of many state-of-the-art methods
2022
Pasquale Cascarano; Elena Loli Piccolomini; Elena Morotti; Andrea Sebastiani
File in questo prodotto:
File Dimensione Formato  
CMIG_PnP_revisione.pdf

embargo fino al 03/02/2024

Tipo: Postprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione 4.71 MB
Formato Adobe PDF
4.71 MB Adobe PDF   Visualizza/Apri   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/903602
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 10
social impact