Uconnect: Synergistic Spectral CT Reconstruction With U-Nets Connecting the Energy Bins

TY - JOUR

T1 - Uconnect

T2 - Synergistic Spectral CT Reconstruction With U-Nets Connecting the Energy Bins

AU - Wang, Zhihan

AU - Bousse, Alexandre

AU - Vermet, Franck

AU - Froment, Jacques

AU - Vedel, Béatrice

AU - Perelli, Alessandro

AU - Tasu, Jean-Pierre

AU - Visvikis, Dimitris

N1 - Copyright: © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

PY - 2024/2

Y1 - 2024/2

N2 - Spectral computed tomography (CT) offers the possibility to reconstruct attenuation images at different energy levels, which can be then used for material decomposition. However, traditional methods reconstruct each energy bin individually and are vulnerable to noise. In this article, we propose a novel synergistic method for spectral CT reconstruction, namely, Uconnect. It utilizes trained convolutional neural networks (CNNs) to connect the energy bins to a latent image so that the full binned data is used synergistically. We experiment on two types of low-dose data: 1) simulated and 2) real patient data. Qualitative and quantitative analysis show that our proposed Uconnect outperforms state-of-the-art model-based iterative reconstruction (MBIR) techniques as well as CNN-based denoising.

AB - Spectral computed tomography (CT) offers the possibility to reconstruct attenuation images at different energy levels, which can be then used for material decomposition. However, traditional methods reconstruct each energy bin individually and are vulnerable to noise. In this article, we propose a novel synergistic method for spectral CT reconstruction, namely, Uconnect. It utilizes trained convolutional neural networks (CNNs) to connect the energy bins to a latent image so that the full binned data is used synergistically. We experiment on two types of low-dose data: 1) simulated and 2) real patient data. Qualitative and quantitative analysis show that our proposed Uconnect outperforms state-of-the-art model-based iterative reconstruction (MBIR) techniques as well as CNN-based denoising.

KW - Deep learning

KW - Spectral CT

KW - regularization

KW - synergistic reconstruction

UR - https://www.scopus.com/pages/publications/85181837747

U2 - 10.1109/TRPMS.2023.3330045

DO - 10.1109/TRPMS.2023.3330045

M3 - Article

SN - 2469-7303

VL - 8

SP - 222

EP - 233

JO - IEEE Transactions on Radiation and Plasma Medical Sciences

JF - IEEE Transactions on Radiation and Plasma Medical Sciences

IS - 2

ER -