Learnable PM diffusion coefficients and reformative coordinate attention network for low dose CT denoising - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Physics in Medicine and Biology Année : 2023

Learnable PM diffusion coefficients and reformative coordinate attention network for low dose CT denoising

Résumé

Objective. Various deep learning methods have recently been used for low dose CT (LDCT) denoising. Aggressive denoising may destroy the edge and fine anatomical structures of CT images. Therefore a key issue in LDCT denoising tasks is the difficulty of balancing noise/artifact suppression and edge/structure preservation. Approach. We proposed an LDCT denoising network based on the encoder-decoder structure, namely the Learnable PM diffusion coefficient and efficient attention network (PMA-Net). First, using the powerful feature modeling capability of partial differential equations, we constructed a multiple learnable edge module to generate precise edge information, incorporating the anisotropic image processing idea of Perona-Malik (PM) model into the neural network. Second, a multiscale reformative coordinate attention module was designed to extract multiscale information. Non-overlapping dilated convolution capturing abundant contextual content was combined with coordinate attention which could embed the spatial location information of important features into the channel attention map. Finally, we imposed additional constraints on the edge information using edge-enhanced multiscale perceptual loss to avoid structure loss and over-smoothing. Main results. Experiments are conducted on simulated and real datasets. The quantitative and qualitative results show that the proposed method has better performance in suppressing noise/artifacts and preserving edges/structures. Significance. This work proposes a novel edge feature extraction method that unfolds partial differential equation into neural networks, which contributes to the interpretability and clinical application value of neural network.
Fichier sous embargo
Fichier sous embargo
0 1 15
Année Mois Jours
Avant la publication
mardi 11 juin 2024
Fichier sous embargo
mardi 11 juin 2024
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04415045 , version 1 (29-02-2024)

Identifiants

Citer

Haowen Zhang, Pengcheng Zhang, Weiting Cheng, Shu Li, Rongbiao Yan, et al.. Learnable PM diffusion coefficients and reformative coordinate attention network for low dose CT denoising. Physics in Medicine and Biology, 2023, Physics in Medicine and Biology, 68 (24), pp.245017. ⟨10.1088/1361-6560/aced33⟩. ⟨hal-04415045⟩
6 Consultations
2 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More