Prompt Guiding Multi-Scale Adaptive Sparse Representation-driven Network for Low-Dose CT MAR

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shi, Baoshun, Chen, Bing, Zhang, Shaolei, Fu, Huazhu, Hu, Zhanli
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911284126023680
author Shi, Baoshun
Chen, Bing
Zhang, Shaolei
Fu, Huazhu
Hu, Zhanli
author_facet Shi, Baoshun
Chen, Bing
Zhang, Shaolei
Fu, Huazhu
Hu, Zhanli
contents Low-dose CT (LDCT) is capable of reducing X-ray radiation exposure, but it will potentially degrade image quality, even yields metal artifacts at the case of metallic implants. For simultaneous LDCT reconstruction and metal artifact reduction (LDMAR), existing deep learning-based efforts face two main limitations: i) the network design neglects multi-scale and within-scale information; ii) training a distinct model for each dose necessitates significant storage space for multiple doses. To fill these gaps, we propose a prompt guiding multi-scale adaptive sparse representation-driven network, abbreviated as PMSRNet, for LDMAR task. Specifically, we construct PMSRNet inspired from multi-scale sparsifying frames, and it can simultaneously employ within-scale characteristics and cross-scale complementarity owing to an elaborated prompt guiding scale-adaptive threshold generator (PSATG) and a built multi-scale coefficient fusion module (MSFuM). The PSATG can adaptively capture multiple contextual information to generate more faithful thresholds, achieved by fusing features from local, regional, and global levels. Furthermore, we elaborate a model interpretable dual domain LDMAR framework called PDuMSRNet, and train single model with a prompt guiding strategy for multiple dose levels. We build a prompt guiding module, whose input contains dose level, metal mask and input instance, to provide various guiding information, allowing a single model to accommodate various CT dose settings. Extensive experiments at various dose levels demonstrate that the proposed methods outperform the state-of-the-art LDMAR methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt Guiding Multi-Scale Adaptive Sparse Representation-driven Network for Low-Dose CT MAR
Shi, Baoshun
Chen, Bing
Zhang, Shaolei
Fu, Huazhu
Hu, Zhanli
Computer Vision and Pattern Recognition
Low-dose CT (LDCT) is capable of reducing X-ray radiation exposure, but it will potentially degrade image quality, even yields metal artifacts at the case of metallic implants. For simultaneous LDCT reconstruction and metal artifact reduction (LDMAR), existing deep learning-based efforts face two main limitations: i) the network design neglects multi-scale and within-scale information; ii) training a distinct model for each dose necessitates significant storage space for multiple doses. To fill these gaps, we propose a prompt guiding multi-scale adaptive sparse representation-driven network, abbreviated as PMSRNet, for LDMAR task. Specifically, we construct PMSRNet inspired from multi-scale sparsifying frames, and it can simultaneously employ within-scale characteristics and cross-scale complementarity owing to an elaborated prompt guiding scale-adaptive threshold generator (PSATG) and a built multi-scale coefficient fusion module (MSFuM). The PSATG can adaptively capture multiple contextual information to generate more faithful thresholds, achieved by fusing features from local, regional, and global levels. Furthermore, we elaborate a model interpretable dual domain LDMAR framework called PDuMSRNet, and train single model with a prompt guiding strategy for multiple dose levels. We build a prompt guiding module, whose input contains dose level, metal mask and input instance, to provide various guiding information, allowing a single model to accommodate various CT dose settings. Extensive experiments at various dose levels demonstrate that the proposed methods outperform the state-of-the-art LDMAR methods.
title Prompt Guiding Multi-Scale Adaptive Sparse Representation-driven Network for Low-Dose CT MAR
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.19687