AS-Mamba: Asymmetric Self-Guided Mamba Decoupled Iterative Network for Metal Artifact Reduction
Authors:
- Bowen NingBNBowen Ning
- Zekun ZhouZZZekun Zhou
- Xinyi ZhongXZXinyi Zhong
- Zhongzhen WangZWZhongzhen Wang
- HongXin WuHWHongXin Wu
- HaiTao WangHWHaiTao Wang
- Liu ShiLSLiu Shi
- Qiegen LiuQiegen Liu
Preprint
Abstract
Metal artifact significantly degrades Computed Tomography (CT) image quality, impeding accurate clinical diagnosis. However, existing deep learning approaches, such as CNN and Transformer, often fail to explicitly capture the directional geometric features of artifacts, leading to compromised structural restoration. To address these limitations, we propose the Asymmetric Self-Guided Mamba (AS-Mamba) for metal artifact reduction. Specifically, the linear propagation of metal-induced streak artifacts aligns well with the sequential modeling capability of State Space Models (SSMs). Consequently, the Mamba architecture is leveraged to explicitly capture and suppress these directional artifacts. Simultaneously, a frequency domain correction mechanism is incorporated to rectify the global amplitude spectrum, thereby mitigating intensity inhomogeneity caused by beam hardening. Furthermore, to bridge the distribution gap across diverse clinical scenarios, we introduce a self-guided contrastive regularization strategy. Extensive experiments on public andclinical dental CBCT datasets demonstrate that AS-Mamba achieves superior performance in suppressing directional streaks and preserving structural details, validating the effectiveness of integrating physical geometric priors into deep network design.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Dual-Teacher Semi-Supervised framework with Mamba-based model for CT metal artifact reductionBiomedical Signal Processing and Control, 2025
- Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentationPattern Recognition, 2023
- InDuDoNet+: A deep unfolding dual domain network for metal artifact reduction in CT imagesMedical Image Analysis, 2022
- DuDoTrans: Dual-Domain Transformer for Sparse-View CT Reconstruction2022
- A review on medical image denoising algorithmsBiomedical Signal Processing and Control, 2020
- An irregular metal trace inpainting network for x‐ray CT metal artifact reductionMedical Physics, 2020
- Adaptive iterative reconstruction based on relative total variation for low-intensity computed tomographySignal Processing, 2019
- CT sinogram‐consistency learning for metal‐induced beam hardening correctionMedical Physics, 2018
- Metal artifact reduction techniques in musculoskeletal CT-imagingEuropean Journal of Radiology, 2018
- Characterization of Metal Artifacts in X‐Ray Computed TomographyCommunications on Pure and Applied Mathematics, 2017