Search papers, labs, and topics across Lattice.
Tsinghua AIBaiyunPortGannan Normal UniversityNYUSanda UniversityShan Dong Xiehe CollegeShenzhen Research Institute of Big DataSouthern Medical UniversityUTSApr 8, 2026arXiv:2604.06622The paper introduces MARMamba, a lightweight UNet architecture incorporating multi-scale Mamba blocks, to reduce metal artifacts in CT images without requiring sinogram data. MARMamba uses a flip Mamba block to capture contextual information from multiple orientations and an average maximum feed-forward network to suppress artifacts. Experiments demonstrate that MARMamba effectively reduces metal artifacts while balancing computational demands, memory usage, and parameter count compared to other methods.
Achieve state-of-the-art metal artifact reduction in CT images with MARMamba, a Mamba-based model that's both lightweight and preserves anatomical structure.
In computed tomography imaging, metal implants frequently generate severe artifacts that compromise image quality and hinder diagnostic accuracy. There are three main challenges in the existing methods: the deterioration of organ and tissue structures, dependence on sinogram data, and an imbalance between resource use and restoration efficiency. Addressing these issues, we introduce MARMamba, which effectively eliminates artifacts caused by metals of different sizes while maintaining the integrity of the original anatomical structures of the image. Furthermore, this model only focuses on CT images affected by metal artifacts, thus negating the requirement for additional input data. The model is a streamlined UNet architecture, which incorporates multi-scale Mamba (MS-Mamba) as its core module. Within MS-Mamba, a flip mamba block captures comprehensive contextual information by analyzing images from multiple orientations. Subsequently, the average maximum feed-forward network integrates critical features with average features to suppress the artifacts. This combination allows MARMamba to reduce artifacts efficiently. The experimental results demonstrate that our model excels in reducing metal artifacts, offering distinct advantages over other models. It also strikes an optimal balance between computational demands, memory usage, and the number of parameters, highlighting its practical utility in the real world. The code of the presented model is available at: https://github.com/RICKand-MORTY/MARMamba.
