Technology Category
Computer Vision: SegmentationMachine Learning: Matrix & Tensor MethodsSearch and Optimization: Metareasoning and Metaheuristics
Reducing CT Metal Artifacts by Learning Latent Space Alignment with Gemstone Spectral Imaging Data
🤖 AI Summary
Metal artifacts in CT severely impair diagnostic accuracy, particularly hindering assessment of periprosthetic tissues. To address this, we propose a latent-space alignment–based metal artifact reduction (MAR) framework. We first observe that conventional CT scans—despite containing severe artifacts—retain implicit, complete anatomical structural information. Leveraging Gemstone Spectral Imaging (GSI) multi-energy data as a reference, our method calibrates conventional CT representations without introducing synthetic noise—a key limitation of prior approaches. We introduce Artifacts-GSI, the first clinically realistic paired dataset for MAR, along with a new benchmark. Our approach integrates latent-space alignment learning, multi-energy modeling, and self-supervised representation transfer. Evaluated on real patient data, it achieves significant artifact suppression, enhanced tissue boundary delineation, and improved diagnostic interpretability. Both code and the Artifacts-GSI dataset are fully open-sourced to accelerate clinical translation of MAR techniques.
Technology Category
Application Category
📝 Abstract
Metal artifacts in CT slices have long posed challenges in medical diagnostics. These artifacts degrade image quality, resulting in suboptimal visualization and complicating the accurate interpretation of tissues adjacent to metal implants. To address these issues, we introduce the Latent Gemstone Spectral Imaging (GSI) Alignment Framework, which effectively reduces metal artifacts while avoiding the introduction of noise information. Our work is based on a key finding that even artifact-affected ordinary CT sequences contain sufficient information to discern detailed structures. The challenge lies in the inability to clearly represent this information. To address this issue, we developed an Alignment Framework that adjusts the representation of ordinary CT images to match GSI CT sequences. GSI is an advanced imaging technique using multiple energy levels to mitigate artifacts caused by metal implants. By aligning the representation to GSI data, we can effectively suppress metal artifacts while clearly revealing detailed structure, without introducing extraneous information into CT sequences. To facilitate the application, we propose a new dataset, Artifacts-GSI, captured from real patients with metal implants, and establish a new benchmark based on this dataset. Experimental results show that our method significantly reduces metal artifacts and greatly enhances the readability of CT slices. All our code and data are available at: https://um-lab.github.io/GSI-MAR/
Problem
Research questions and friction points this paper is trying to address.
Reducing metal artifacts in CT slices for better diagnostics
Aligning ordinary CT images with GSI data to suppress artifacts
Enhancing CT slice readability without introducing noise information
Innovation
Methods, ideas, or system contributions that make the work stand out.
Latent GSI Alignment Framework reduces metal artifacts
Aligns ordinary CT representation to GSI sequences
Uses multi-energy GSI to suppress artifacts clearly
🔎 Similar Papers
No similar papers found.
