Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction
This work addresses the problem of data scarcity in medical imaging for clinicians and researchers by providing a scalable, data-efficient method for artifact reduction, though it is incremental as it adapts existing foundation models rather than creating a new paradigm from scratch.
The paper tackles CT metal artifact reduction by reframing it as an in-context reasoning task using a vision-language diffusion foundation model adapted with LoRA, achieving effective artifact suppression with only 16 to 128 paired training examples, reducing data requirements by two orders of magnitude and demonstrating state-of-the-art performance on the AAPM CT-MAR benchmark.
Metal artifacts from high-attenuation implants severely degrade CT image quality, obscuring critical anatomical structures and posing a challenge for standard deep learning methods that require extensive paired training data. We propose a paradigm shift: reframing artifact reduction as an in-context reasoning task by adapting a general-purpose vision-language diffusion foundation model via parameter-efficient Low-Rank Adaptation (LoRA). By leveraging rich visual priors, our approach achieves effective artifact suppression with only 16 to 128 paired training examples reducing data requirements by two orders of magnitude. Crucially, we demonstrate that domain adaptation is essential for hallucination mitigation; without it, foundation models interpret streak artifacts as erroneous natural objects (e.g., waffles or petri dishes). To ground the restoration, we propose a multi-reference conditioning strategy where clean anatomical exemplars from unrelated subjects are provided alongside the corrupted input, enabling the model to exploit category-specific context to infer uncorrupted anatomy. Extensive evaluation on the AAPM CT-MAR benchmark demonstrates that our method achieves state-of-the-art performance on perceptual and radiological-feature metrics . This work establishes that foundation models, when appropriately adapted, offer a scalable alternative for interpretable, data-efficient medical image reconstruction. Code is available at https://github.com/ahmetemirdagi/CT-EditMAR.