Solving Energy-Independent Density for CT Metal Artifact Reduction via Neural Representation

2024-05-11

AI Summary

Metal artifacts in CT severely degrade image quality. To address this, we propose an unsupervised metal artifact reduction (MAR) method that requires no paired training data. Our approach models CT reconstruction as an energy-independent density estimation task, rigorously adhering to photon–tissue absorption physics. For the first time, we formulate MAR as a neural density representation problem based on neural radiance fields (NeRF), incorporating a water-equivalent tissue approximation and a novel polychromatic X-ray physical model to fundamentally decouple beam-hardening nonlinearities at the source. Evaluated on both synthetic and real clinical CT data, our method significantly outperforms state-of-the-art supervised MAR techniques in artifact suppression accuracy and cross-scanning robustness, while eliminating reliance on large-scale annotated datasets.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Computer Vision: Low Level & Physics-based Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

X-ray CT often suffers from shadowing and streaking artifacts in the presence of metallic materials, which severely degrade imaging quality. Physically, the linear attenuation coefficients (LACs) of metals vary significantly with X-ray energy, causing a nonlinear beam hardening effect (BHE) in CT measurements. Reconstructing CT images from metal-corrupted measurements consequently becomes a challenging nonlinear inverse problem. Existing state-of-the-art (SOTA) metal artifact reduction (MAR) algorithms rely on supervised learning with numerous paired CT samples. While promising, these supervised methods often assume that the unknown LACs are energy-independent, ignoring the energy-induced BHE, which results in limited generalization. Moreover, the requirement for large datasets also limits their applications in real-world scenarios. In this work, we propose Density neural representation (Diner), a novel unsupervised MAR method. Our key innovation lies in formulating MAR as an energy-independent density reconstruction problem that strictly adheres to the photon-tissue absorption physical model. This model is inherently nonlinear and complex, making it a rarely considered approach in inverse imaging problems. By introducing the water-equivalent tissues approximation and a new polychromatic model to characterize the nonlinear CT acquisition process, we directly learn the neural representation of the density map from raw measurements without using external training data. This energy-independent density reconstruction framework fundamentally resolves the nonlinear BHE, enabling superior MAR performance across a wide range of scanning scenarios. Extensive experiments on both simulated and real-world datasets demonstrate the superiority of our unsupervised Diner over popular supervised methods in terms of MAR performance and robustness.

Problem

• CT imaging
• metal artifact reduction
• image quality enhancement

Innovation

• Diner
• Metal Artifact Reduction
• X-ray Imaging