ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction

Abstract

Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods that rely on synthesized metal artifacts for training. However, as synthesized data may not accurately simulate the underlying physical mechanisms of CT imaging, the supervised methods often generalize poorly to clinical applications. To address this problem, we propose, to the best of our knowledge, the first unsupervised learning approach to MAR. Specifically, we introduce a novel artifact disentanglement network that disentangles the metal artifacts from CT images in the latent space. It supports different forms of generations (artifact reduction, artifact transfer, and self-reconstruction, etc.) with specialized loss functions to obviate the need for supervision with synthesized data. Extensive experiments show that when applied to a synthesized dataset, our method addresses metal artifacts significantly better than the existing unsupervised models designed for natural image-to-image translation problems, and achieves comparable performance to existing supervised models for MAR. When applied to clinical datasets, our method demonstrates better generalization ability over the supervised models. The source code of this paper is publicly available at https://github.com/liaohaofu/adn.

arXiv commentThis is the extended version of arXiv:1906.01806. This paper is accepted to IEEE Transactions on Medical Imaging

References in corpus (1)

• Convolutional Neural Network Based Metal Artifact Reduction in X-ray Computed Tomography

Cited by in corpus (12)

• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Learning Disentangled Representations in the Imaging Domain
• Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models
• InDuDoNet+: A Deep Unfolding Dual Domain Network for Metal Artifact Reduction in CT Images
• DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
• Metal Artifact Reduction in 2D CT Images with Self-supervised Cross-domain Learning
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• Quad-Net: Quad-domain Network for CT Metal Artifact Reduction
• Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
• Orientation-Shared Convolution Representation for CT Metal Artifact Learning
• Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging
• Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling