Data-consistent Unsupervised Diffusion Model for Metal Artifact Reduction
- 5 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 33, 1467-1472
Abstract
Computed Tomography (CT) is an imaging technique widely used in clinical diagnosis. However, high-attenuation metallic implants result in the obstruction of low-energy Xrays and further lead to metal artifacts in the reconstructed CT images. Deep supervised model-based metal artifact reduction(MAR) approaches are limited in clinical applications due to the difficulty in obtaining paired artifact-affected and artifactfree data. Furthermore, these model-based methods lack the consideration of data consistency in the sinogram-domain to perform exact metal trace inpainting. To address these challenges, we propose a Data-consistent unsupErVised diffusiOn model for meTal artifact rEDuction, called DEVOTED-Net. First, DEVOTED-Net leverages prior knowledge to guide the conditional diffusion model for fine-grained metal trace inpainting. Second, an unsupervised MAR framework is designed in the reverse process for the unknown metal traces restoration in the sinogram domain. Third, to further enhance the sinogram-domain data consistency, physics-based consistency constraint loss including conjugateray consistency loss and accumulation-ray consistency loss is designed. Extensive experiments are carried out to verify the performance of our algorithm on the publicly available dataset and clinical experimental dataset. This efficient, accurate, and reliable MAR approach holds great potential in clinics.Keywords
Funding Information
- Research and Development
- National Natural Science Foundation of China
- Research and Development
This publication has 15 references indexed in Scilit:
- Low-Dose CT Denoising via Sinogram Inner-Structure TransformerIEEE Transactions on Medical Imaging, 2022
- Learning Image Inpainting from Incomplete Images using Self-Supervision2021
- ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact ReductionIEEE Transactions on Medical Imaging, 2019
- Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database2018
- Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed TomographyIEEE Transactions on Medical Imaging, 2018
- Deep residual learning enabled metal artifact reduction in CT2018
- Self-adaptive extreme learning machineNeural Computing and Applications, 2015
- A radial adaptive filter for metal artifact reduction2005
- CT artifact correction: an image-processing approach1996
- Iterative deblurring for CT metal artifact reductionIEEE Transactions on Medical Imaging, 1996