UPMCL-Net: Unsupervised Projection-Domain Multiview Constraint Learning for CBCT Metal Artifact Reduction
- 28 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 1776-1786
Abstract
Cone-Beam Computed Tomography (CBCT) provides real-time three-dimensional (3D) imaging support for intraoperative navigation. However, high-attenuation metal implants introduce severe metal artifacts in reconstructed CBCT images. These artifacts compromise image quality and therefore may affect diagnostic accuracy. Current CBCT metal artifact reduction (MAR) algorithms overlook the complementary information available across CBCT views, leading to inaccurate projection-domain interpolation and secondary artifacts in the reconstructed images. To tackle these challenges, we propose a novel Unsupervised Projection-domain Multiview Constraint Learning Network (UPMCL-Net), which directly learns from metal-affected data for CBCT MAR without ground truths. In addition, a transformer-based MultiView Consistency Module (MVCM) is constructed to interpolate the projection-domain metal region for cross-view consistency. Finally, a Hybrid Feature Attention Module (HFAM) is designed to adaptively fuse interview and intraview features. Comprehensive experiments conducted on real clinical datasets confirm the performance of UPMCL-Net, showcasing its potential as an efficient, accurate, and reliable approach for CBCT MAR in clinical intraoperative interventions.Keywords
Funding Information
- Key Project of Research and Development Plan of Hunan Province (2022YFC2408500)
- National Natural Science Foundation of China (T2225025)
- National Natural Science Foundation of China (62401141)
- Key Research and development Programs in Jiangsu Province of China (BE2021703)
- Key Research and development Programs in Jiangsu Province of China (BE2022768)
- Civil Space Technology Pre-research Foundation (D010101)
- Jiangsu Province Science Foundation for Youths (BK20241305)
- China Postdoctoral Science Foundation (2023M740607)
This publication has 44 references indexed in Scilit:
- Deep convolutional‐neural‐network‐based metal artifact reduction for CT‐guided interventional oncology procedures (MARIO)Medical Physics, 2024
- Deep Learning in Image Processing: Part 2—Image Enhancement, Reconstruction and Registration2023
- Metal artifact correction in photon‐counting detector computed tomography: metal trace replacement using high‐energy dataMedical Physics, 2022
- Convolutional neural network–based metal and streak artifacts reduction in dental CT images with sparse‐view sampling schemeMedical Physics, 2022
- InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction2021
- Synthetic CT generation from CBCT images via deep learningMedical Physics, 2019
- Frequency split metal artefact reduction in pelvic computed tomographyEuropean Radiology, 2013
- Metal artefact reduction in gemstone spectral imaging dual-energy CT with and without metal artefact reduction softwareEuropean Radiology, 2012
- Metal artifact reduction by dual energy computed tomography using monoenergetic extrapolationEuropean Radiology, 2011
- A pragmatic approach to metal artifact reduction in CT: merging of metal artifact reduced imagesEuropean Radiology, 2004