Unsupervised metal artifacts reduction network for CT images based on efficient transformer

Article Radiology, Nuclear Medicine & Medical Imaging

A semi-supervised learning method of latent features based on convolutional neural networks for CT metal artifact reduction

Zaifeng Shi et al.

Summary: In this study, a semi-supervised learning method based on convolutional neural networks is proposed to remove metal artifacts in CT images while ensuring a good generalization ability for real-artifact CT images.

MEDICAL PHYSICS (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Deep Sinogram Completion With Image Prior for Metal Artifact Reduction in CT Images

Lequan Yu et al.

Summary: In this article, a novel metal artifact reduction method is proposed, which leverages the advantages of image domain and sinogram domain-based techniques for enhanced results in radiation therapy, effectively reducing new artifacts in reconstructed CT images.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Unsupervised CT Metal Artifact Learning Using Attention-Guided β-CycleGAN

Junghyun Lee et al.

Summary: Metal artifact reduction is a significant research topic in CT, with deep learning methods being widely used. Although supervised learning methods are popular, it is challenging to obtain matched image pairs in real CT acquisition. A recent unsupervised learning approach was proposed, but the complex network architecture struggled with large clinical images. This study introduces a simple and effective unsupervised learning method based on a novel beta-cycleGAN architecture, which, combined with CBAM layers in the generator, achieves improved metal artifact reduction.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

添加到收藏夹

Article Engineering, Biomedical

DAN-Net: Dual-domain adaptive-scaling non-local network for CT metal artifact reduction

Tao Wang et al.

Summary: In this study, a novel dual-domain adaptive-scaling non-local network (DAN-Net) is proposed for reducing metal artifacts in CT scans. By utilizing a new network model, the performance of metal artifact reduction is significantly improved.

PHYSICS IN MEDICINE AND BIOLOGY (2021)

添加到收藏夹

Article Chemistry, Analytical

Completion of Metal-Damaged Traces Based on Deep Learning in Sinogram Domain for Metal Artifacts Reduction in CT Images

Linlin Zhu et al.

Summary: The traditional U-net, modified and augmented with two sinogram feature losses, enhances the accuracy of metal artifact data. Masking metal traces during artifact reduction improves stability and reliability. The proposed method accurately repairs missing data and reduces metal artifacts in reconstructed images.

SENSORS (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications