Ms. Lei Wang Profile

Lei Wang

at Southern Medical Univ

SPIE Involvement:

Author

Publications (3)

Proceedings Article | 18 October 2022 Open Access

Self-supervised nonlocal spectral similarity induced material decomposition network for dual-energy CT

Lei Wang, Yongbo Wang, Zhaoying Bian, Dong Zeng, Jianhua Ma

Proceedings Volume 12304, 123040W (2022) https://doi.org/10.1117/12.2646645

KEYWORDS: Bone, Data modeling, Computed tomography, Signal to noise ratio, Signal attenuation, Model-based design, Image processing, Signal processing, Performance modeling, Medical imaging

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 16 March 2020 Paper

Progressive transfer learning strategy for low-dose CT image reconstruction with limited annotated data

Mingqiang Meng, Danyang Li, Sui Li, Manman Zhu, Lei Wang, Qi Gao, Zhaoying Bian, Xinyu Zhang, Jing Huang, Dong Zeng, Jianhua Ma

Proceedings Volume 11312, 1131242 (2020) https://doi.org/10.1117/12.2548946

KEYWORDS: Computed tomography, Convolution, CT reconstruction, Image restoration, Image quality, Medical imaging, Network architectures, Lithium, Cancer, Diagnostics

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Semi-supervised noise distribution learning for low-dose CT restoration

Lei Wang, Qi Gao, Mingqiang Meng, Sui Li, Manman Zhu, Danyang Li, Gaofeng Chen, Dong Zeng, Qi Xie, Qian Zhao, Zhaoying Bian, Deyu Meng, Jianhua Ma

Proceedings Volume 11312, 1131244 (2020) https://doi.org/10.1117/12.2548944

KEYWORDS: Computed tomography, X-ray computed tomography, Image restoration, Machine learning, Lithium, Medical imaging, Gallium nitride, Data modeling, Biomedical engineering, Image processing

Read Abstract +

Fully supervised deep learning (DL) methods have been widely used in low-dose CT (LDCT) imaging field and can usually achieve high accuracy results. These methods require a large labeled training set which consists of pairs of LDCT images as well as their corresponding high-dose CT (HDCT) ones. They successfully learn intermediate concept of features describing important components in CT images, such as noise distribution, and structure details, which is important to capture dependencies from LDCT image to HDCT ones. However, it should be noted that it is quite time-consuming and costly to obtain such a large of labeled CT images especially the HDCT images are limited in clinics. In comparison, lots of unlabeled LDCT images are usually easily accessible and massive critical information latent in the unlabeled LDCT can be leveraged to further boost restoration performance. Therefore, in this work, we present a semi-supervised noise distribution learning network to suppress noise-induced artifacts in the LDCT images. For simplicity, the presented network in termed as "SNDL-Net". The presented SNDL-Net consists of two sub-networks, i.e., supervised network, and unsupervised network. In the supervised network, the LDCT/HDCT image pairs are used for network training. And the unsupervised network considers the complex noise distribution in the LDCT images, and model the noise with a Gaussian mixture framework, then learns the proper gradient of LDCT images in a purely unsupervised manner. Similar with the supervised network training, the gradient information in a large of unlabeled LDCT images can be used for unsupervised network training. Moreover, to learn the noise distribution accurately, the discrepancy between the learned noise distribution in the supervised network and learned noise distribution in the unsupervised network can be modeled by a Kullback-Leibler (KL) divergence. Experiments on the Mayo clinic dataset verify the method is effective in low-dose CT image restoration with only a small amount of labeled data compared to previous supervised deep learning methods.

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years