Ms. Jingyi Liao Profile

Jingyi Liao

at Southern Medical Univ

SPIE Involvement:

Author

Publications (6)

Proceedings Article | 7 April 2023 Poster + Paper

Robust multi-institution low-dose CT imaging with semi-supervised federated learning network

Danyang Li, Cuidie Zeng, Jingyi Liao, Mingqiang Meng, Hao Wang, Yuting Wang, Dong Zeng, Jianhua Ma

Proceedings Volume 12463, 1246339 (2023) https://doi.org/10.1117/12.2654184

KEYWORDS: Data modeling, Education and training, Performance modeling, Computed tomography, Statistical modeling, Model-based design, X-ray computed tomography, Neural networks, Attenuation, Visualization

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Semi-centralized federated learning network for low-dose CT imaging

Danyang Li, Hao Wang, Jingyi Liao, Mingqiang Meng, Cuidie Zeng, Yuting Wang, Dong Zeng, Jianhua Ma

Proceedings Volume 12463, 124634W (2023) https://doi.org/10.1117/12.2654180

KEYWORDS: Education and training, Data modeling, Performance modeling, Computed tomography, Image quality standards, Statistical modeling, X-ray computed tomography, Windows, Visualization, Tunable filters

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Adaptive semi-supervised learning material estimation network in dual-energy CT

Zheng Duan, Jingyi Liao, Yongbo Wang, Danyang Li, Zhaoying Bian, Dong Zeng, Jianhua Ma

Proceedings Volume 12463, 124633F (2023) https://doi.org/10.1117/12.2654207

KEYWORDS: Signal to noise ratio, Machine learning, Image quality, Education and training, Data modeling, Bone, X-rays, Neural networks, Model-based design, Tissues

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Self-attention network for weak-supervised learning multi-material decomposition in dual energy CT

Zheng Duan, Danyang Li, Jingyi Liao, Yongbo Wang, Dong Zeng, Zhaoying Bian, Jianhua Ma

Proceedings Volume 12463, 124633E (2023) https://doi.org/10.1117/12.2654205

KEYWORDS: Education and training, Dual energy imaging, Deep learning, Bone, Tissues, Machine learning, X-ray computed tomography, Visualization, Matrices, Iodine

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Noise-conscious explicit weighting network for robust low-dose CT imaging

Shengwang Peng, Jingyi Liao, Danyang Li, Zhaoying Bian, Dong Zeng, Jing Huang, Jianhua Ma

Proceedings Volume 12463, 124633C (2023) https://doi.org/10.1117/12.2654192

KEYWORDS: Education and training, Computed tomography, Image quality, Image restoration, CT reconstruction, Deep learning, Medical image reconstruction, Associative arrays, Windows, Prior knowledge

Read Abstract +

Supervised deep learning (DL) methods have been widely developed to remove noise-induced artifacts and promote image quality in the low-dose CT imaging task via good mapping capabilities. These supervised DL methods are usually trained based on a large amount of low- and normal-dose sinogram/image pairs and the reconstruction performance of such supervised DL methods heavily depends on the quality of reference training images. In the CT imaging, it is challenging to collect lots of high quality reference training images in practice due to the risk of high radiation dose to patients. Moreover, the medium quality or even low quality reference training images (i.e., the low quality labeled data with some noise-induced artifacts) might be collected for the supervised DL networks training, which would degrade the reconstruction performance of the network. To address this issue, in this work, we propose an effective noise-conscious explicit weighting network (NEW-Net) for low-dose CT imaging wherein the CT images with noise-induced artifacts are treated as labeled data in the network training. Specifically, the proposed NEW-Net consists of two sub-networks, i.e., noise estimation sub- network, and noise-conscious weighting sub-network. The noise estimation sub-network produces the noise map from the low-quality training data to estimate the noise-conscious weights, which determines the contribution of the label data, i.e., small weights go along with the low quality label data with severe nosie-induced artifacts, and large weights go along with high quality label data with a few noise-induced artifacts. Then the estimated weights are used to condition the training data to train the noise-conscious weighting sub-network to eliminate the effects of low quality label data and promote the reconstruction performance and stability of the proposed NEW-Net method. The Mayo clinic data are utilized to validate and evaluate the reconstruction performance of the proposed NEW-Net method. And the experimental results demonstrate that the proposed NEW-Net method outperforms the other competing methods in the case of low quality training data, in terms of noise-induced artifacts and structure detail preservation both qualitatively and quantitatively.

Proceedings Article | 7 April 2023 Poster + Paper

Deep learning-based all-in-one combined visualization strategy for disease screening in CT imaging

Hao Zhou, Jingyi Liao, Zhixiong Zeng, Danyang Li, Yongbo Wang, Zhaoying Bian, Dong Zeng, Jianhua Ma

Proceedings Volume 12463, 124633B (2023) https://doi.org/10.1117/12.2654188

KEYWORDS: Computed tomography, Windows, Tunable filters, Lung, Image filtering, Chest, Image sharpness, Visualization, Deep learning, Diseases and disorders

Read Abstract +

Showing 5 of 6 publications

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