Ms. Lisha Yao Profile

Lisha Yao

SPIE Involvement:

Author

Publications (4)

Proceedings Article | 16 March 2020 Paper

Leveraging deep generative model for direct energy-resolving CT imaging via existing energy-integrating CT images

Lisha Yao, Sui Li, Danyang Li, Manman Zhu, Qi Gao, Shanli Zhang, Zhaoying Bian, Jing Huang, Dong Zeng, Jianhua Ma

Proceedings Volume 11312, 113124U (2020) https://doi.org/10.1117/12.2548992

KEYWORDS: Computed tomography, Convolution, Image classification, Data modeling, Image analysis, Lithium, Photon counting, Sensors, Spatial resolution, Neural networks

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Non-local texture learning approach for CT imaging problems using convolutional neural network

Sui Li, Lisha Yao, Manman Zhu, Danyang Li, Qi Gao, Xinyu Zhang, Rikui Zhong, Zhaoying Bian, Dong Zeng, Jianhua Ma

Proceedings Volume 11312, 113124B (2020) https://doi.org/10.1117/12.2548949

KEYWORDS: Computed tomography, Convolutional neural networks, Convolution, 3D image processing, CT reconstruction, Reconstruction algorithms, 3D acquisition, Neural networks, Lithium, Evolutionary algorithms

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Semi-supervised learned sinogram restoration network for low-dose CT image reconstruction

Mingqiang Meng, Sui Li, Lisha Yao, Danyang Li, Manman Zhu, Qi Gao, Qi Xie, Qian Zhao, Zhaoying Bian, Jing Huang, Deyu Meng, Dong Zeng, Jianhua Ma

Proceedings Volume 11312, 113120B (2020) https://doi.org/10.1117/12.2548985

KEYWORDS: Machine learning, Reconstruction algorithms, X-ray computed tomography, Computed tomography, CT reconstruction, Image processing, Image filtering, Denoising, Data modeling, Lithium

Read Abstract +

With the development of deep learning (DL), many deep learning (DL) based algorithms have been widely used in the low-dose CT imaging and achieved promising reconstruction performance. However, most DL-based algorithms need to pre-collect a large set of image pairs (low-dose/high-dose image pairs) and trains networks in a supervised end-to-end manner. Actually, it is not feasible in clinical to obtain such a large amount of paired training data, especially for high-dose ones. Therefore, in this work, we present a semi-supervised learned sinogram restoration network (SLSR-Net) for low-dose CT image reconstruction. The presented SLSR-Net consists of supervised sub-network and unsupervised sub-network. Specifically, different from the traditional supervised DL networks which only use low-dose/high-dose sinogram pairs, the presented SLSR-Net method is capable of feeding only a few supervised sinogram pairs and massive unsupervised low-dose sinograms into the network training procedure. The supervised pairs are used to capture critical features (i.e., noise distribution, and tissue characteristics) latent in a supervised way and the unsupervised sub-network efficiently learns these features using a conventional weighted least-squares model with a regularization term. Moreover, another contribution of the presented SLSR-Net method is to adaptively transfer learned feature distribution from supervised subnetwork with the paired sinograms to unsupervised sub-network with unlabeled low-dose sinograms to obtain high-fidelity sinogram with a Kullback-Leibler divergence. Finally, the filtered backprojection algorithm is used to reconstruct CT images from the obtained sinograms. Real patient datasets are used to evaluate the performance of the presented SLSR-Net method and the corresponding experimental results show that compared with the traditional supervised learning method, the presented SLSR-Net method achieves competitive performance in terms of noise reduction and structure preservation in low-dose CT imaging.

Proceedings Article | 28 May 2019 Paper

Multi-energy computed tomography reconstruction using an average image induced low-rank tensor decomposition with spatial-spectral total variation regularization

Lisha Yao, Dong Zeng, Sui Li, Zhaoying Bian, Jianhua Ma

Proceedings Volume 11072, 110722O (2019) https://doi.org/10.1117/12.2534802

KEYWORDS: CT reconstruction, Computed tomography, Signal to noise ratio, 3D image processing, Tissues, 3D displays, 3D modeling, 3D image reconstruction, Visualization, Lithium

Read Abstract +

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