Runrui Li

Runrui Li

Auto-generated profile, based on publicly available information

Runrui Li

School of Artificial Intelligence, Beijing Normal University, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 September 2022 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
RLRunrui Li
Runrui Li
QLQing Li
Qing Li
HWHexi Wang
Hexi Wang
SLSaize Li
Saize Li
JZJuanjuan Zhao
Juanjuan Zhao
LWLong Wang
Long Wang
Computed tomography (CT) is increasingly essential for clinical diagnosis nowadays while X-ray ionizing radiation is harmful and may increase the risk of cancers. Researchers have thus proposed to obtain the sparse sinograms by reducing the number of detectors to reduce the radioactive impact on human body. However, the sparse-view sinograms have some problems including blurring and streak artifacts, which may adversely confuse the diagnostic assessment to some extent. In this paper, we propose a Transformer-based module named DDPTransformer Block to capture the long-term dependencies within the images and reconstruct high-quality CT images from sparsely sampled sinograms. More specifically, we replace the traditional convolution operation with the Parallel Transformers, and augment the edge information of patch blocks by different splits. In addition, considering that the images to be processed are two-dimensioned, we propose the Layer-Conv-Layer (LCL) module to replace the multilayer perceptron (MLP) in Transformer for feature extraction. Finally, with DDPTransformer Block as the backbone, we propose a deep learning model with four stages including Interpolation, Sinogram Domain Subnet, Filtered BackProjection (FBP) and Image Domain SubNet. For training the model, we use the dataset from the “ Low Dose CT Image and Projection Data (LDCT-and-Projection data)”. Experimental results show that the proposed model outperforms the state-of-the-art algorithms for various sparsely sampled sinograms and its robustness has been further verified through other datasets. The code and model are publicly available at: https://github.com/MikasaLee/DDPTransformer .

25 January 2024 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
YCYubin Cheng
Yubin Cheng
QLQing Li
Qing Li
RLRunrui Li
Runrui Li
TWTao Wang
Tao Wang
JZJuanjuan Zhao
Juanjuan Zhao
YGYan Geng
Yan Geng
In computed tomography (CT), although sparse sampling of projections effectively mitigates radiation problems, the quality of CT images is severely compromised. Recovering high-quality CT images from sparsely sampled data is a challenging task. Recently, “Iterative Theory + Deep Learning” schemes have shown promising results in CT reconstruction tasks. In this paper, we propose an Iterative Reconstruction Network Model based on learnable projection operators (LIR-NET). Unlike existing image domain iteration schemes that fuse information from the projection domain, LIR-Net achieves joint optimization and iteration of dual-domain data. The dual-domain subnetwork uses a replaceable and lightweight U-net. We propose an Enhanced Aligned Loss (EAL) scheme to speed up convergence in the projection domain subnet. A designed last-iteration Sparse Truth Bootstrap (STB) module improves data distortion, while Bit-plane Codec (BC) is combined to enhance the noise discovery and removal capability of the image domain subnet. Extensive experiments based on the dataset from the “Low Dose CT Image and Projection Data (LDCT-and-Projection data)” show that our approach outperforms the best available solutions in both quantitative and qualitative evaluations. Moreover, the robustness of the proposed scheme has been tested and validated on an additional dataset. Our code and data are available at https://github.com/YB-Cheng/LIR-Net .

11 February 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
LSLei Shi
Lei Shi
YCYubin Cheng
Yubin Cheng
RLRunrui Li
Runrui Li
HWHexi Wang
Hexi Wang
JZJun Zhao
Jun Zhao
JZJuanjuan Zhao
Juanjuan Zhao
Deep neural network models generally enhance super-resolution reconstruction of remote sensing images but may distort feature edge details. Recovering low-resolution remote sensing images with clear texture and high-fidelity edge details is challenging. Recent approaches improve feature fusion in the frequency domain, yielding promising results. We propose a Dual-Domain Optimization Network (DDOM) based on Discrete Fourier Transform (DFT) and frequency domain complex-valued neural networks. Unlike end-to-end approaches in the image domain, DDOM incorporates frequency-domain information via DFT transformation operators, preserving high-level semantics (phase) and low-level statistical information (magnitude). Using lightweight complex neural networks and SwinTransformer architecture, the frequency-domain and image-domain subnetworks are designed. The dual-domain data consistency constraints ensure the positivity of model optimization. Extensive experiments show superior performance over existing methods in quantitative and qualitative evaluations. The proposed scheme’s robustness is verified on additional datasets. Code and model configurations are available at http://github.com/YB-Cheng/DDOM.