YXYan Xi

Yan Xi

*This is an algorithmically generated author record based on publicly available information.

Yan Xi has a total of 85 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • SIX: A Self-Supervised Interactive Algorithm for Low-Dose X-Ray Fluoroscopy Image Denoising

    by Mingzhi Wen, Tianling Lyu, Zhan Wu, Yan Xi, Pinzheng Zhang, Yang Chen, Yuanjing Feng

    Low-dose X-ray fluoroscopy is essential in interventional procedures to reduce radiation exposure, yet image quality is inevitably degraded by predominantly Poisson noise, compromising diagnostic reliability. Existing denoising methods commonly rely on large annotated medical datasets, which are scarce in practice, and struggle to balance noise suppression with the preservation of fine structural details. To overcome the above-mentioned problems, we propose SIX, a zero-shot self-supervised interactive denoising framework for low-dose fluoroscopy. The framework integrates a physics-driven noise model with a deep image prior. It performs prior-based denoising via probabilistic modeling with an intuitive hyperparameter, allowing a flexible balance between noise suppression and structural fidelity according to specific diagnostic requirements. Experiments on an in-house dataset show that SIX outperforms various conventional and deep learning methods in PSNR and SSIM, as well as in clinically critical metrics including contrast-to-noise ratio and spatial resolution. With its flexibility and user-friendly design, SIX holds strong potential for deployment in clinical image-guided workflows.


  • MVSS-PCR: A Multiview Subsampling Approach With Prior-Constrained Reconstruction for Self-Supervised CT Denoising

    by Tong Lin, Xi Wang, Wenhui Huang, Yan Xi, Xu Ji, Qiegen Liu, Jian Yang, Yikun Zhang, Yang Chen

    Computed tomography (CT) is widely used for non-invasive diagnostics but exposes patients to radiation. The simplest way to reduce radiation dose is by lowering the tube current and voltage, but this also decreases the number of penetrating photons, increasing noise in the projections. Compared with supervised and unsupervised learning methods, self-supervised learning methods enable noise mitigation. However, existing self-supervised methods often suffer from pixel misalignment during subsampling, leading to excessive smoothing and loss of structural details. To address these challenges, we propose Multi-View Sinogram Sampling (MVSS), which enhances alignment between training and target images by aggregating sinograms from multiple views. Furthermore, a Non-Local Means (NLM) module with a global search strategy is integrated to overcome the limitations of convolutional neural networks (CNNs) in capturing long-range dependencies, thereby providing higher-quality training targets. Finally, a prior-constrained iterative reconstruction framework with adaptive step-size adjustment is employed to enforce data consistency and restore fine anatomical structures while accelerating convergence. Experimental evaluations on three phantoms and the AAPM dataset demonstrate that the proposed method outperforms competing self-supervised approaches, achieving a PSNR of 35.79 dB and an SSIM of 0.955 on AAPM. Across datasets of Catphan 700, CIRS 057A, and head phantoms acquired on different CBCT systems, the proposed method consistently achieves lower standard deviation (STD) in homogeneous regions with uniform pixel intensity, reaching 28.8 HU, 159.1 HU, and 12.1 HU, respectively, while effectively restoring fine structural details.

  • UPMCL-Net: Unsupervised Projection-Domain Multiview Constraint Learning for CBCT Metal Artifact Reduction

    by Zhan Wu, Yang Yang, Yongjie Guo, Dayang Wang, Tianling Lyu, Yan Xi, Yang Chen, Hengyong Yu

    Cone-Beam Computed Tomography (CBCT) provides real-time three-dimensional (3D) imaging support for intraoperative navigation. However, high-attenuation metal implants introduce severe metal artifacts in reconstructed CBCT images. These artifacts compromise image quality and therefore may affect diagnostic accuracy. Current CBCT metal artifact reduction (MAR) algorithms overlook the complementary information available across CBCT views, leading to inaccurate projection-domain interpolation and secondary artifacts in the reconstructed images. To tackle these challenges, we propose a novel Unsupervised Projection-domain Multiview Constraint Learning Network (UPMCL-Net), which directly learns from metal-affected data for CBCT MAR without ground truths. In addition, a transformer-based MultiView Consistency Module (MVCM) is constructed to interpolate the projection-domain metal region for cross-view consistency. Finally, a Hybrid Feature Attention Module (HFAM) is designed to adaptively fuse interview and intraview features. Comprehensive experiments conducted on real clinical datasets confirm the performance of UPMCL-Net, showcasing its potential as an efficient, accurate, and reliable approach for CBCT MAR in clinical intraoperative interventions.

  • UPGRADE-Net: Unsupervised Sinogram-domain Data-Consistent Network for Metal Artifact Reduction

    by Zhan Wu, Yikun Zhang, Yongjie Guo, Hui Tang, Yinsheng Li, Huazhong Shu, Yan Xi, Yi Zhang, Gouenou Coatrieux, Yang Chen

    Computed tomography (CT) scanners are widely used to obtain detailed internal images in clinical diagnosis. Highly attenuated metallic implants resulting from strong and energy-dependent attenuation cause metal artifacts in CT scanning. However, current supervised deep network-based metal artifact reduction (MAR) methods hardly generalize in clinical diagnosis and treatment because of difficult acquisition for the paired artifact-affected and artifact-free data. In addition, these deep model-based methods cannot ensure the sinogram-domain data consistency for the exact metal trace inpainting. To address the above problems, we propose an UnsuPervised sinoGRam-domAin Data-consistEnt network for MAR, i.e., UPGRADE-Net. First, UPGRADE-Net fully leverages the prior knowledge to guide the generative conditional diffusion model for fine-grained metal trace inpainting. Second, without the artifact-free ground truth, a deep unsupervised MAR framework in the reverse process is constructed to contextually learn the known background data distribution for the unknown metal trace restoration in sinogram-domain. Third, to further maintain the sinogram-domain data consistency, two physics-based consistency constraint loss functions, including conjugate-ray and accumulation-ray consistency loss, are designed for the conjugate point constraint and the accumulation constraint. The proposed UPGRADE-Net is trained and evaluated on a publicly available dataset and a clinical dataset. Extensive experimental results validate that the proposed method outperforms the state-of-the-art competing methods for MAR.

  • TIF-Net: Self-Supervised Net via Tuy's Inversion Formula for Limited Angle Reconstruction

    by Guojun Zhu, Xinyun Zhong, Wenhui Huang, Guotao Quan, Yan Xi, Shipeng Xie, Yikun Zhang, Xu Ji, Yang Chen

    In medical or industrial measurements, limited angle reconstruction is a kind of ill-posed problem in computed tomography (CT). The CT images reconstructed from conventional analytical algorithms demonstrates structural distortions and artifacts. Recently, deep learning-based methods are utilized to resolve the limited angle reconstruction problem. However, most of the methods are supervised and require full scan CT images for training purposes. The training labels are often unavailable under real-world scenarios. In this work, we pro-posed a self-supervised limited-angle reconstruction method for CT that entirely eliminates the reliance on external supervision signals. It requires only limited-angle data acquired via a limited angle acquisition protocol, enabling computationally efficient and rapid reconstruction. The method utilized the reconstruction results from Tuy's inversion method as training labels. To bridge the distribution gap between the regions that satisfy and fail to satisfy Tuy's data sufficiency condition, a dedicated data synthesis process was designed. The method was validated using both numerical simulations and real experimental data. Results demonstrated that the proposed method can effectively suppress the limited angle artifacts without the need of any full scan CT labels. The performance of the proposed method approaches that of the supervised methods, based on visual inspections. The proposed method is also computationally efficient, enabling real time limited angle CT reconstruction.


  • A Hybrid Cone-Beam CT Scatter Correction Method Combining Fast Monte-Carlo Simulation and Deep Neural Network

    by Wenhui Huang, Chenglong Xu, Chenlong Miao, Xu Zhuo, Xinyun Zhong, Yan Xi, Yang Chen, Xu Ji

    X-ray scatter presents a significant challenge in computed tomography (CT) by introducing artifacts and diminishing contrast, ultimately affecting measurement accuracy in reconstructed images. While Monte Carlo (MC) simulation is the gold standard for scatter correction, its high computational cost limits clinical applications. Accelerated MC methods improve efficiency but may compromise accuracy. Scatter kernel-based approaches allow quick implementation but lack precision in measurement. Deep learning-based methods show promising results but require thorough evaluation for generalizability across diverse imaging protocols. This study presents a hybrid scatter correction method for cone-beam CT (CBCT) that integrates fast MC simulation with a deep neural network, aiming to enhance measurement precision and efficiency. Fast MC simulations are employed for low-dose, sparse-view scatter estimations, serving as references for missing-view scatter predictions. The network inputs and outputs are designed as differences relative to the reference signal, improving the method’s generalizability across varying imaging conditions. The proposed approach is validated through numerical simulations and physical experiments. Results demonstrate that the method achieves scatter predictions and CT reconstructions closer to ground truth, offering measurement accuracy comparable to standard MC simulations. Compared with scatter kernel-based methods and other deep learning-based approaches, the proposed method exhibits superior accuracy and robustness across diverse objects and system geometries, making it a reliable solution for accurate scatter measurement in clinical settings.

  • Dual-Source CBCT for Large FoV Imaging Under Short-Scan Trajectories

    by Tianling Lyu, Xusheng Zhang, Xinyun Zhong, Zhan Wu, Yan Xi, Wei Zhao, Yang Chen, Yuanjing Feng, Wentao Zhu

    Cone-beam CT is extensively used in medical diagnosis and treatment. Despite its large longitudinal field of view (FoV), the horizontal FoV of CBCT systems is severely limited due to the detector width. Certain commercial CBCT systems increase the horizontal FoV by employing the offset detector method. However, this method necessitates 360° full circular scanning trajectory which increases the scanning time and is not compatible with specific CBCT system models. In this paper, we investigate the feasibility of large FoV imaging under short scan trajectories with an additional X-ray source. A dual-source CBCT geometry is proposed as well as two corresponding image reconstruction algorithms. The first one is based on cone-parallel rebinning and the subsequent employs a modified Parker weighting scheme. Theoretical calculations demonstrate that the proposed geometry achieves a wider horizontal FoV than the 90% detector offset geometry (radius of 214.83mm vs. 198.99mm) with a significantly reduced rotation angle (less than 230° vs. 360°). As demonstrated by experiments, the proposed geometry and reconstruction algorithms obtain comparable imaging qualities within the FoV to conventional CBCT imaging techniques. Implementing the proposed geometry is straightforward and does not substantially increase development expenses. It possesses the capacity to expand CBCT applications even further.

  • Cone-Beam Computed Tomography Limited-Angle Image Reconstruction Using Planning CT-Guided Deep Diffusion Model

    by Zhan Wu, Yang Yang, Dianlin Hu, Tianling Lyu, Yinsheng Li, Hao Tang, Huazhong Shu, Yan Xi, Yi Zhang, Yang Chen

    For existing image-guided radiation therapy (IGRT) systems, the limited angular range of the cone-beam computed tomography (CBCT) scanning improves the compactness of the system and compatibility between CBCT and linear accelerator (LINAC) configurations. However, the limited-angle CBCT (LA-CBCT) reconstruction under incomplete projection data causes severe artifacts in the reconstructed images, further having a negative impact on the registration accuracy in IGRT. In this article, we propose a planning CT-guided deep diffusion model, termed LARGE-DiffNet, to improve imaging quality and registration accuracy for LA-CBCT image reconstruction. In stark contrast to existing approaches leveraging hand-crafted regularization, such as local smoothness and/or sparsity of the image, LARGE-DiffNet learns the distribution-level prior knowledge to describe the features of ideal CBCT images via a planning CT-guided diffusion model. The proposed LARGE-DiffNet is evaluated on the clinical CBCT dataset, and extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art (SOTA) methods. The proposed LARGE-DiffNet technique has great potential in IGRT.


  • RSTAR4D: Rotational Streak Artifact Reduction in 4-D CBCT Using Separable 4-D Convolutions

    by Ziheng Deng, Hua Chen, Yongzheng Zhou, Haibo Hu, Zhiyong Xu, Tianling Lyu, Yan Xi, Yang Chen, Jiayuan Sun, Jun Zhao

    Four-dimensional cone-beam computed tomography (4D CBCT) provides respiration-resolved images and facilitates image-guided radiation therapy. However, the ability to reveal respiratory motion comes at the cost of image artifacts. As raw projection data are sorted into multiple respiratory phases, the reconstructed 4D CBCT images are covered by severe streak artifacts. Although several deep learning-based methods have been proposed to address this issue, most algorithms formulate it as a 2D image enhancement task, neglecting the dynamic nature of 4D CBCT. In this paper, we first identify the origin and appearance of streak artifacts in 4D CBCT images. We find that streak artifacts exhibit a unique “rotational motion” along with the patient’s respiration, distinguishable from diaphragm-driven respiratory motion in 4D space. Therefore, we introduce RSTAR4D-Net, a 4D model that performs Rotational STreak Artifact Reduction by exploring the dynamic prior of 4D CBCT images. Specifically, we overcome the computational and training difficulties of a 4D neural network. The specially designed model decomposes the 4D convolutions into multiple lower-dimensional operations and thus efficiently processes a whole 4D image. Additionally, a Tetris training strategy is proposed to effectively train the model using limited 4D data. Extensive experiments substantiate the superior performance of RSTAR4D-Net compared to existing methods.


  • PRAISE-Net: Deep Projection-Domain Data-Consistent Learning Network for CBCT Metal Artifact Reduction

    by Zhan Wu, Xinyun Zhong, Tianling Lyu, Yan Xi, Xu Ji, Yi Zhang, Shipeng Xie, Hengyong Yu, Yang Chen

    High-attenuation metal implants can cause metal artifacts in cone-beam CT (CBCT) scanning due to their strong and energy-dependent photon-absorption ability. These artifacts severely degrade image quality in intraoperative radiotherapy and postoperative diagnosis for clinical physicians. The conventional projection-domain metal artifact reduction (MAR) methods for fan-beam geometry are not efficiently applicable to CBCT MAR, because metallic implants in cone-shaped X-ray beam scanning lead to serious data missing at all the projection views. To tackle the aforementioned challenge, we present a novel PRojection-domAIn data-conSistent lEarning network, i.e., PRAISE-Net, to suppress CBCT metal artifacts. First, a Low2High strategy which inpaints metal traces at low resolution and restores high-resolution results with a super-resolution reconstruction module is proposed to reduce computation costs. Second, a PIG-DDPM module with prior knowledge is designed for fine-grained projection-domain metal area inpainting. Third, a CBCT Domain Adaptation (CBCT-DA) is incorporated in the PIG-DDPM to step across the gap between simulated data and clinical CBCT data. The proposed PRAISE-Net is trained and evaluated on a publicly available dataset and a private clinical CBCT dataset, and our results confirm that the proposed method outperforms the state-of-the-art competing methods. This efficient, accurate, and reliable CBCT MAR technique has a great potential for clinical applications.