XZXiaoming Zhang

Xiaoming Zhang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xiaoming Zhang has a total of 74 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Anatomy-Conditioned Domain Randomization for Zero-Shot 3D Cerebrovascular Segmentation

    by Matteo Pentassuglia, Xiaoming Zhang, Benjamin Billot, Maria A. Zuluaga

  • Large-scale AI-guided liver malignancy diagnosis: multicenter study and a single-arm trial

    by Xiaoming Zhang, Chunli Li, Xu Han, Xiaoli Yin, Chaoya Zhang, Jian Zhou, Kai Cao, Qi Liu, Yang Hong, Yingshan Gao, et al.

    Liver malignancies are frequently evaluated on contrast-enhanced computed tomography (CE-CT), but missed or delayed diagnoses remain a clinically important challenge in high-volume, real-world radiology workflows, highlighting the need for scalable diagnostic safety net approaches. To address this, we developed the Liver DiagnOsis Network (LiON), a CE-CT-based artificial intelligence (AI) system that supports flexible multiphase processing, clinical data integration and workflow-compatible liver malignancy diagnosis. LiON was trained on 6,443 patients and retrospectively validated across 22,251 patients from multicenter and real-world cohorts. LiON achieved high performance for malignancy diagnosis, with an area under the receiver operating characteristic curve (AUC) of 0.975 (95% confidence interval (CI): 0.971−0.979), and maintained robust performance in real-world cohorts and among patients with hepatic steatosis (AUC 0.971, 95% CI: 0.952−0.985) and cirrhosis (AUC 0.924, 95% CI: 0.901−0.946). We then conducted a single-arm trial in 10,333 patients in routine clinical practice, in which LiON functioned as an additional AI reader within the existing clinical workflow. The trial met its primary endpoint, defined as an AUC for malignancy diagnosis with the lower bound of the 95% CI exceeding 0.900, achieving an AUC of 0.952 (95% CI: 0.942−0.961). Secondary outcomes demonstrated that AI−human collaboration identified 51 previously overlooked lesions (15 malignancies) and triggered 37 amended radiology reports, 22 multidisciplinary team escalations and clinical management changes in a subset of patients. These findings suggest that AI, when deployed as a workflow-compatible diagnostic support, may help reduce missed or delayed diagnoses and guide clinical interventions. Nevertheless, further evidence from prospective comparative studies across diverse healthcare systems is warranted to assess effects on clinical outcomes. ClinicalTrials.gov identifier: NCT07153783.


  • Top Cited Papers
    Open Access

    Multi-modal AI for opportunistic screening, staging and progression risk stratification of steatotic liver disease

    by Yuan Gao, Chunli Li, Wanxing Chang, Bai Du, Xianghua Ye, Yee Hui Yeo, Yingda Xia, Heng Guo, Xiaoming Zhang, Wei Liu, et al.

    The global rise in steatotic liver disease poses a significant public health challenge. While non-contrast computed tomography scans hold promise for opportunistic detection of steatotic liver disease, their potential for staging and risk assessment remains underexplored. Here we present a multimodal AI model trained on a large dataset, comprising of (n=968) histopathologically and (n=1103) radiologically confirmed cases, validated against both histology (n=660) and MRI-PDFF (n=375) gold standards, demonstrating high accuracy in detecting mild to severe steatosis (AUC: 0.904-0.929) and clinically significant fibrosis (AUC: 0.824-0.888). Furthermore, integrating the model into the standard clinical pathway improves primary risk screening in a retrospective patient cohort (n=1192), identifying 36% more patients at risk of fibrosis progression. Using Cox proportional hazard model, we observe that the intermediate-high risk patients identified by the optimized clinical pathway exhibits a significantly higher incidence of cirrhosis (hazard ratio: 5.54: 2.69-11.42), showcasing the model's potential for early detection and management of steatotic liver disease.


  • Non-contrast CT esophageal varices grading through clinical prior-enhanced multi-organ analysis

    by Xiaoming Zhang, Chunli Li, Jiacheng Hao, Yuan Gao, Danyang Tu, Jianyi Qiao, Xiaoli Yin, Le Lu, Ling Zhang, Ke Yan, et al.


  • Open Access

    Can diffusion-based generated magnetic resonance images predict glioma methylation accurately?

    by Xiaoming Zhang, Chunli Li, Tianrui Li, Junpeng Li, Mengting Yin, Yang Zhou

    Background: Reconstructing accelerated magnetic resonance images across various modalities, particularly those involving pathological features such as brain tumors, represents a challenging yet crucial task for medical diagnostics. While deep learning approaches have improved reconstruction quality, existing methods often struggle with preserving diagnostic features across different contrasts. The development of methods that maintain pathological details while substantially reducing scan time remains a clinical need. The purpose of this study is to develop a generative model capable of reconstructing high-quality sequences from accelerated T1-weighted scans, while preserving pathological features critical for glioma diagnosis and MGMT prediction. Methods: In this retrospective study using the BraTS 2021 dataset (n=1,480), we present a diffusion-based generative model capable of producing enhanced magnetic resonance images from T1-weighted scans for T1 contrast-enhanced (T1CE), T2, and fluid attenuated inversion recovery (FLAIR) sequences. Our model was trained on 785 scans and validated on 695 scans with MGMT using 5-fold cross-validation. Simulating K-space degradation, our model recreates the effects of quicker scans at 4-fold and 32-fold acceleration. Results: For 4-fold acceleration, quantitative assessment showed high fidelity reconstruction across sequences [T1CE: structural similarity (SSIM) =0.972, peak signal-to-noise ratio (PSNR) =37.43; T2: SSIM =0.963, PSNR =33.44; FLAIR: SSIM =0.963, PSNR =34.16]. Two radiologists’ visual assessments showed no significant differences between reconstructed and original images (P>0.05). The synthesized images also demonstrated consistent methylation classification, showing strong agreement for T1CE: concordance correlation coefficient (CCC) =0.966, R2=0.938; T2: CCC =0.945, R2=0.893; FLAIR: CCC =0.963, R2=0.928. Area under curve values for MGMT prediction remained stable across original and reconstructed images (FLAIR: 0.606, 0.603, 0.601 for original, 4-fold, and 32-fold acceleration, respectively). Conclusions: Our diffusion-based model demonstrates promise in accelerating magnetic resonance image acquisition while preserving vital pathological detail, suggesting enhanced diagnostic capabilities. Future research will evaluate its clinical application, aiming to enhance procedural efficiency and patient comfort.

  • MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution

    by Chengxing Xie, Xiaoming Zhang, Linze Li, Yuqian Fu, Biao Gong, Tianrui Li, Kai Zhang

    Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent drawbacks, especially the significantly increased computational demands. Moreover, the feature perception within a fixed-size window of existing models restricts the effective receptive field (ERF) and the intermediate feature diversity. We demonstrate that a flexible integration of attention across diverse spatial extents can yield significant performance enhancements. In line with this insight, we introduce Multi-Range Attention Transformer (MAT) for SR tasks. MAT leverages the computational advantages inherent in dilation operation, in conjunction with self-attention mechanism, to facilitate both multi-range attention (MA) and sparse multi-range attention (SMA), enabling efficient capture of both regional and sparse global features. Combined with local feature extraction, MAT adeptly capture dependencies across various spatial ranges, improving the diversity and efficacy of its feature representations. We also introduce the MSConvStar module, which augments the model’s ability for multi-range representation learning. Comprehensive experiments show that our MAT exhibits superior performance to existing state-of-the-art SR models with remarkable efficiency (∼ 3.3× faster than SRFormer-light). The codes are available at https://github.com/stella-von/MAT.


  • Open Access

    Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation

    by Xiaole Zhao, Linze Li, Chengxing Xie, Xiaoming Zhang, Ting Jiang, Wenjie Lin, Shuaicheng Liu, Tianrui Li

    Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the complex calculation of multi-head self-attention (MSA), seriously hindering their practical application and deployment. In this work, we present an efficient SR model to mitigate the dilemma between model efficiency and SR performance, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA). From the perspective of information theory, EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. On the other hand, SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features. Since the implementation of EA and SLKA does not involve complex computations (such as extensive matrix multiplications), the proposed method can achieve faster nonlinear inference than Transformer-based SR models while maintaining better SR performance. Extensive experiments show that the proposed model can significantly reduce the delay of model inference while achieving the SR performance comparable with other advanced models.


  • Open Access

    Hi-ResNet: Edge Detail Enhancement for High-Resolution Remote Sensing Segmentation

    by Yuxia Chen, Pengcheng Fang, Xiaoling Zhong, Jianhui Yu, Xiaoming Zhang, Tianrui Li

    High-resolution remote sensing (HRS) semantic segmentation extracts key objects from high-resolution coverage areas. However, objects of the same category within HRS images generally show significant differences in scale and shape across diverse geographical environments, making it difficult to fit the data distribution. Additionally, a complex background environment causes similar appearances of objects of different categories, which precipitates a substantial number of objects into misclassification as background. These issues make existing learning algorithms sub-optimal. In this work, we solve the above-mentioned problems by proposing a High-resolution remote sensing network (Hi-ResNet) with efficient network structure designs, which consists of a funnel module, a multi-branch module with stacks of information aggregation (IA) blocks, and a feature refinement module, sequentially, and class-agnostic edge aware (CEA) loss. Specifically, we propose a funnel module to downsample, which reduces the computational cost, and extracts high-resolution semantic information from the initial input image. Secondly, we downsample the processed feature images into multi-resolution branches incrementally to capture image features at different scales. Furthermore, with the design of the Window multi-head self-attention, SE attention, and Depth-Wise convolution, the light-efficient IA blocks are utilized to distinguish image features of the same class with variant scales and shapes. Finally, our feature refinement module integrates the CEA loss function, which disambiguates inter-class objects with similar shapes and increases the data distribution distance for correct predictions. With effective pre-training strategies, we demonstrate the superiority of Hi-ResNet over the existing prevalent methods on three HRS segmentation benchmarks.


  • Lightweight Remote-Sensing Image Super-Resolution via Re-Parameterized Feature Distillation Network

    by Tianlin Zhang, Chunjiang Bian, Xiaoming Zhang, Hongzhen Chen, Shi Chen

    Recent deep learning based-works have made remarkable progress in Remote-Sensing Image Super-Resolution (RSISR). However, the complicated network architecture as well as a huge amount of parameters increase computational cost, hindering their practical deployment. To alleviate this problem, we propose a novel Re-parameterized Feature Distillation Network (ReFDN) for lightweight and efficient RSISR tasks. Feature distillation, refinement, condensation, and enhancement are efficiently integrated into the re-parameterized feature distillation block named ReFDB for lighter and stronger feature extraction. With the help of elaborate re-parameterized convolution (ReConv) design, we further boost the feature refinement capability without extra inference costs. Additionally, we design an efficient channel and spatial attention module (ECSA) to enhance the important objects and regions of the intermediate features adaptively. Conducted on both commonly used datasets and additional Google Earth data, the experimental results demonstrate our method can achieve a good trade-off between SR performance and network complexity. Our code will be publicly available at https://github.com/DaxingZ/ReFDN.


  • Response to pain by different gestational age neonates

    by Xia Chuanxiong, Yang Lei, Zhao Ping, Zhang Xiaoming

    One hundred infants were divided into the following 3 gestational age (GA) groups: (I) premature infants (n=30) with the gestational age between 29 and 32 weeks; (II) premature infants (n=30) with the gestational age between 33 and 36 weeks; (III) full-term infants (n=40). The recorded responses of all infants to pain included the behavioral responses to painful stimuli (cry, facial activity and limbs movement) and the variety of heart rate. The results indicated that the infants of 3 groups had different degree response to various painful stimuli. Pain expression in full term infants was more significant than premature infants to same stimuli. 33-weeks GA infants were differential from 29-weeks GA infants. Full term infants showed more vertical mouth stretch and more taut tongue and more hand to mouth than premature infants, but more horizontal mouth stretch in premature infants.