WXWeini Xin

Weini Xin

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Weini Xin has a total of 45 co-authors. Here are the top co-authors by number of shared publications:

  • Bo Peng

    State Key Laboratory of Flexible Electronics (LoFE) & Institute of Flexible Electronics (IFE), Northwestern Polytechnical University, 127 West Youyi Road, Xi’an 710072, China

    2 shared publications
  • Chen-Zhong Li

    Department of Biomedical Engineering, School of Medicine, The Chinese University of Hong Kong (Shenzhen)

    2 shared publications
  • Cheng Jiang

    School of Medicine, The Chinese University of Hong Kong, Shenzhen, China

    2 shared publications
  • Huangan Liao

    School and Hospital of Stomatology, Guangdong Engineering Research Center of Oral Restoration and Reconstruction, Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou Medical University, Guangzhou, China

    2 shared publications
  • Huibin Ma

    Hospital of Stomatology Shantou University Medical College, Shantou, China

    2 shared publications
  • Ji Jie

    Network & Information Center of Shantou University, Shantou, China

    2 shared publications

Latest Publications

  • An amplification-free dual-readout biosensor integrating colorimetry and single-particle counting for ultrasensitive miRNA detection in esophageal cancer

    by Wenjing Zhang, Anyu Wang, Zheyan He, Jiali Chen, Yuhang Zhou, Xinying Li, Weini Xin, Xiaohui Zheng, Chenzhong Li, Cheng Jiang

  • Open Access

    Impact of moodle-based clinically oriented blended teaching on educational environment and clinical competence in dental materials: a prospective quasi‑experimental study

    by Kexiao Chen, Zhanyu Huang, Yinan Wang, Xiaoran Zhao, Weini Xin

    Dental materials science, a foundational discipline in stomatology, faces persistent challenges in traditional pedagogy: voluminous content, outdated textbooks, and a disconnect between theoretical knowledge and clinical application. Students often memorize material parameters passively without developing the capacity to translate this knowledge into real-world clinical decision-making. Blended learning platforms such as Moodle offer a promising avenue to bridge this gap through clinically oriented supplementary instruction. This study aimed to construct and evaluate a Moodle-based, clinically oriented online supplementary course in dental materials, and to examine its differential effects on students at different educational stages. A prospective quasi-experimental design with pre- and post-test comparisons was employed. A total of 60 undergraduate dental students were enrolled, comprising 30 fourth-year students (pre-clinical, G4) and 30 fifth-year students (clinical internship, G5). All participants completed a 4-week Moodle-based online supplementary course featuring H5P interactive videos, virtual case decision-making modules, and structured peer-review exercises. Learning outcomes were assessed via a self-developed Clinical Case Test (CCT) scored independently by two clinical teachers (ICC > 0.8), a modified Dundee Ready Education Environment Measure (DREEM) inventory (Cronbach's α = 0.947), and a course satisfaction questionnaire (Cronbach's α = 0.927). Statistical analysis was performed using paired and independent samples t-tests with α = 0.05. Both groups perceived the educational environment positively (overall DREEM score rate 82.35%). After the intervention, G4 students demonstrated a significant improvement in case analysis scores (24.30 ± 4.34 to 28.33 ± 6.76, P = 0.0083), while total CCT scores showed marginal significance (70.83 ± 7.79 to 75.73 ± 11.46, P = 0.0583). G5 students showed no significant change in total scores (75.77 ± 8.17 to 77.53 ± 9.86, P = 0.4532) but significant improvement in case analysis (29.57 ± 4.80 to 33.87 ± 4.97, P = 0.0012). Post-intervention, G4 CCT scores were statistically indistinguishable from G5 baseline scores (P = 0.5170), indicating that the intervention elevated pre-clinical students to near-internship levels. DREEM subscale comparisons revealed G4 scored significantly higher than G5 in Students' Perception of Learning (SPL: 47.40 ± 6.66 vs. 43.30 ± 9.00, P = 0.050) and Social Self-Perception (SSP: 13.03 ± 1.99 vs. 11.80 ± 2.55, P = 0.042). Course satisfaction was high overall (G4: 87.77 ± 11.74; G5: 83.20 ± 13.33), with 71.67% of students affirming that blended teaching most helped with "knowledge integration and clinical transformation." Moodle-based clinically oriented blended teaching enhances dental students' clinical case analysis competence, particularly for students at the pre-clinical stage. The platform effectively bridges the gap between theoretical knowledge and clinical application, positioning it as a valuable supplementary tool for clinical pre-education. Platform design should be dynamically adapted to students' clinical experience levels.

  • Open Access

    Brain-Derived Extracellular Vesicle Subpopulations: from Bulk Measurements to Single-Entity Assays

    by Shiyao Bai, Leyi Chen, Wenjing Zhang, Mingyuan Li, Han Liu, Xiaowen Huang, Lianqun Zhou, Weini Xin, Cheng Jiang, Chen-Zhong Li

    Neurodegenerative diseases (NDs), such as Alzheimer’s disease (AD) and Parkinson’s disease (PD), pose a significant global health challenge, currently affecting over 40 million individuals and placing a heavy burden on healthcare systems. Existing diagnostic methods, such as neuroimaging and cognitive assessments, often lack sufficient sensitivity and specificity, especially in the early stages of disease. This underscores the need for novel biomarkers. Extracellular vesicles (EVs), particularly those derived from the brain, i.e., brain-derived extracellular vesicles (BDEVs), hold great potential as noninvasive diagnostic tools due to their ability to reflect the physiological and pathological states of their cells of origin. However, isolation and detection of such EV subpopulations from accessible body fluids such as blood remain a technical challenge due to their low abundance and overlapping physical properties compared to other EVs. This review discusses rationally designed isolation and detection technologies for EVs from major brain cell subpopulations and their integration with emerging fields like AI and big data analysis. We specifically contrast traditional ensemble-averaged bulk measurements with emerging single-entity assays, highlighting how the latter bypass biological noise to resolve rare BDEV subpopulations. It highlights the potential of these EV subpopulations as biomarkers, addresses EV isolation challenges and proposes standardized methodologies, and emphasizes the need for comprehensive profiling of EV markers at single-entity level, and point-of-care testing (POCT) development.

  • Open Access

    Advances in deep learning for bacterial image segmentation in optical microscopy

    by Zhijun Tan, Yang Ding, Huibin Ma, Jintao Li, Danrou Zheng, Hua Bai, Weini Xin, Lin Li, Bo Peng

    Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics, offering critical insights into bacterial physiology and pathogenicity. Image segmentation techniques enable quantitative analysis of bacterial structures, facilitating precise measurement of morphological variations and population behaviors at single-cell resolution. This paper reviews advancements in bacterial image segmentation, emphasizing the shift from traditional thresholding and watershed methods to deep learning-driven approaches. Convolutional neural networks (CNNs), U-Net architectures, and three-dimensional (3D) frameworks excel at segmenting dense biofilms and resolving antibiotic-induced morphological changes. These methods combine automated feature extraction with physics-informed postprocessing. Despite progress, challenges persist in computational efficiency, cross-species generalizability, and integration with multimodal experimental workflows. Future progress will depend on improving model robustness across species and imaging modalities, integrating multimodal data for phenotype-function mapping, and developing standard pipelines that link computational tools with clinical diagnostics. These innovations will expand microbial phenotyping beyond structural analysis, enabling deeper insights into bacterial physiology and ecological interactions.


  • Open Access

    Deep learning for automated mandibular canal segmentation in CBCT scans

    by Jingna Huang, Ji Jie, Huibin Ma, Shimin Xie, Huangan Liao, Kexiong Ouyang, Weini Xin

    This study aims to develop a framework for automated mandibular canal segmentation in cone beam computed tomography (CBCT) scans. The dataset, source code, and trained models are publicly accessible, allowing for reproducibility and further development by the research community. A total of 236 CBCT scans were collected from the Stomatology Hospital of the Shantou University Medical College, and the mandibular canals in these scans were manually annotated with fine granularity. A custom-designed 3D U-Net, named ManCan_ResU-Net, along with two commonly used 3D U-Net models, was employed as candidate models. The soft Dice Similarity Coefficient (DSC) loss was used as the loss function. During inference, a post-processing step involving connected components analysis and removal of small disconnected objects was applied to refine the segmentation results. Model performance was evaluated using following metrics: voxel accuracy (ACC), sensitivity (SEN), specificity (SPE), DSC, Hausdorff distance (HD), 95th percentile Hausdorff distance (HD95), average surface distance (ASD), and average symmetric surface distance (ASSD). The MCSTU dataset, which contains a development dataset (218 CBCT images) and an independent test dataset (18 CBCT images) with fine-grained annotations, has been made publicly available. The validation loss of ManCan_ResU-Net was lower than those of two commonly used models. Incorporating post-processing significantly improved model performance, particularly by reducing the HD metric. On the hold-out test dataset, the ManCan_ResU-Net model achieved ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.86 (0.83–0.87), 1 (1–1), 0.85 (0.83–0.86), 10.1 (8.67–13.6), 1.8 (1.6–2.2), 0.69 (0.58–0.85), and 0.72 (0.6–0.83), respectively. On the test dataset, the ManCan_ResU-Net model obtained ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.93 (0.91–0.95), 1 (1–1), 0.80 (0.79–0.81), 21.3 (11.7–53.9), 2.59 (2.33–3), 1 (0.96–1.21), and 0.92 (0.861–1), respectively. Both the code and trained models are publicly available. The proposed segmentation framework achieved strong performance on both the hold-out and independent test datasets. In the future, after further validation of the model’s generalization ability, it may be applied in real clinical settings for oral surgery planning.


  • Open Access

    Automated Mandibular Canal Segmentation on CBCT using Deep Learning

    by Jingna Huang, Ji Jie, Huibin Ma, Shimin Xie, Huangan Liao, Kexiong Ouyang, Weini Xin

    Objective: This study aims to develop a publicly accessible dataset for mandibular canal segmentation in cone beam computed tomography (CBCT) scans and to propose a framework for automated mandibular canal segmentation. Methods: A total of 236 CBCT scans were collected from the Stomatology Hospital of the Shantou University Medical College, and the mandibular canals in these files were finely annotated. A custom designed 3D UNet, named MyResUNet, along with two commonly used UNet models, were used as candidate models. Soft dice similarity coefficient (DSC) loss was used as the loss function. A post-processing step involving connected components analysis and removing small objects was applied during inference. Model performance was assessed using voxel accuracy (ACC), sensitivity (SEN), specificity (SPE),DSC(1), Hausdorff distance (HD), the 95th percentile Hausdorff distance (HD95), average surface distance (ASD), and average symmetric surface distance (ASSD). Results: The MCSTU dataset, which contains a development dataset and an independent test dataset comprising 218 and 18 CBCT images with fine-grained annotations, respectively, has been made publicly available. The validation loss of MyResUNet was lower than that of two commonly used models. The inclusion of post-processing significantly enhanced the performance, especially by reducing the HD metric. On the hold-out test dataset, the MyResUNet model achieved ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1-1), 0.86 (0.83-0.87), 1 (1-1), 0.85 (0.83-0.86), 10.1 (8.67-13.6), 1.8 (1.6-2.2), 0.69 (0.58-0.85), and 0.72 (0.6-0.83), respectively. On the test dataset, the MyResUNet model obtained ACC, SEN, SPE, DICE, HD, HD95, ASD, ASSD(2, 3)with 95% confidence interval of 1 (1-1), 0.93 (0.91-0.95), 1 (1-1), 0.80 (0.79-0.81), 21.3 (11.7-53.9), 2.59 (2.33-3), 1 (0.96-1.21), and 0.92 (0.861-1), respectively. Both the code and trained models are publicly available. Conclusion: The proposed segmentation framework achieved strong performance on both the hold-out and independent test datasets. In the future, after further validation of the model’s generalization ability, it may be applied in real clinical settings for oral surgery planning.

  • Open Access

    Artificial Intelligence for Organelle Segmentation in Live-Cell Imaging

    by Yang Ding, Zhijun Tan, Jintao Li, Weisen Zhang, Bin Fang, Hua Bai, Weini Xin, Nicolas H. Voelcker, Bo Peng, Lin Li

    Organelle morphology and dynamics are closely linked to cellular function and fate, yet their relationships remain poorly defined across physiological and pathological contexts. Live-cell imaging enables the visualization of subcellular structures and dynamic processes but often requires extensive manual analysis, introducing variability and limiting reproducibility and throughput. Image segmentation partitions digital images into meaningful regions, facilitating the quantification of organelle morphology and molecular behavior for precise subcellular analysis. Herein, this review surveys recent advances in live-cell imaging segmentation algorithms across diverse organelles, from traditional thresholding-based methods to deep learning approaches that enhance accuracy and adaptability in complex biological environments. We discuss key challenges, including 3-dimensional imaging, multi-organelle segmentation, and generalization across diverse imaging modalities. We also highlight label-efficient strategies, synthetic data, and physics-guided modeling that reduce reliance on manual annotations and large annotated datasets. By advancing generalist models, these innovations improve quantitative cell biology, accelerate disease research, and drive therapeutic discovery, underscoring the transformative role of artificial intelligence in biomedical microscopy.


  • Open Access

    Sicca Symptoms, Oral Health Conditions, Salivary Flow and Oral Candida in Sjögren’s Syndrome Patients

    by Weini Xin, Katherine Chiu Man Leung, Edward Chin Man Lo, Mo Yin Mok, Moon Ho Leung

    This study aimed to investigate the relationships among sicca symptoms, oral health conditions, salivary profiles and oral Candida in Sjögren’s syndrome (SS) patients. Eighty-five SS patients (mean age = 50.5) and 40 healthy non-SS individuals (mean age = 51.4) were recruited. They self-completed the Sicca Symptoms Inventory (SSI). Decayed, missing and filled surface (DMFS) scores, salivary flow rates, pH and oral Candida colonization were determined. Mean SSI summary scores of SS patients and non-SS individuals were 11.1 and 5.4 respectively (p < 0.001). The most prevalent sicca symptoms in SS patients were eye irritation (93%), dry throat or nose (88%) and need of fluid for mouth wetting (88%). SS patients had significantly lower whole salivary flow rates than the non-SS individuals. Candida strains were isolated from over 60% of SS patients but not in non-SS patients. C. albicans was the predominant species. SSI summary score was negatively correlated to salivary flow rates while SSI summary and domain scores were positively correlated to the number of filled surfaces (FS) and DMFS scores and oral Candida counts. In conclusion, SS patients had more severe sicca symptoms than non-SS individuals. SSI scores were negatively correlated to the salivary flow rates but positively correlated to caries experience and oral Candida colonization.