WHWei Hu

Wei Hu

*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


Wei Hu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:

  • Akram Osman

    Xinjiang Medical University, Ürümqi, Ürümqi, China

    2 shared publications
  • Adina Abulizi

    Department of Radiology

    1 shared publication
  • Ehsan Abduhani

    The Second Spine Department of the Fourth School of Clinical Medicine of Xinjiang Medical University, Spine Department of the First Affiliated Hospital of Shihezi University, Shihezi, China

    1 shared publication
  • Haiting Ma

    Department of Radiology

    1 shared publication
  • Jiangbin Wang

    Department of Radiology

    1 shared publication
  • Jianhua- Sun

    The Second Spine Department of the Fourth School of Clinical Medicine of Xinjiang Medical University, Spine Department of the First Affiliated Hospital of Shihezi University, Shihezi, China

    1 shared publication

Latest Publications

  • Open Access

    Computer-aided detection of equivocal spinal tuberculosis on X-ray using a YOLOv11-based deep learning model

    by Yan Yuan, Juan Ma, Haiting Ma, Mei Zhang, Xinyue Qiu, Lingyan Shen, Zhenwei Ren, Jiangbin Wang, Adina Abulizi, Wei Hu, et al.

    Background: Spinal tuberculosis (STB), also known as Pott's disease or tuberculous spondylitis, remains a substantial clinical burden in some remote and resource-limited regions, where X-ray imaging is often the primary modality available for initial assessment. However, early- and mid-stage STB frequently presents with subtle, equivocal, or atypical structural changes on X-ray images, which may lead to delayed recognition and referral in primary-care settings. Investigating suspicious-region localization in cases with clinical suspicion of STB but equivocal X-ray findings may provide supportive information for further imaging evaluation and referral decisions in primary-care settings. Methods: This retrospective study included 307 patients from three tertiary hospitals, all of whom had equivocal X-ray findings and CT-confirmed STB. CT-referenced suspicious-region annotations were established on X-ray images according to the CT-confirmed involved spinal levels and their anatomical correspondence on radiographs. A single-class suspicious-region localization model was developed based on the YOLOv11 object detection framework, and the dataset was split at the patient level into training and test sets. Model performance was evaluated using mAP@0.5, mAP@0.5:0.95, precision, recall, F1-confidence curves, precision-recall curves, and confidence-related curves. Patient-level detection rate and missed-case rate were further introduced to evaluate case-level alerting performance. To assess the spatial correspondence between CT-referenced annotations and suspicious regions visible on X-ray images, an agreement analysis between X-ray-only blinded annotations and CT-referenced annotations was additionally performed. Results: On the test set, the YOLOv11 model achieved an mAP@0.5 of 0.7664, an mAP@0.5:0.95 of 0.4520, a precision of 0.8358, and a recall of 0.6215. Threshold-related curves showed a trade-off between precision and recall across different confidence thresholds. At the provisional working threshold of 0.25, the patient-level detection rate was 0.8073, with a missed-case rate of 0.1927, indicating that the model could provide at least one suspicious-region prompt in most CT-confirmed positive test cases. The agreement analysis showed that all 40 randomly selected test cases could be annotated with at least one suspicious region based on X-ray images alone. The mean maximum IoU between X-ray-only blinded annotations and CT-referenced annotations was 0.7542; 34/40 cases reached a maxIoU ≥0.5, and 38/40 cases reached a maxIoU ≥0.3. Conclusion: This study shows that, using X-ray images alone as input, a deep learning model can provide suspicious-region localization prompts for CT-confirmed STB cases with equivocal X-ray findings. The proposed approach provides a feasible proof-of-concept framework for early risk prompting and referral support for STB in resource-limited settings. Further studies incorporating normal cases and non-tuberculous spinal disease controls, as well as external validation and prospective evaluation, are required to assess its applicability in real-world primary-care settings.

  • Open Access

    Effect of spinal orthosis on clinical outcomes of patients after oblique lumbar interbody fusion: a randomized controlled trial study protocol

    by Nian-Rong Han, Akram Osman, Wei Hu, Yi-Fei Huang, Yan-Lu Liu, Zhan-Jun Ma

    Background: Oblique lumbar interbody fusion (OLIF) is an internationally popular minimally invasive technology for the treatment of various lumbar diseases. Since its introduction to China in 2014, OLIF technology has clearly shown its superiority in reconstructing intervertebral stability, restoring intervertebral space height, achieving indirect decompression, and restoring normal lumbar sequence. However, some patients still suffer from persistent symptoms after OLIF, including low back pain and soreness, which indirectly affect the overall surgical efficacy and patient satisfaction. Therefore, some clinicians recommend that patients routinely use spinal orthoses after OLIF to reduce the stress on the lower back muscles and ligaments, thereby relieving or avoiding postoperative residual symptoms or new symptoms. Accordingly, spinal orthosis use after OLIF has emerged as an essential option. However, the role of spinal orthoses in OLIF and their specific impact on postoperative patient clinical outcomes have remained unclear, and there is a lack of strong clinical evidence to indirectly or directly support the role of spinal orthoses in OLIF and demonstrate their impact on patient clinical outcomes. This study aims to investigate the role of spinal orthoses in OLIF by grouping patients based on the use or nonuse of spinal orthosis after OLIF, thus providing a better basis for the majority of patients and physicians. Methods/design: We plan to conduct a 1-year randomized controlled trial involving 60 subjects. The subjects will be randomized into two groups: group A (those wearing spinal orthoses after surgery) and group B (those not wearing spinal orthoses after surgery). The clinical outcomes of these patients will be evaluated using the Oswestry disability index, visual analog scale, and Brantigan, Steffee, Fraser 1 day before surgery and 2 weeks and 1, 6, and 12 months after surgery. Discussion: This randomized controlled trial aims to provide a reference for further comprehensive trial design. The findings of this study will provide a better and more scientific basis for the choice of postoperative rehabilitation and treatment for patients undergoing such a procedure. Trial registration: This study has been registered in the Chinese Clinical Trial Registry (Registration No.: ChiCTR2200059000). Registration date: April 22, 2022. Registration website: http://www.chictr.org.cn/showproj.aspx?proj=166310


  • Open Access

    Caudal epidural steroid injections versus selective nerve root blocks for single-level lumbar spinal stenosis: a study protocol for a randomized controlled trial

    by Akram Osman, Wei Hu, Jianhua- Sun, Jing Li, Xiao Luo, Nianrong Han, Ehsan Abduhani, Zhenqiang Liu

    Background: Lumbar spinal stenosis (LSS) is a common degenerative condition associated with old age. Its incidence continues to increase with the rapidly aging population in China. Treatment for LSS usually begins with conservative treatments, as some patients refuse surgical procedures or have surgery contraindications. Caudal epidural steroid injections (CESIs) and selective nerve root blocks (SNRBs) are two commonly used conservative treatments for LSS, which have proven to be effective at relieving LSS symptoms in many studies. However, there are no randomized controlled trials comparing these two procedures. We planned the first study to assess which one of these two procedures is more effective in treating LSS. We will compare the efficacy of these two treatment methods in terms of duration of symptom relief and recurrence rate. We hope our findings will help clinicians choose an optimal treatment for LSS patients. Methods/design: We plan to conduct a 1-year randomized controlled trial that will include a total of 76 subjects. They will be randomly divided into two groups: group A (patients will receive CESIs) and group B (patients will receive SNRBs). Two days before the procedure, we will assess these patients using the Leeds Assessment of Neuropathic Symptoms and Signs (LANSS) pain scale, Oswestry Disability Index (ODI), and numeric rating scale (NRS) for pain. One day, 2 weeks, 3 months, 6 months, and 1 year after the procedure, we will assess the condition of these patients again with the NRS and ODI. Discussion: We hope our findings will lay the foundation for the design of further comprehensive studies and help clinicians make a choice between CESIs and SNRBs for LSS patients. Trial registration: Chinese Clinical Trial Registry ChiCTR1900028038. Registered on 8 December 2019