Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shijie Zhang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:

  • Guorong Lyu

    Department of Ultrasound, Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China

    2 shared publications
  • Shaozheng He

    Department of Ultrasound, Artificial Intelligence Professional Group, Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China

    2 shared publications
  • Dandan Wang

    Department of Ultrasound, Artificial Intelligence Professional Group, Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China

    1 shared publication
  • Guorong Lyu

    Department of Ultrasound, Second Affiliated Hospital of Fujian Medical University, Quanzhou, China

    1 shared publication
  • Jiangfeng Dai

    The Second Affiliated Hospital of Fujian Medical University

    1 shared publication
  • Jiawen Li

    The Second Affiliated Hospital of Fujian Medical University

    1 shared publication

Latest Publications

    • 20 July 2025
      • Vol. 45  (7) , 1563-1570

    [A multi-feature fusion-based model for fetal orientation classification from intrapartum ultrasound videos].

    by Ziyu Zheng, Xiaying Yang, Shengjie Wu, Shijie Zhang, Guorong Lyu, Peizhong Liu, Jun Wang, Shaozheng He

    To construct an intelligent analysis model for classifying fetal orientation during intrapartum ultrasound videos based on multi-feature fusion. The proposed model consists of the Input, Backbone Network and Classification Head modules. The Input module carries out data augmentation to improve the sample quality and generalization ability of the model. The Backbone Network was responsible for feature extraction based on Yolov8 combined with CBAM, ECA, PSA attention mechanism and AIFI feature interaction module. The Classification Head consists of a convolutional layer and a softmax function to output the final probability value of each class. The images of the key structures (the eyes, face, head, thalamus, and spine) were annotated with frames by physicians for model training to improve the classification accuracy of the anterior occipital, posterior occipital, and transverse occipital orientations. The experimental results showed that the proposed model had excellent performance in the tire orientation classification task with the classification accuracy reaching 0.984, an area under the PR curve (average accuracy) of 0.993, and area under the ROC curve of 0.984, and a kappa consistency test score of 0.974. The prediction results by the deep learning model were highly consistent with the actual classification results. The multi-feature fusion model proposed in this study can efficiently and accurately classify fetal orientation in intrapartum ultrasound videos.

  • Open Access

    Transperineal ultrasound measurement of the levator plate angle and anorectal angle is a useful method for evaluating uterine prolapse : a prospective cohort study

    by Jiangfeng Dai, Shunlan Liu, Jiawen Li, Shijie Zhang, Wu Xu, Guorong Lyu, Shaozheng He

    Background Confirming the patient's cervical position using transperineal ultrasound is not an easy task. This study aimed to employ transperineal ultrasound to measure the levator plate angle (LPA) and anorectal angle (ARA) in patients with varying degrees of uterine prolapse and to explore their efficacy in assessing uterine prolapse. Methods This prospective study consecutively enrolled 130 female patients who underwent examinations for lower urinary tract or pelvic floor dysfunction symptoms at the Second Affiliated Hospital of Fujian Medical University from August 2022 to December 2023. Participants were divided into three groups based on the Pelvic Organ Prolapse Quantification (POP-Q) system: POP-Q = 0 (n = 45), POP-Q = 1 (n = 45), and POP-Q ≥ 2 (n = 40). Transperineal ultrasound was used to measure the LPA and ARA at rest (rLPA and rARA) and during maximum Valsalva maneuver (vLPA and vARA). Changes in LPA and ARA from rest to maximal Valsalva (ΔLPA and ΔARA) were calculated. The differences in these ultrasound parameters among the three groups were compared. The area under the curve (AUC) was calculated to assess the diagnostic performance. Results With increasing severity of uterine prolapse, vLPA decreased progressively, while vARA and ΔARA initially decreased and then increased (P < 0.05). Compared with the POP-Q stage = 0 group, rLPA was reduced in the POP-Q stage ≥ 2 group, and ΔLPA was reduced in the POP-Q stage = 1 and POP-Q stage ≥ 2 groups (P < 0.05). The optimal cutoff values for diagnosing POP-Q stage ≥ 1 were 27.01° for rLPA, -2.29° for vLPA, and − 26.11° for ΔLPA, with corresponding AUCs of 0.65, 0.86, and 0.75. For diagnosing POP-Q stage ≥ 2, the optimal cutoff values were 24.11° for rLPA, -6.97° for vLPA, and − 34.57° for ΔLPA, with corresponding AUCs of 0.67, 0.80, and 0.69. DeLong's test indicated that vLPA had the highest efficacy in diagnosing both POP-Q stage ≥ 1 and POP-Q stage ≥ 2 (P < 0.05). Conclusion Transperineal ultrasound measurement of the LPA and ARA is a simple and effective method for assessing uterine prolapse.