Rapid vessel segmentation and reconstruction of head and neck angiograms from MR vessel wall images.

Journal: NPJ digital medicine
Published Date: Jul 28, 2025

Abstract

Three-dimensional magnetic resonance vessel wall imaging (3D MR-VWI) is critical for characterizing cerebrovascular pathologies, yet its clinical adoption is hindered by labor-intensive postprocessing. We developed VWI Assistant, a multi-sequence integrated deep learning platform trained on multicenter data (study cohorts 1981 patients and imaging datasets) to automate artery segmentation and reconstruction. The framework demonstrated robust performance across diverse patient populations, imaging protocols, and scanner manufacturers, achieving 92.9% qualified rate comparable to expert manual delineation. VWI Assistant reduced processing time by over 90% (10-12 min per case) compared to manual methods (p < 0.001) and improved inter-/intra-reader agreement. Real-world deployment (n = 1099 patients) demonstrated rapid clinical adoption, with utilization rates increasing from 10.8% to 100.0% within 12 months. By streamlining 3D MR-VWI workflows, VWI Assistant addresses scalability challenges in vascular imaging, offering a practical tool for routine use and large-scale research, significantly improving workflow efficiency while reducing labor and time costs.

Authors

  • Jin Zhang
    Department of Otolaryngology, The Second People's Hospital of Yibin, Yibin, Sichuan, China.
  • Wen Wang
    Clinical and Research Center for Infectious Diseases, Beijing Youan Hospital, Capital Medical University, Beijing, China.
  • Jinhua Dong
    United Imaging Healthcare CO., Ltd, Shanghai, China.
  • Xiong Yang
    School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China. Electronic address: xiong.yang@tju.edu.cn.
  • Shuwei Bai
    Shanghai Clinical Research and Trial Center, Shanghai, China.
  • Jiaqi Tian
    College of Food Science and Technology, Henan Agricultural University, Zhengzhou 450002, PR China.
  • Bo Li
    Electric Power Research Institute, Yunnan Power Grid Co., Ltd., Kunming, Yunnan, China.
  • Xiao Li
    Department of Inner Mongolia Clinical Medicine College, Inner Mongolia Medical University, Hohhot, Inner Mongolia, China.
  • Jianjian Zhang
    Department of Radiology, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Hangyu Wu
    Department of Radiology, Ningbo Hangzhou Bay Hospital, Ningbo, China.
  • Xiaoxi Zeng
  • Yongqiang Ye
    South TaiHu Hospital Affiliated to Huzhou College, Huzhou, China.
  • Shenghao Ding
    Department of Neurosurgery, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China.
  • Jieqing Wan
    Cerebrovascular Disease Center, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China. Electronic address: wjq_renji@126.com.
  • Ke Wu
    Shanghai Medical Aid Team in Wuhan, Shanghai General Hospital, Shanghai Jiao Tong University, School of Medicine, Shanghai, China.
  • Yufei Mao
    United Imaging Healthcare CO., Ltd, Shanghai, China.
  • Cheng Li
    College of Food and Bioengineering, Henan University of Science and Technology, Luoyang, China.
  • Na Zhang
    Department of Nutrition and Food Hygiene, School of Public Health, Peking University, Beijing, China.
  • Jianrong Xu
    Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200127.
  • Yongming Dai
    Central Research Institute, United Imaging Healthcare, 2258 Chengbei Rd., Jiading District, Shanghai, 201807, China.
  • Feng Shi
    Department of Research and Development, Shanghai United Imaging Intelligence, Co., Ltd. Shanghai, China.
  • Beibei Sun
    School of Public Health, Xinxiang Medical University, Xinxiang, Henan Province, China.
  • Yan Zhou
    Department of Computer Science, University of Texas at Dallas, Richardson, Texas 75080, United States.
  • Huilin Zhao
    Department of Radiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals