You are here

  • Home
  • Online First
  • Diagnosis of intracranial aneurysms by computed tomography angiography using deep learning-based detection and segmentation

Article Text

Article menu
Download PDFPDF
Vascular neurology
Diagnosis of intracranial aneurysms by computed tomography angiography using deep learning-based detection and segmentation
  1. Wei You1,
  2. Junqiang Feng2,
  3. Jing Lu3,
  4. Ting Chen4,
  5. Xinke Liu1,
  6. Zhenzhou Wu5,
  7. Guoyang Gong5,
  8. Yutong Sui5,
  9. Yanwen Wang5,
  10. Yifan Zhang5,
  11. Wanxing Ye5,
  12. Xiheng Chen2,
  13. Jian Lv1,
  14. Dachao Wei1,
  15. Yudi Tang1,
  16. Dingwei Deng6,
  17. Siming Gui1,
  18. Jun Lin1,
  19. Peike Chen1,
  20. Ziyao Wang7,
  21. Wentao Gong7,
  22. Yang Wang2,
  23. Chengcheng Zhu8,
  24. Yue Zhang9,
  25. David A Saloner9,10,
  26. Dimitrios Mitsouras9,10,
  27. Sheng Guan7,
  28. Youxiang Li1,11,
  29. Yuhua Jiang1,11,
  30. Yan Wang9,10
  1. 1Department of Neurosurgery, Beijing Tiantan Hospital and Beijing Neurosurgical Institute, Capital Medical University, Beijing, China
  2. 2Department of Neurosurgery, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
  3. 3Department of Radiology, Third Medical Center of Chinese PLA General Hospital, Beijing, China
  4. 4School of Biomedical Engineering, Capital Medical University, Beijing, China
  5. 5Artificial Intelligence Research Center, China National Clinical Research Center for Neurological Diseases, Beijing, China
  6. 6Department of Intervention, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
  7. 7Department of Interventional Neuroradiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
  8. 8Department of Radiology, University of Washington, Seattle, Washington, USA
  9. 9San Francisco Veterans Affairs Medical Center, San Francisco, California, USA
  10. 10Department of Radiology and Biomedical Imaging, University California, San Francisco, San Francisco, California, USA
  11. 11Department of Neurointerventional Engineering and Technology (NO: BG0287), Beijing Engineering Research Center, Beijing, China
  1. Correspondence to Dr Yuhua Jiang, Department of Neurosurgery, Beijing Tiantan Hospital and Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; jyhttins{at}163.com; Dr Youxiang Li, Department of Neurosurgery, Beijing Tiantan Hospital and Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; liyouxiang{at}mail.ccmu.edu.cn

Abstract

Background Detecting and segmenting intracranial aneurysms (IAs) from angiographic images is a laborious task.

Objective To evaluates a novel deep-learning algorithm, named vessel attention (VA)-Unet, for the efficient detection and segmentation of IAs.

Methods This retrospective study was conducted using head CT angiography (CTA) examinations depicting IAs from two hospitals in China between 2010 and 2021. Training included cases with subarachnoid hemorrhage (SAH) and arterial stenosis, common accompanying vascular abnormalities. Testing was performed in cohorts with reference-standard digital subtraction angiography (cohort 1), with SAH (cohort 2), acquired outside the time interval of training data (cohort 3), and an external dataset (cohort 4). The algorithm’s performance was evaluated using sensitivity, recall, false positives per case (FPs/case), and Dice coefficient, with manual segmentation as the reference standard.

Results The study included 3190 CTA scans with 4124 IAs. Sensitivity, recall, and FPs/case for detection of IAs were, respectively, 98.58%, 96.17%, and 2.08 in cohort 1; 95.00%, 88.8%, and 3.62 in cohort 2; 96.00%, 93.77%, and 2.60 in cohort 3; and, 96.17%, 94.05%, and 3.60 in external cohort 4. The segmentation accuracy, as measured by the Dice coefficient, was 0.78, 0.71, 0.71, and 0.66 for cohorts 1–4, respectively. VA-Unet detection recall and FPs/case and segmentation accuracy were affected by several clinical factors, including aneurysm size, bifurcation aneurysms, and the presence of arterial stenosis and SAH.

Conclusions VA-Unet accurately detected and segmented IAs in head CTA comparably to expert interpretation. The proposed algorithm has significant potential to assist radiologists in efficiently detecting and segmenting IAs from CTA images.

  • CT angiography
  • aneurysm
  • artery

Data availability statement

Data are available upon reasonable request.

https://doi.org/10.1136/jnis-2023-021022

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available upon reasonable request.

    View Full Text

    Footnotes

    • WY and JF contributed equally.

    • YL and YJ contributed equally.

    • Contributors Youxiang Li, Yuhua Jiang, and Sheng Guan initiated the project and designed this study. Wei You, Junqiang Feng, Jing Lu, Sheng Guan, Youxiang Li, and Xinke Liu developed protocols. Zhenzhou Wu, Ting Chen, Guoyang Gong, Yanwen Wang, Yifan Zhang, Wanxing Ye, and Yutong Sui developed the algorithm and contributed to the software engineering. Wei You, Junqiang Feng, Jian Lv, Xiheng Chen, Dachao Wei, Yudi Tang, Dingwei Deng, Siming Gui, Jun Lin, Peike Chen, Ziyao Wang, and Wentao Gong contributed to data acquisition, defined clinical labels, image interpretation. Wei You, Junqiang Feng, and Yan Wang performed the data analysis. Wei You and Junqiang Feng wrote the paper. Wei You, Yang Wang, Yue Zhang, Chengcheng Zhu, David Saloner, Dimitrios Mitsouras, Youxiang Li, Yuhua Jiang, and Sheng Guan performed the revision of the current literature. Youxiang Li serves as the guarantor, taking full responsibility for the overall content, conduct of the study, and the finished work. He had access to the data and played a pivotal role in controlling the decision to publish. All authors contributed to the manuscript and approved the final version.

    • Funding This work was supported by Natural Science Foundation of Beijing Municipality (Beijing Natural Science Foundation) (No. M22007), National Natural Science Foundation of China (NSFC) (No. 8217050951).

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.