Article Text

Download PDFPDF
Original research
Two-stage convolutional neural network for segmentation and detection of carotid web on CT angiography
  1. Hulin Kuang1,
  2. Xianzhen Tan1,
  3. Fouzi Bala2,3,
  4. Jialiang Huang1,
  5. Jianhai Zhang2,
  6. Ibrahim Alhabli2,
  7. Faysal Benali2,
  8. Nishita Singh2,4,
  9. Aravind Ganesh2,
  10. Shelagh B Coutts2,
  11. Mohammed A Almekhlafi2,
  12. Mayank Goyal2,5,
  13. Michael D Hill2,5,
  14. Wu Qiu6,
  15. Bijoy K Menon2
    1. 1Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
    2. 2Department of Clinical Neurosciences, University of Calgary Cumming School of Medicine, Calgary, Alberta, Canada
    3. 3Diagnostic and Interventional Neuroradiology Department, University Hospital of Tours, Avenue de la République, France
    4. 4Neurology Division, Department of Internal Medicine, University of Manitoba Max Rady College of Medicine, Winnipeg, Manitoba, Canada
    5. 5Department of Diagnostic Imaging, Foothills Medical Center, University of Calgary, Calgary, Alberta, Canada
    6. 6Deaprtment of Biomedical Engineering, School of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China
    1. Correspondence to Prof Wu Qiu, Department of Biomedical Engineering, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China;{at}


    Background Carotid web (CaW) is a risk factor for ischemic stroke, mainly in young patients with stroke of undetermined etiology. Its detection is challenging, especially among non-experienced physicians.

    Methods We included patients with CaW from six international trials and registries of patients with acute ischemic stroke. Identification and manual segmentations of CaW were performed by three trained radiologists. We designed a two-stage segmentation strategy based on a convolutional neural network (CNN). At the first stage, the two carotid arteries were segmented using a U-shaped CNN. At the second stage, the segmentation of the CaW was first confined to the vicinity of the carotid arteries. Then, the carotid bifurcation region was localized by the proposed carotid bifurcation localization algorithm followed by another U-shaped CNN. A volume threshold based on the derived CaW manual segmentation statistics was then used to determine whether or not CaW was present.

    Results We included 58 patients (median (IQR) age 59 (50–75) years, 60% women). The Dice similarity coefficient and 95th percentile Hausdorff distance between manually segmented CaW and the algorithm segmented CaW were 63.20±19.03% and 1.19±0.9 mm, respectively. Using a volume threshold of 5 mm3, binary classification detection metrics for CaW on a single artery were as follows: accuracy: 92.2% (95% CI 87.93% to 96.55%), precision: 94.83% (95% CI 88.68% to 100.00%), sensitivity: 90.16% (95% CI 82.16% to 96.97%), specificity: 94.55% (95% CI 88.0% to 100.0%), F1 measure: 0.9244 (95% CI 0.8679 to 0.9692), area under the curve: 0.9235 (95%CI 0.8726 to 0.9688).

    Conclusions The proposed two-stage method enables reliable segmentation and detection of CaW from head and neck CT angiography.

    • Artery
    • CT Angiography
    • Embolic
    • Stroke
    • Vascular Malformation

    Data availability statement

    Data are available upon reasonable request.

    Statistics from

    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


    • X @FouziBala, @draravindganesh, @AlmekhlafiMa, @mihill68

    • HK, XT and FBa contributed equally.

    • Contributors HK, XT, and FBa contribute to this work equally. HK, XT, FBa, JH, JZ, IA, FBe, NS, AG, MDH, MG, SBC, MAA, WQ, and BKM had full access to all data in the study and take responsibility for the data integrity and accuracy of the analysis. HK, XT, FBa, and WQ participated in the concept and design. HK, XT, FBa, JH, JZ, IA, FBe, NS, AG, MDH, MG, SBC, MAA, WQ, and BKM participated in the acquisition, analysis, or interpretation of data, as well as review of testing data. HK, XT, FBa, BKM, and WQ were involved in drafting and critical revision of the article for important intellectual content. HK, XT, and FBa performed the statistical analysis. FBa obtained the funding. HK, XT, FBa, and WQ participated in administrative, technical, or material support. WQ and BKM acted as supervisors. WQ and BKM are guarantors of this work.

    • Funding FBa received a research grant from the Society of Vascular and Interventional Neurology (SVIN).FBa received a research grant from the Society of Vascular and Interventional Neurology (SVIN).

    • 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.