You are here

  • Home
  • Online First
  • CTA-based deep-learning integrated model for identifying irregular shape and aneurysm size of unruptured intracranial aneurysms

Article Text

Article menu
Download PDFPDF
Neuroimaging
Original research
CTA-based deep-learning integrated model for identifying irregular shape and aneurysm size of unruptured intracranial aneurysms
  1. Ke Tian1,
  2. Zhenyao Chang2,3,
  3. Yi Yang2,
  4. Peng Liu2,3,
  5. Mahmud Mossa-Basha4,
  6. Michael R Levitt5,
  7. Dihua Zhai1,
  8. Danyang Liu1,
  9. Hao Li1,
  10. Yang Liu2,
  11. Jinhao Zhang2,
  12. Cijian Cao2,3,
  13. Chengcheng Zhu4,
  14. Peng Jiang2,3,
  15. Qingyuan Liu2,
  16. Hongwei He2,3,
  17. Yuanqing Xia1
  1. 1Beijing Institute of Technology School of Automation, Beijing, Beijing, China
  2. 2Department of Neurosurgery, Beijing Tiantan Hospital Affiliated to Capital Medical University, Beijing, China
  3. 3Beijing Neurosurgical Institute, Beijing, China
  4. 4Department of Radiology, University of Washington, Seattle, Washington, USA
  5. 5Department of Neurological Surgery, University of Washington School of Medicine, Seattle, Washington, USA
  1. Correspondence to Dr Hongwei He; ttyyhhw{at}126.com

Abstract

Background Artificial intelligence can help to identify irregular shapes and sizes, crucial for managing unruptured intracranial aneurysms (UIAs). However, existing artificial intelligence tools lack reliable classification of UIA shape irregularity and validation against gold-standard three-dimensional rotational angiography (3DRA). This study aimed to develop and validate a deep-learning model using computed tomography angiography (CTA) for classifying irregular shapes and measuring UIA size.

Methods CTA and 3DRA of UIA patients from a referral hospital were included as a derivation set, with images from multiple medical centers as an external test set. Senior investigators manually measured irregular shape and aneurysm size on 3DRA as the ground truth. Convolutional neural network (CNN) models were employed to develop the CTA-based model for irregular shape classification and size measurement. Model performance for UIA size and irregular shape classification was evaluated by intraclass correlation coefficient (ICC) and area under the curve (AUC), respectively. Junior clinicians’ performance in irregular shape classification was compared before and after using the model.

Results The derivation set included CTA images from 307 patients with 365 UIAs. The test set included 305 patients with 350 UIAs. The AUC for irregular shape classification of this model in the test set was 0.87, and the ICC of aneurysm size measurement was 0.92, compared with 3DRA. With the model’s help, junior clinicians’ performance for irregular shape classification was significantly improved (AUC 0.86 before vs 0.97 after, P<0.001).

Conclusion This study provided a deep-learning model based on CTA for irregular shape classification and size measurement of UIAs with high accuracy and external validity. The model can be used to improve reader performance.

  • CT Angiography
  • Aneurysm
  • Technology

Data availability statement

Data are available upon reasonable request.

https://doi.org/10.1136/jnis-2024-022784

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

    • X @DrMichaelLevitt

    • KT and ZC contributed equally.

    • Contributors All authors met the requirements for the authorship. HH YX and QL first initiated this project and make the study design. KT, ZC and YY developed the protocol. HH, PL, PJ and QL was responsible for the development of gold standard for the model constructing. ZC, YL, JZ and CC contributed to data acquisition, defined clinical labels, image annotation and interpretation. KT, ZC and YY performed the data analysis. KT, ZC and QL wrote this paper. MM-B, ML and CZ performed the revision of the current literature. HH 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 prominent role in controlling the decision to publish.

    • Funding Thise study was supported by the Wuxi Taihu Lake Talent Plan, Team in Medical and Health Profession (Grant No. TH202109) and the Beijing Municipal Natural Science Foundation (Grant 4242048 and L242045).

    • 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.