Skip to main content
SpringerLink
Log in

Automated unruptured cerebral aneurysms detection in TOF MR angiography images using dual-channel SE-3D UNet: a multi-center research

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

Time of flight magnetic resonance angiography (TOF-MRA) is the primary non-invasive screening method for cerebral aneurysms. We aimed to develop a computer-aided aneurysm detection method to improve the diagnostic efficiency and accuracy, especially decrease the false positive rate.

Methods

This is a retrospective multicenter study. The dataset contained 1160 TOF-MRA examinations composed of unruptured aneurysms (n = 1096) and normal controls (n = 166) from six hospitals. A total of 1037 examinations acquired from 2013 to 2019 were used as training set; 123 examinations acquired from 2020 to 2021 were used as external test set. We proposed an equalized augmentation strategy based on aneurysm location and constructed a detection model based on dual channel SE-3D UNet. The model was trained with a 5-fold cross-validation in the training set, then tested on the external test set.

Results

The proposed method achieved 82.46% sensitivity on patient-level, 73.85% sensitivity on lesion-level, and 0.88 false positives per case in the external test set. The performance did not show significant differences in subgroups according to the aneurysm site (except ACA), aneurysm size (except smaller than 3 mm), or MRI scanners. The performance preceded the basic SE-3D UNet by increasing 15.79% patient-level sensitivity and decreasing 4.19 FPs/case.

Conclusions

The proposed automated aneurysm detection method achieved acceptable sensitivity while controlling fairly low false positives per case. It might provide a useful auxiliary tool of cerebral aneurysms MRA screening.

Key Points

• The need for automated cerebral aneurysms detecting is growing.

• The strategy of equalized augmentation based on aneurysm location and dual-channel input could improve the model performance.

• The retrospective multi-center study showed that the proposed automated cerebral aneurysms detection using dual-channel SE-3D UNet could achieve acceptable sensitivity while controlling a low false positive rate.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Abbreviations

ACA:

Anterior cerebral artery

AchA:

Anterior choroidal artery

Acom:

Anterior communicating artery

BA:

Basilar artery

DSA:

Digital subtraction angiography

FP:

False positive

FROC:

Free-response receiver operating characteristics

GPU:

Graphic processing unit

ICA:

Internal carotid artery

MCA:

Middle cerebral artery

PCA:

Posterior cerebral artery

Pcom:

Posterior communicating artery

TOF-MRA:

Time-of-flight magnetic resonance angiography

VA:

Vertebral artery

References

  1. Vlak MHM, Algra A, Brandenburg R, Rinkel GJE (2011) Prevalence of unruptured intracranial aneurysms, with emphasis on sex, age, comorbidity, country, and time period: a systematic review and meta-analysis. Lancet Neurol 10:626–636

    Article  PubMed  Google Scholar 

  2. Wermer MJH, van der Schaaf IC, Algra A, Rinkel GJE (2007) Risk of rupture of unruptured intracranial aneurysms in relation to patient and aneurysm characteristics - an updated meta-analysis. Stroke 38:1404–1410

    Article  PubMed  Google Scholar 

  3. Sailer AMH, Wagemans B, Nelemans PJ, de Graaf R, van Zwam WH (2014) Diagnosing intracranial aneurysms with MR angiography systematic review and meta-analysis. Stroke 45:119–126

    Article  PubMed  Google Scholar 

  4. Philipp LR, McCracken DJ, McCracken CE et al (2017) Comparison between CTA and digital subtraction angiography in the diagnosis of ruptured aneurysms. Neurosurgery 80:769–777

    Article  PubMed  Google Scholar 

  5. Yang ZL, Ni QQ, Schoepf UJ et al (2017) Small intracranial aneurysms: diagnostic accuracy of CT angiography. Radiology 285:941–952

    Article  PubMed  Google Scholar 

  6. Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. Springer International Publishing, Cham, pp 424–432

    Google Scholar 

  7. Kamnitsas K, Ledig C, Newcombe VFJ et al (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78

    Article  PubMed  Google Scholar 

  8. He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, pp 770-778

  9. Faron A, Sichtermann T, Teichert N et al (2020) Performance of a deep-learning neural network to detect intracranial aneurysms from 3D TOF-MRA compared to human readers. Clin Neuroradiol 30:591–598

    Article  PubMed  Google Scholar 

  10. Shimada Y, Tanimoto T, Nishimori M et al (2020) Incidental cerebral aneurysms detected by a computer-assisted detection system based on artificial intelligence a case series. Medicine (Baltimore) 99:4

  11. Stember JN, Chang P, Stember DM et al (2019) Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography. J Digit Imaging 32:808–815

    Article  PubMed  Google Scholar 

  12. Nakao T, Hanaoka S, Nomura Y et al (2018) Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging 47:948–953

    Article  PubMed  Google Scholar 

  13. Ueda D, Yamamoto A, Nishimori M et al (2019) Deep learning for MR angiography: automated detection of cerebral aneurysms. Radiology 290:187–194

    Article  PubMed  Google Scholar 

  14. Chen G, Wei X, Lei H et al (2020) Automated computer-assisted detection system for cerebral aneurysms in time-of-flight magnetic resonance angiography using fully convolutional network. Biomed Eng Online 19:38

    Article  PubMed  PubMed Central  Google Scholar 

  15. Wen L, Wang X, Wu Z, Zhou M, Jin JS (2015) A novel statistical cerebrovascular segmentation algorithm with particle swarm optimization. Neurocomputing 148:569–577

    Article  Google Scholar 

  16. Gonzalez RC (2009) Digital Image Processing. Pearson education India

  17. Isensee F, Kickingereder P, Wick W, Bendszus M, Maier-Hein KH (2018) Brain tumor segmentation and radiomics survival prediction: contribution to the BRATS 2017 challenge. Springer International Publishing, Cham, pp 287–297

    Google Scholar 

  18. Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-Excitation Networks. IEEE Trans Pattern Anal Mach Intell 42:2011–2023

    Article  PubMed  Google Scholar 

  19. Sichtermann T, Faron A, Sijben R, Teichert N, Freiherr J, Wiesmann M (2019) Deep learning–based detection of intracranial aneurysms in 3D TOF-MRA. AJNR Am J Neuroradiol 40:25–32

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Funding

This work was supported by National Natural Science Foundation of China [81971685], Jiangsu Natural Science Foundation [BK20180221], Science and Technology Commission of Shanghai Municipality [19411951200], Suzhou Science and Technology Development Project [SS202054, SS202072], Suzhou Health Science & Technology Project [GWZX201904], Youth Innovation Promotion Association CAS [2021324], and Shandong Natural Science Foundation [ZR2022QF093].

Author information

Author notes

  1. Geng Chen and Bao Yifang contributed equally to this work.

Authors and Affiliations

  1. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China

    Geng Chen, Zhou Zhiyong, Dai Bin & Dai Yakang

  2. Jinan Guoke Medical Technology Development Co. Ltd., Jinan, China

    Geng Chen & Dai Yakang

  3. Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China

    Bao Yifang, Wang Dongdong, Di Ruoyu, Piao Sirong, Geng Daoying & Li Yuxin

  4. Institute of Functional and Molecular Medical Imaging, Fudan University, Shanghai, China

    Bao Yifang, Wang Dongdong, Geng Daoying & Li Yuxin

  5. School of Electronic & Information Engineering, Suzhou University of Science and Technology, Suzhou, China

    Zhang Jiajun

  6. School of Biomedical Engineering, Xuzhou Medical University, Xuzhou, China

    Chen Meng

Authors
  1. Geng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bao Yifang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhang Jiajun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wang Dongdong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhou Zhiyong
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Di Ruoyu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Dai Bin
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Piao Sirong
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Geng Daoying
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Chen Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Dai Yakang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Li Yuxin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Dai Yakang or Li Yuxin.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Yuxin Li.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

The informed consents were waived since all of TOF-MRA images were acquired from routine clinical work.

Ethical approval

The ethics board of our institution comprehensively reviewed and approved the protocol of this retrospective study.

Methodology

• retrospective

• diagnostic or prognostic study

• multicenter study

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

ESM 1

(DOCX 28 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, G., Yifang, B., Jiajun, Z. et al. Automated unruptured cerebral aneurysms detection in TOF MR angiography images using dual-channel SE-3D UNet: a multi-center research. Eur Radiol 33, 3532–3543 (2023). https://doi.org/10.1007/s00330-022-09385-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-09385-z

Keywords

Search

Navigation