Skip to main content
SpringerLink
Log in

Identification of high-risk carotid plaque with MRI-based radiomics and machine learning

  • Magnetic Resonance
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

We sought to build a high-risk plaque MRI-based model (HRPMM) using radiomics features and machine learning for differentiating symptomatic from asymptomatic carotid plaques.

Materials and methods

One hundred sixty-two patients with carotid stenosis were randomly divided into training and test cohorts. Multi-contrast MRI including time of flight (TOF), T1- and T2-weighted imaging, and contrast-enhanced imaging was done. Radiological characteristics of the carotid plaques were recorded and calculated to build a traditional model. After extracting the radiomics features on these images, we constructed HRPMM with least absolute shrinkage and selection operator algorithm in the training cohort and evaluated its performance in the test cohort. A combined model was also built using both the traditional and radiomics features. The performance of all the models in the identification of high-risk carotid plaque was compared.

Results

Intraplaque hemorrhage and lipid-rich necrotic core were independently associated with clinical symptoms and were used to build the traditional model, which achieved an area under the curve (AUC) of 0.825 versus 0.804 in the training and test cohorts. The HRPMM and the combined model achieved an AUC of 0.988 versus 0.984 and of 0.989 versus 0.986 respectively in the two cohorts. Both the radiomics model and combined model outperformed the traditional model, whereas the combined model showed no significant difference with the HRPMM.

Conclusions

Our MRI-based radiomics model can accurately distinguish symptomatic from asymptomatic carotid plaques. It is superior to the traditional model in the identification of high-risk plaques.

Key Points

• Carotid plaque multi-contrast MRI stores other valuable information to be further exploited by radiomics analysis.

• Radiomics analysis can accurately distinguish symptomatic from asymptomatic carotid plaques.

• The radiomics model is superior to the traditional model in the identification of high-risk plaques.

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

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CER:

Contrast enhancement ratio

GLCM:

Gray-level co-occurrence matrix

GLDM:

Gray-level dependence matrix

GLRLM:

Gray-level run-length matrix

GLSZM:

Gray-level size-zone matrix

HRPMM:

High-risk plaque MRI-based model

ICC:

Intraclass coefficient

IPH:

Intraplaque hemorrhage

LASSO:

Least absolute shrinkage and selection operator

LRNC:

Lipid-rich necrotic core

MLA:

Minimal luminal area

MRI:

Magnetic resonance imaging

NDLR:

Negative diagnostic likelihood ratio

NPV:

Negative predictive value

PB:

Plaque burden

PDLR:

Positive diagnostic likelihood ratio

PPV:

Positive predictive value

RI:

Remodeling index

ROC:

Receiver operating characteristic

TOF:

Time of flight

VIBE:

Volume-interpolated breath-hold examination

References

  1. Ooi YC, Gonzalez NR (2015) Management of extracranial carotid artery disease. Cardiol Clin 33:1–35

    Article  Google Scholar 

  2. Naghavi M, Libby P, Falk E et al (2003) From vulnerable plaque to vulnerable patient: a call for new definitions and risk assessment strategies: part I. Circulation 108:1664–1672

    Article  Google Scholar 

  3. Redgrave JN, Lovett JK, Gallagher PJ, Rothwell PM (2006) Histological assessment of 526 symptomatic carotid plaques in relation to the nature and timing of ischemic symptoms: the Oxford plaque study. Circulation 113:2320–2328

    Article  CAS  Google Scholar 

  4. Zhou T, Jia S, Wang X et al (2019) Diagnostic performance of MRI for detecting intraplaque hemorrhage in the carotid arteries: a meta-analysis. Eur Radiol 29:5129–5138

    Article  Google Scholar 

  5. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577

    Article  Google Scholar 

  6. Segal E, Sirlin CB, Ooi C et al (2007) Decoding global gene expression programs in liver cancer by noninvasive imaging. Nat Biotechnol 25:675–680

    Article  CAS  Google Scholar 

  7. Coroller TP, Grossmann P, Hou Y et al (2015) CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiother Oncol 114:345–350

    Article  Google Scholar 

  8. Li W, Zhang L, Tian C et al (2019) Prognostic value of computed tomography radiomics features in patients with gastric cancer following curative resection. Eur Radiol 29:3079–3089

    Article  Google Scholar 

  9. Wan L, Zhang C, Zhao Q et al (2019) Developing a prediction model based on MRI for pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Abdom Radiol (NY) 44:2978–2987

    Article  Google Scholar 

  10. Kakkos SK, Stevens JM, Nicolaides AN et al (2007) Texture analysis of ultrasonic images of symptomatic carotid plaques can identify those plaques associated with ipsilateral embolic brain infarction. Eur J Vasc Endovasc Surg 33:422–429

    Article  CAS  Google Scholar 

  11. Acharya UR, Sree SV, Mookiah MRK et al (2013) Computed tomography carotid wall plaque characterization using a combination of discrete wavelet transform and texture features: a pilot study. Proc Inst Mech Eng H 227:643–654

    Article  CAS  Google Scholar 

  12. Shi Z, Zhu C, Degnan AJ et al (2018) Identification of high-risk plaque features in intracranial atherosclerosis: initial experience using a radiomic approach. Eur Radiol 28:3912–3921

    Article  Google Scholar 

  13. Barnett HJM, Taylor DW, Haynes RB et al (1991) Beneficial effect of carotid endarterectomy in symptomatic patients with high-grade carotid stenosis. N Engl J Med 325:445–453

    Article  CAS  Google Scholar 

  14. Moseley ME, Kucharczyk J, Mintorovitch J et al (1990) Diffusion-weighted MR imaging of acute stroke: correlation with T2-weighted and magnetic susceptibility-enhanced MR imaging in cats. AJNR Am J Neuroradiol 11:423–429

    CAS  PubMed  Google Scholar 

  15. Azizyan A, Sanossian N, Mogensen MA, Liebeskind DS (2011) Fluid-attenuated inversion recovery vascular hyperintensities: an important imaging marker for cerebrovascular disease. AJNR Am J Neuroradiol 32:1771–1775

    Article  CAS  Google Scholar 

  16. Takaya N, Yuan C, Chu B et al (2006) Association between carotid plaque characteristics and subsequent ischemic cerebrovascular events: a prospective assessment with MRI--initial results. Stroke 37:818–823

    Article  Google Scholar 

  17. Zhao X, Hippe DS, Li R et al (2017) Prevalence and characteristics of carotid artery high-risk atherosclerotic plaques in Chinese patients with cerebrovascular symptoms: a Chinese atherosclerosis risk evaluation II study. J Am Heart Assoc 6:e005831

    PubMed  PubMed Central  Google Scholar 

  18. Howard DP, van Lammeren GW, Rothwell PM et al (2015) Symptomatic carotid atherosclerotic disease: correlations between plaque composition and ipsilateral stroke risk. Stroke 46:182–189

    Article  Google Scholar 

  19. Yuan C, Kerwin WS, Ferguson MS et al (2002) Contrast-enhanced high resolution MRI for atherosclerotic carotid artery tissue characterization. J Magn Reson Imaging 15:62–67

    Article  Google Scholar 

  20. Yu JH, Kwak HS, Chung GH, Hwang SB, Park MS, Park SH (2015) Association of intraplaque hemorrhage and acute infarction in patients with basilar artery plaque. Stroke 46:2768–2772

    Article  CAS  Google Scholar 

  21. Qian Z, Li Y, Wang Y et al (2019) Differentiation of glioblastoma from solitary brain metastases using radiomic machine-learning classifiers. Cancer Lett 451:128–135

    Article  CAS  Google Scholar 

  22. Zhang L, Dong D, Li H et al (2019) Development and validation of a magnetic resonance imaging-based model for the prediction of distant metastasis before initial treatment of nasopharyngeal carcinoma: a retrospective cohort study. EBioMedicine 40:327–335

    Article  Google Scholar 

  23. Kim SM, Kim Y, Jeong K, Jeong H, Kim J (2018) Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography. Ultrasonography 37:36–42

    Article  Google Scholar 

  24. Xie H, Ma S, Wang X, Zhang X (2020) Noncontrast computer tomography-based radiomics model for predicting intracerebral hemorrhage expansion: preliminary findings and comparison with conventional radiological model. Eur Radiol 30:87–98

    Article  Google Scholar 

  25. Fluss R, Faraggi D, Reiser B (2005) Estimation of the Youden index and its associated cutoff point. Biom J 47:458–472

    Article  Google Scholar 

  26. Huang X, Zhang Y, Qian M et al (2016) Classification of carotid plaque echogenicity by combining texture features and morphologic characteristics. J Ultrasound Med 35:2253–2261

    Article  Google Scholar 

Download references

Funding

The authors state that this work has not received any funding.

Author information

Author notes

  1. Ranying Zhang and Qingwei Zhang contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, Zhongshan Hospital, Fudan University and Shanghai Institute of Medical Imaging, 180 Fenglin Road, Shanghai, 200032, China

    Ranying Zhang, Aihua Ji, Peng Lv, Jingjing Zhang & Jiang Lin

  2. Division of Gastroenterology and Hepatology, Key Laboratory of Gastroenterology and Hepatology, Ministry of Health, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai Institute of Digestive Disease, 145 Middle Shandong Road, Shanghai, China

    Qingwei Zhang

  3. MR Application Development, Siemens Shenzhen Magnetic Resonance Ltd., Gaoxin C. Ave, 2nd, Hi-Tech Industrial Park, Shenzhen, 518057, China

    Caixia Fu

Authors
  1. Ranying Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qingwei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aihua Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peng Lv
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jingjing Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Caixia Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jiang Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiang Lin.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jiang Lin.

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

Zhang Qingwei and Zhang Ranying did statistical analysis. 

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Diagnostic or prognostic study

• Performed at one institution

Additional information

Publisher’s note

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

Electronic supplementary material

LASSO algorithm was applied, 33 features were finally retained and used to build HRPMM (details in Appendix).

The ICCs for measuring the radiological and radiomics features ranged from 0.705 to 0.951 and were summarized in the Appendix.

In the 33 final features, only sphericity, i.e. a shape feature, appeared in the four sequences’ final screening results (see Appendix).

ESM 1

(DOCX 21 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, R., Zhang, Q., Ji, A. et al. Identification of high-risk carotid plaque with MRI-based radiomics and machine learning. Eur Radiol 31, 3116–3126 (2021). https://doi.org/10.1007/s00330-020-07361-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-07361-z

Keywords

Search

Navigation