Skip to main content

Advertisement

SpringerLink
Log in

Radiomics from magnetic resonance imaging may be used to predict the progression of white matter hyperintensities and identify associated risk factors

  • Neuro
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

The progression of white matter hyperintensities (WMH) varies considerably in adults. In this study, we aimed to predict the progression and related risk factors of WMH based on the radiomics of whole-brain white matter (WBWM).

Methods

A retrospective analysis was conducted on 141 patients with WMH who underwent two consecutive brain magnetic resonance (MR) imaging sessions from March 2014 to May 2018. The WBWM was segmented to extract and score the radiomics features at baseline. Follow-up images were evaluated using the modified Fazekas scale, with progression indicated by scores ≥ 1. Patients were divided into progressive (n = 65) and non-progressive (n = 76) groups. The progressive group was subdivided into any WMH (AWMH), periventricular WMH (PWMH), and deep WMH (DWMH). Independent risk factors were identified using logistic regression.

Results

The area under the curve (AUC) values for the radiomics signatures of the training sets were 0.758, 0.749, and 0.775 for AWMH, PWMH, and DWMH, respectively. The AUC values of the validation set were 0.714, 0.697, and 0.717, respectively. Age and hyperlipidemia were independent predictors of progression for AWMH. Age and body mass index (BMI) were independent predictors of progression for DWMH, while hyperlipidemia was an independent predictor of progression for PWMH. After combining clinical factors and radiomics signatures, the AUC values were 0.848, 0.863, and 0.861, respectively, for the training set, and 0.824, 0.818, and 0.833, respectively, for the validation set.

Conclusions

MRI-based radiomics of WBWM, along with specific risk factors, may allow physicians to predict the progression of WMH.

Key Points

• Radiomics features detected by magnetic resonance imaging may be used to predict the progression of white matter hyperintensities.

• Radiomics may be used to identify risk factors associated with the progression of white matter hyperintensities.

• Radiomics may serve as non-invasive biomarkers to monitor white matter status.

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

AUC:

Area under the curve

AWMH:

Progression of WMH in any (periventricular and/or deep) region

BMI:

Body mass index

DTI:

Diffusion tensor imaging

DWMH:

Deep white matter hyperintensities

FLAIR:

Fluid attenuated inversion recovery

GLCM:

Gray-level co-occurrence matrix

ICC:

Intraclass correlation coefficient

LASSO:

The least absolute shrinkage and selection operator

LDL:

Low-density lipoprotein

MRI:

Magnetic resonance imaging

NAWM:

Normal-appearing white matter

PWMH:

Periventricular white matter hyperintensities

RLM:

Run-length matrix

ROC:

Receiver operating characteristic

ROI:

Region of interest

WBWM:

Whole-brain white matter

WMH:

White matter hyperintensities

References

  1. Wardlaw JM, Smith C, Dichgans M (2013) Mechanisms of sporadic cerebral small vessel disease: insights from neuroimaging. Lancet Neurol 12:483–497

    Article  PubMed  Google Scholar 

  2. Maillard P, Fletcher E, Harvey D et al (2011) White matter hyperintensity penumbra. Stroke 42:1917–1922

    Article  PubMed  PubMed Central  Google Scholar 

  3. Valdes Hernandez Mdel C, Armitage PA, Thrippleton MJ et al (2015) Rationale, design and methodology of the image analysis protocol for studies of patients with cerebral small vessel disease and mild stroke. Brain Behav 5:e00415

    PubMed  Google Scholar 

  4. Taylor ANW, Kambeitz-Ilankovic L, Gesierich B et al (2017) Tract-specific white matter hyperintensities disrupt neural network function in Alzheimer’s disease. Alzheimers Dement 13:225–235

    Article  PubMed  PubMed Central  Google Scholar 

  5. Valdes Hernandez MDC, Gonzalez-Castro V, Chappell FM et al (2017) Application of texture analysis to study small vessel disease and blood-brain barrier integrity. Front Neurol 8:327

    Article  PubMed  PubMed Central  Google Scholar 

  6. Lee WJ, Jung KH, Ryu YJ et al (2017) Progression of cerebral white matter hyperintensities and the associated sonographic index. Radiology 284:824–833

    Article  PubMed  Google Scholar 

  7. Holmegaard L, Jensen C, Redfors P, Blomstrand C, Jern C, Jood K (2018) Long-term progression of white matter hyperintensities in ischemic stroke. Acta Neurol Scand 138:548–556

    Article  CAS  PubMed  Google Scholar 

  8. Yip SS, Aerts HJ (2016) Applications and limitations of radiomics. Phys Med Biol 61:R150–R166

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Liang C, Huang Y, He L et al (2016) The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I-II and stage III-IV colorectal cancer. Oncotarget 7:31401–31412

    Article  PubMed  PubMed Central  Google Scholar 

  10. Huang YQ, Liang CH, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164

    Article  PubMed  Google Scholar 

  11. Abbasian Ardakani A, Gharbali A, Saniei Y, Mosarrezaii A, Nazarbaghi S (2015) Application of texture analysis in diagnosis of multiple sclerosis by magnetic resonance imaging. Glob J Health Sci 7:68–78

  12. Holli KK, Harrison L, Dastidar P et al (2010) Texture analysis of MR images of patients with mild traumatic brain injury. BMC Med Imaging 10:8

    Article  PubMed  PubMed Central  Google Scholar 

  13. Wardlaw JM, Valdes Hernandez MC, Munoz-Maniega S (2015) What are white matter hyperintensities made of? Relevance to vascular cognitive impairment. J Am Heart Assoc 4:001140

    Article  PubMed  Google Scholar 

  14. Promjunyakul N, Lahna D, Kaye JA et al (2015) Characterizing the white matter hyperintensity penumbra with cerebral blood flow measures. Neuroimage Clin 8:224–229

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Shao Y, Chen Z, Ming S et al (2018) Predicting the development of normal-appearing white matter with radiomics in the aging brain: a longitudinal clinical study. Front Aging Neurosci 10:393

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Prins ND, van Straaten EC, van Dijk EJ et al (2004) Measuring progression of cerebral white matter lesions on MRI: visual rating and volumetrics. Neurology 62:1533–1539

    Article  CAS  PubMed  Google Scholar 

  17. Kim KW, MacFall JR, Payne ME (2008) Classification of white matter lesions on magnetic resonance imaging in elderly persons. Biol Psychiatry 64:273–280

    Article  PubMed  PubMed Central  Google Scholar 

  18. ten Dam VH, van den Heuvel DM, de Craen AJ et al (2007) Decline in total cerebral blood flow is linked with increase in periventricular but not deep white matter hyperintensities. Radiology 243:198–203

    Article  PubMed  Google Scholar 

  19. van den Heuvel DM, ten Dam VH, de Craen AJ et al (2006) Increase in periventricular white matter hyperintensities parallels decline in mental processing speed in a non-demented elderly population. J Neurol Neurosurg Psychiatry 77:149–153

    Article  PubMed  PubMed Central  Google Scholar 

  20. Maillard P, Carmichael O, Fletcher E, Reed B, Mungas D, DeCarli C (2012) Coevolution of white matter hyperintensities and cognition in the elderly. Neurology 79:442–448

    Article  PubMed  PubMed Central  Google Scholar 

  21. Park BY, Lee MJ, Lee SH et al (2018) DEWS (DEep White matter hyperintensity Segmentation framework): a fully automated pipeline for detecting small deep white matter hyperintensities in migraineurs. Neuroimage Clin 18:638–647

    Article  PubMed  PubMed Central  Google Scholar 

  22. Fazekas F, Kleinert R, Offenbacher H et al (1993) Pathologic correlates of incidental MRI white matter signal hyperintensities. Neurology 43:1683–1689

    Article  CAS  PubMed  Google Scholar 

  23. Schmidt R, Schmidt H, Haybaeck J et al (2011) Heterogeneity in age-related white matter changes. Acta Neuropathol 122:171–185

    Article  PubMed  Google Scholar 

  24. Bernbaum M, Menon BK, Fick G et al (2015) Reduced blood flow in normal white matter predicts development of leukoaraiosis. J Cereb Blood Flow Metab 35:1610–1615

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  25. Nasel C, Boubela R, Kalcher K, Moser E (2017) Normalised time-to-peak-distribution curves correlate with cerebral white matter hyperintensities - could this improve early diagnosis? J Cereb Blood Flow Metab 37:444–455

    Article  Google Scholar 

  26. Madden DJ, Spaniol J, Whiting WL et al (2007) Adult age differences in the functional neuroanatomy of visual attention: a combined fMRI and DTI study. Neurobiol Aging 28:459–476

    Article  PubMed  Google Scholar 

  27. Maillard P, Fletcher E, Lockhart SN et al (2014) White matter hyperintensities and their penumbra lie along a continuum of injury in the aging brain. Stroke 45:1721–1726

    Article  PubMed  PubMed Central  Google Scholar 

  28. Yoon CW, Choi Y, Jeon S et al (2017) Is antiplatelet treatment effective at attenuating the progression of white matter hyperintensities? PLoS One 12:e0176300

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  29. Munoz Maniega S, Chappell FM, Valdes Hernandez MC et al (2017) Integrity of normal-appearing white matter: influence of age, visible lesion burden and hypertension in patients with small-vessel disease. J Cereb Blood Flow Metab 37:644–656

    Article  PubMed  Google Scholar 

  30. Grueter BE, Schulz UG (2012) Age-related cerebral white matter disease (leukoaraiosis): a review. Postgrad Med J 88:79–87

    Article  PubMed  Google Scholar 

  31. Moody DM, Thore CR, Anstrom JA, Challa VR, Langefeld CD, Brown WR (2004) Quantification of afferent vessels shows reduced brain vascular density in subjects with leukoaraiosis. Radiology 233:883–890

    Article  PubMed  Google Scholar 

  32. Stokes KY, Cooper D, Tailor A, Granger DN (2002) Hypercholesterolemia promotes inflammation and microvascular dysfunction: role of nitric oxide and superoxide. Free Radic Biol Med 33:1026–1036

    Article  CAS  PubMed  Google Scholar 

  33. VanTeeffelen JW, Constantinescu AA, Vink H, Spaan JA (2005) Hypercholesterolemia impairs reactive hyperemic vasodilation of 2A but not 3A arterioles in mouse cremaster muscle. Am J Physiol Heart Circ Physiol 289:H447–H454

    Article  CAS  PubMed  Google Scholar 

  34. Cho YI, Cho DJ, Rosenson RS (2014) Endothelial shear stress and blood viscosity in peripheral arterial disease. Curr Atheroscler Rep 16:404

    Article  PubMed  Google Scholar 

  35. Ryu WS, Woo SH, Schellingerhout D et al (2014) Grading and interpretation of white matter hyperintensities using statistical maps. Stroke 45:3567–3575

    Article  PubMed  Google Scholar 

  36. Griffanti L, Jenkinson M, Suri S et al (2018) Classification and characterization of periventricular and deep white matter hyperintensities on MRI: a study in older adults. Neuroimage 170:174–181

    Article  PubMed  Google Scholar 

  37. van Overbeek EC, Staals J, Knottnerus IL, ten Cate H, van Oostenbrugge RJ et al (2016) Plasma tPA-activity and progression of cerebral white matter hyperintensities in lacunar stroke patients. PLoS One 11:e0150740

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  38. Lee WJ, Jung KH, Ryu YJ et al (2017) Cystatin C, a potential marker for cerebral microvascular compliance, is associated with white-matter hyperintensities progression. PLoS One 12:e0184999

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  39. Harrison LC, Raunio M, Holli KK et al (2010) MRI texture analysis in multiple sclerosis: toward a clinical analysis protocol. Acad Radiol 17:696–707

    Article  PubMed  Google Scholar 

  40. Tozer DJ, Zeestraten E, Lawrence AJ, Barrick TR, Markus HS (2018) Texture analysis of T1-weighted and fluid-attenuated inversion recovery images detects abnormalities that correlate with cognitive decline in small vessel disease. Stroke 49:1656–1661

    Article  PubMed  PubMed Central  Google Scholar 

  41. Loizou CP, Pattichis CS, Seimenis I et al (2009) Quantitative analysis of brain white matter lesions in multiple sclerosis subjects. International Conference on Information Technology & Applications in Biomedicine; 1–4

  42. Li Z, Mao Y, Huang W et al (2017) Texture-based classification of different single liver lesion based on SPAIR T2W MRI images. BMC Med Imaging 17:42

    Article  PubMed  PubMed Central  Google Scholar 

  43. Yu O, Steibel J, Mauss Y et al (2004) Remyelination assessment by MRI texture analysis in a cuprizone mouse model. Magn Reson Imaging 22:1139–1144

    Article  PubMed  Google Scholar 

  44. Gouw AA, van der Flier WM, van Straaten EC et al (2008) Reliability and sensitivity of visual scales versus volumetry for evaluating white matter hyperintensity progression. Cerebrovasc Dis 25:247–253

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgments

We are grateful to Ms. Peipei Pang (GE Healthcare, Shanghai, China) for her technical support.

Funding

Fund of Zhejiang Traditional Chinese Medicine Science Research Projection in China (2019ZA004) and Fund of Health Commission of Zhejiang Province in China (2019KY302).

Author information

Authors and Affiliations

  1. Department of Radiology, Zhejiang Provincial People’s Hospital, People’s Hospital of Hangzhou Medical College, Hangzhou, China

    Zhenyu Shu, Yuyun Xu, Yuan Shao & Xiangyang Gong

  2. GE Healthcare (China), Shanghai, China

    Peipei Pang

  3. Institute of Artificial Intelligence and Remote Imaging, Hangzhou Medical College, Hangzhou, China

    Xiangyang Gong

Authors
  1. Zhenyu Shu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuyun Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuan Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peipei Pang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiangyang Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yuyun Xu or Xiangyang Gong.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Zhenyu Shu.

Conflict of interest

One of the authors of this manuscript (Peipei Pang) is an employee of GE Healthcare China. The remaining authors declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

Some study subjects or cohorts have been previously reported in Shao Y, Chen Z, Ming S, et al Predicting the Development of Normal-Appearing White Matter With Radiomics in the Aging Brain: A Longitudinal Clinical Study. Front Aging Neurosci 2018;10:393.

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

ESM 1

(DOC 1621 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shu, Z., Xu, Y., Shao, Y. et al. Radiomics from magnetic resonance imaging may be used to predict the progression of white matter hyperintensities and identify associated risk factors. Eur Radiol 30, 3046–3058 (2020). https://doi.org/10.1007/s00330-020-06676-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-06676-1

Keywords

Search

Navigation