Ischemic stroke enhancement using a variational model and the expectation maximization method

  • Allan Felipe Fattori Alves
  • Rachid Jennane
  • José Ricardo Arruda de Miranda
  • Carlos Clayton Macedo de Freitas
  • Nitamar Abdala
  • Diana Rodrigues de Pina
Computed Tomography
  • 16 Downloads

Abstract

Objectives

In order to enable less experienced physicians to reliably detect early signs of stroke, A novel approach was proposed to enhance the visual perception of ischemic stroke in non-enhanced CT.

Methods

A set of 39 retrospective CT scans were used, divided into 23 cases of acute ischemic stroke and 16 normal patients. Stroke cases were obtained within 4.5 h of symptom onset and with a mean NIHSS of 12.9±7.4. After selection of adjunct slices from the CT exam, image averaging was performed to reduce the noise and redundant information. This was followed by a variational decomposition model to keep the relevant component of the image. The expectation maximization method was applied to generate enhanced images.

Results

We determined a test to evaluate the performance of observers in a clinical environment with and without the aid of enhanced images. The overall sensitivity of the observer’s analysis was 64.5 % and increased to 89.6 % and specificity was 83.3 % and increased to 91.7 %.

Conclusion

These results show the importance of a computational tool to assist neuroradiology decisions, especially in critical situations such as the diagnosis of ischemic stroke.

Key Points

• Diagnosing patients with stroke requires high efficiency to avoid irreversible cerebral damage.

• A computational algorithm was proposed to enhance the visual perception of stroke.

• Observers’ performance was increased with the aid of enhanced images.

Keywords

Stroke Brain Algorithms Tomography Early diagnosis 

Abbreviations

ASPECTS

Alberta Stroke Program Early CT Score

CPU

Central Processing Unit

CT

Computed tomography

DICOM

Digital Imaging and Communications in Medicine

E1

Evaluation 1

E2

Evaluation 2

FN

False negative

FP

False positive

HU

Hounsfield units

MRI

Magnetic resonance image

NECT

Non-enhanced computed tomography

O1-6

Observer 1-6

TN

True Negative

TP

True Positive

VM

Variational Model

Notes

Acknowledgements

The authors wish to thank all clinical personnel of the Botucatu Medical School Radiodiagnostic facility. We also thank the Laboratories I3MTO from University of Orleans and LAFAR from São Paulo State University.

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is José Ricardo de Arruda Miranda from São Paulo State University, Brazil.

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

Written informed consent was not required for this study because all CT scans used were retrospective and no confidential patient information was used throughout this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Supplementary material

330_2018_5378_MOESM1_ESM.docx (39 kb)
ESM 1 (DOCX 38 kb)

References

  1. 1.
    Benjamin EJ, Blaha MJ, Chiuve SE et al (2017) Heart disease and stroke statistics—2017 update: a report from the American Heart Association. Circulation.  https://doi.org/10.1161/cir.0000000000000485
  2. 2.
    Jauch EC, Saver JL, Adams HP Jr et al (2013) Guidelines for the early management of patients with acute ischemic stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke 44:870–947CrossRefPubMedGoogle Scholar
  3. 3.
    Amar AP (2011) Brain and vascular imaging of acute stroke. World Neurosurg 76:S3–S8CrossRefPubMedGoogle Scholar
  4. 4.
    Mohr JP, Biller J, Hilal SK et al (1995) Magnetic resonance versus computed tomographic imaging in acute stroke. Stroke 26:807–812CrossRefPubMedGoogle Scholar
  5. 5.
    Wu H-Q, Wu H, Shi L-L et al (2017) The association between retinal vasculature changes and stroke: a literature review and meta-analysis. Int J Ophthalmol 10:109–114PubMedPubMedCentralGoogle Scholar
  6. 6.
    Barber PA, Demchuk AM, Zhang J, Buchan AM (2000) Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy. Lancet 355:1670–1674CrossRefPubMedGoogle Scholar
  7. 7.
    Przelaskowski A, Sklinda K, Bargieł P, Walecki J, Biesiadko-Matuszewska M, Kazubek M (2007) Improved early stroke detection: wavelet-based perception enhancement of computerized tomography exams. Comput Biol Med 37:524–533CrossRefPubMedGoogle Scholar
  8. 8.
    Chawla M, Sharma S, Sivaswamy J, Kishore L (2009) A method for automatic detection and classification of stroke from brain CT images. Conf Proc IEEE Eng Med Biol Soc 2009:3581–3584PubMedGoogle Scholar
  9. 9.
    Tang F-h, Ng DKS, Chow DHK (2011) An image feature approach for computer-aided detection of ischemic stroke. Comput Biol Med 41:529–536CrossRefPubMedGoogle Scholar
  10. 10.
    Hacke W, Kaste M, Bluhmki E et al (2008) Thrombolysis with alteplase 3 to 4.5 hours after acute ischemic stroke. N Engl J Med 359:1317–1329CrossRefPubMedGoogle Scholar
  11. 11.
    Huisa BN, Raman R, Ernstrom K et al (2010) Alberta stroke program early CT score (ASPECTS) in patients with wake-up stroke. J Stroke Cerebrovasc Dis 19:475–479CrossRefPubMedPubMedCentralGoogle Scholar
  12. 12.
    Bergounioux M (2016) Mathematical analysis of a inf-convolution model for image processing. J Optim Theory Appl 168:1–21CrossRefGoogle Scholar
  13. 13.
    Bergounioux M, Caillau J-B, Haberkorn T, Peyré G, Schnörr C (2016) Variational methods in imaging and geometric control. de Gruyter, FranceCrossRefGoogle Scholar
  14. 14.
    Bilmes JA (1998) A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. University of Berkeley, California 94704-1198Google Scholar
  15. 15.
    Zhang Y, Brady M, Smith S (2001) Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans Med Imaging 20:45–57CrossRefPubMedGoogle Scholar
  16. 16.
    Newcombe RG (1998) Two-sided confidence intervals for the single proportion: comparison of seven methods. Stat Med 17:857–872CrossRefPubMedGoogle Scholar
  17. 17.
    Patel SC, Levine SR, Tilley BC et al (2001) Lack of clinical significance of early ischemic changes on computed tomography in acute stroke. JAMA 286:2830–2838CrossRefPubMedGoogle Scholar
  18. 18.
    von Kummer R, Holle R, Gizyska U et al (1996) Interobserver agreement in assessing early CT signs of middle cerebral artery infarction. Am J Neuroradiol 17:1743–1748Google Scholar
  19. 19.
    Latchaw RE, Alberts MJ, Lev MH et al (2009) Recommendations for imaging of acute ischemic stroke. A scientific statement from the American Heart Association. Stroke 40:3646–3678CrossRefPubMedGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  • Allan Felipe Fattori Alves
    • 1
  • Rachid Jennane
    • 2
  • José Ricardo Arruda de Miranda
    • 1
  • Carlos Clayton Macedo de Freitas
    • 3
  • Nitamar Abdala
    • 4
  • Diana Rodrigues de Pina
    • 5
  1. 1.Instituto de Biociências de Botucatu, Departamento de Física e BiofísicaUNESP—Universidade Estadual PaulistaBotucatuBrazil
  2. 2.Laboratory I3MTO – University of OrleansOrléansFrance
  3. 3.Departamento de Neurologia, Psicologia e Psiquiatria, Faculdade de Medicina de BotucatuUNESP—Universidade Estadual PaulistaBotucatuBrazil
  4. 4.Departamento de Diagnóstico por ImagemEscola Paulista de Medicina – UNIFESPSão PauloBrazil
  5. 5.Departamento de Doenças Tropicais e Diagnóstico por Imagem, Faculdade de Medicina de BotucatuUNESP—Universidade Estadual PaulistaBotucatuBrazil

Personalised recommendations