Advertisement

Classification Improvement for Parkinson’s Disease Diagnosis Using the Gradient Magnitude in DaTSCAN SPECT Images

  • Diego Castillo-BarnesEmail author
  • Fermin Segovia
  • Francisco J. Martinez-Murcia
  • Diego Salas-Gonzalez
  • Javier Ramírez
  • Juan M. Górriz
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 771)

Abstract

In this work, we propose a novel imaging preprocessing step based on the use of the gradient magnitude for medical DaTSCAN SPECT images. As Parkinson’s Disease (PD) is characterized by a marked reduction of intensity at striatum area, measuring intensities in this region is considered as a good marker for this neurological disorder. To extend this idea, we have been studying how quick these values decrease. A simple way to do this was using the gradient of each image. Applying Machine Learning algorithms, we have classified the gradient images and obtained an accuracy improvement of almost 2%. These results prove that the gradient magnitude is even a better marker for PD diagnosis and opens the door to new future investigations about this pathology.

Keywords

Parkinson’s Disease Gradient SVM Classification Machine Learning \(\alpha \)-Stable distributions Parkinson’s Progression Markers Initiative (PPMI) SPECT DaTSCAN Neuroimaging 

Notes

Acknowledgements

This work was supported by the MINECO/FEDER under the TEC2015-64718-R project and the Ministry of Economy, Innovation, Science and Employment of the Junta de Andalucía under the Excellence Project P11-TIC-7103.

References

  1. 1.
    Pohl, A.: Impaired emotional mirroring in Parkinsons disease - a study on brain activation during processing of facial expressions. Front. Neurol. 8, 682 (2017)CrossRefGoogle Scholar
  2. 2.
    Kordower, J.H.: Disease duration and the integrity of the nigrostriatal system in Parkinsons disease. Brain 136(8), 2419–2431 (2013)CrossRefGoogle Scholar
  3. 3.
    Neumeyer, J.L.: [123I]-2\(\beta \)-carbomethoxy-3\(\beta \)-(4-iodophenyl)tropane: high-affinity SPECT (single photon emission computed tomography) radiotracer of monoamine reuptake sites in brain. J. Med. Chem. 34(10), 3144–3146 (1991)CrossRefGoogle Scholar
  4. 4.
    Sixel-Döring, F.: The role of 123I-FP-CIT-SPECT in the differential diagnosis of Parkinson and tremor syndromes: a critical assessment of 125 cases. J. Neurol. 258(12), 2147–2154 (2011)CrossRefGoogle Scholar
  5. 5.
    Marek, K.L.: [123I]\(\beta \)-CIT SPECT imaging assessment of the rate of Parkinson’s disease progression. Neurology 57(11), 2089–2094 (2001)CrossRefGoogle Scholar
  6. 6.
    Illán, I.A.: Automatic assistance to Parkinsons disease diagnosis in DaTSCAN SPECT imaging. Med. Phys. 39(10), 5971–5980 (2012)CrossRefGoogle Scholar
  7. 7.
    Segovia, F.: Improved Parkinsonism diagnosis using a partial least squares based approach. Med. Phys. 39, 4395–4403 (2012)CrossRefGoogle Scholar
  8. 8.
    Martínez-Murcia, F.J.: Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of Parkinsonism. Med. Phys. 41(1), 012502 (2014)CrossRefGoogle Scholar
  9. 9.
    Wyman-Chick, K.A.: Cognition in patients with a clinical diagnosis of Parkinson disease and scans without evidence of dopaminergic deficit (SWEDD): 2-year follow-up. Cognit. Behav. Neurol. 29(4), 190–196 (2016)CrossRefGoogle Scholar
  10. 10.
    Salas-González, D.: Finite mixture of \(\alpha \)-stable distributions. Digit. Signal Process. 19(2), 250–264 (2009)CrossRefGoogle Scholar
  11. 11.
    Salas-González, D.: Linear intensity normalization of FP-CIT SPECT brain images using the \(\alpha \)-stable distribution. NeuroImage 65(C), 449–455 (2013)CrossRefGoogle Scholar
  12. 12.
    Brahim, A.: Intensity normalization of DaTSCAN SPECT imaging using a model-based clustering approach. Appl. Soft Comput. 37(C), 234–244 (2015)CrossRefGoogle Scholar
  13. 13.
    Sobel, I.: History and Definition of the Sobel Operator (2014)Google Scholar
  14. 14.
    Engel, K.: Real-time Volume Graphics, 2nd edn, pp. 109–113. A. K. Peters Ltd., Natick (2006)CrossRefGoogle Scholar
  15. 15.
    Martínez-Murcia, F.J.: Computer aided diagnosis tool for Alzehimer’s disease based on Mann-Whitney-Wilcoxon U-Test. Expert Syst. Appl. 39(10), 9676–9685 (2012)CrossRefGoogle Scholar
  16. 16.
    Tong, T.: Multi-modal classification of Alzheimers disease using nonlinear graph fusion. Pattern Recognit. 63(C), 171–181 (2017)CrossRefGoogle Scholar
  17. 17.
    Li, Q.: Multi-modal discriminative dictionary learning for Alzheimers disease and mild cognitive impairment. Comput. Methods Programs Biomed. 150(C), 1–8 (2017)CrossRefGoogle Scholar
  18. 18.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI 1995), vol. 2, pp. 1137–1145 (1995)Google Scholar
  19. 19.
    Zweig, M.H.: Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin. Chem. 39(4), 561–577 (1993)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Diego Castillo-Barnes
    • 1
    Email author
  • Fermin Segovia
    • 1
  • Francisco J. Martinez-Murcia
    • 1
  • Diego Salas-Gonzalez
    • 1
  • Javier Ramírez
    • 1
  • Juan M. Górriz
    • 1
  1. 1.Department of Signal Theory, Networking and CommunicationsUniversity of GranadaGranadaSpain

Personalised recommendations