Advertisement

Deep Convolutional Autoencoders vs PCA in a Highly-Unbalanced Parkinson’s Disease Dataset: A DaTSCAN Study

  • Francisco Jesús Martinez-MurciaEmail author
  • Andres Ortiz
  • Juan Manuel Gorriz
  • Javier Ramirez
  • Diego Castillo-Barnes
  • Diego Salas-Gonzalez
  • Fermin Segovia
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 771)

Abstract

The automated analysis of medical imaging, especially brain imaging, is a challenging high-dimensional task. Computer Aided Diagnosis (CAD) tools often require the images to be spatially normalized and then perform feature extraction to be able to avoid the small sample size problem. However, the spatial normalization often introduces artefacts, especially in functional imaging. Furthermore, variance-based decomposition techniques like PCA, which are extensively used in CAD tools, often perform poorly in highly-unbalanced dataset. To overcome these two problems, we propose a deep Convolutional Autoencoder (CAE) architecture that performs image decomposition -or encoding- in images that were not spatially normalized. A CAD system that used CAE for feature extraction and a Support Vector Machine Classifier (SVC) for classification was tested on a strongly imbalanced (5.69/1) Parkinson’s Disease (PD) neuroimaging dataset from the Parkinson’s Progression Markers Initiative (PPMI), achieving more than 93% accuracy in detecting PD with DaTSCAN imaging, and a area under the ROC curve higher than 0.96. This system paves the way for new deep learning decompositions that bypass the common spatial normalization step and are able to extract relevant information in highly-imbalanced datasets.

Keywords

Autoencoder Convolutional neural networks Deep learning Parkinson’s Disease DaTSCAN 

Notes

Acknowledgements

This work was partly supported by the MINECO/FEDER under the TEC2015-64718-R project and the Consejera de Economía, Innovación, Ciencia y Empleo (Junta de Andalucía, Spain) under the Excellence Project P11-TIC- 7103.

References

  1. 1.
    Baldi, P.: Autoencoders, unsupervised learning, and deep architectures. In: Proceedings of ICML Workshop on Unsupervised and Transfer Learning, pp. 37–49 (2012)Google Scholar
  2. 2.
    De Martino, F., Gentile, F., Esposito, F., Balsi, M., Di Salle, F., Goebel, R., Formisano, E.: Classification of fMRI independent components using IC-fingerprints and support vector machine classifiers. Neuroimage 34(1), 177–194 (2007)CrossRefGoogle Scholar
  3. 3.
    Duin, R.P.W.: Classifiers in almost empty spaces. In: Proceedings 15th International Conference on Pattern Recognition, vol. 2, pp. 1–7. IEEE (2000)Google Scholar
  4. 4.
    Ecker, C., Marquand, A., Mourão-Miranda, J., Johnston, P., Daly, E.M., Brammer, M.J., Maltezos, S., Murphy, C.M., Robertson, D., Williams, S.C., Murphy, D.G.M.: Describing the brain in autism in five dimensions-magnetic resonance imaging-assisted diagnosis of autism spectrum disorder using a multiparameter classification approach. J. Neurosci. 30(32), 10612–10623 (2010)CrossRefGoogle Scholar
  5. 5.
    Fischl, B., Dale, A.M.: Measuring the thickness of the human cerebral cortex from magnetic resonance images. Proc. Nat. Acad. Sci. 97(20), 11050–11055 (2000)CrossRefGoogle Scholar
  6. 6.
    Friston, K., Ashburner, J., Kiebel, S., Nichols, T., Penny, W.: Statistical Parametric Mapping: The Analysis of Functional Brain Images. Academic Press, London (2007)CrossRefGoogle Scholar
  7. 7.
    Hansen, L.K., Larsen, J., Nielsen, F.Å., Strother, S.C., Rostrup, E., Savoy, R., Lange, N., Sidtis, J., Svarer, C., Paulson, O.B.: Generalizable patterns in neuroimaging: how many principal components? NeuroImage 9(5), 534–544 (1999)CrossRefGoogle Scholar
  8. 8.
    Initiative, T.P.P.M.: PPMI. Imaging Technical Operations Manual, 2 edn., June 2010Google Scholar
  9. 9.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of International Joint Conference on AI, pp. 1137–1145 (1995). http://citeseer.ist.psu.edu/kohavi95study.html
  10. 10.
    Lila, E., Aston, J.A., Sangalli, L.M., et al.: Smooth principal component analysis over two-dimensional manifolds with an application to neuroimaging. Ann. Appl. Stat. 10(4), 1854–1879 (2016)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Martínez-Murcia, F., Górriz, J., Ramírez, J., Moreno-Caballero, M., Gómez-Río, M., Parkinson’s Progression Markers Initiative, et al.: Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of parkinsonism. Med. Phys. 41(1), 012502 (2014)Google Scholar
  12. 12.
    Martinez-Murcia, F.J., Górriz, J.M., Ramírez, J., Illán, I.A., Segovia, F., Castillo-Barnes, D., Salas-Gonzalez, D.: Functional brain imaging synthesis based on image decomposition and kernel modeling: application to neurodegenerative diseases. Front. Neuroinformatics 11, 65 (2017)CrossRefGoogle Scholar
  13. 13.
    Martínez-Murcia, F.J., Górriz, J., Ramírez, J., Puntonet, C.G., Illán, I.: Functional activity maps based on significance measures and independent component analysis. Comput. Methods Programs Biomed. 111(1), 255–268 (2013)CrossRefGoogle Scholar
  14. 14.
    Martínez-Murcia, F.J., Górriz, J.M., Ramírez, J., Illán, I.A., Puntonet, C.G.: Texture features based detection of Parkinson’s Disease on DaTSCAN images. In: Natural and Artificial Computation in Engineering and Medical Applications, pp. 266–277. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  15. 15.
    Martinez-Murcia, F.J., Ortiz, A., Górriz, J.M., Ramírez, J., Segovia, F., Salas-Gonzalez, D., Castillo-Barnes, D., Illán, I.A.: A 3D convolutional neural network approach for the diagnosis of Parkinson’s Disease. In: Natural and Artificial Computation for Biomedicine and Neuroscience, pp. 324–333. Springer International Publishing, Cham (2017)CrossRefGoogle Scholar
  16. 16.
    Martinez-Torteya, A., Rodriguez-Rojas, J., Celaya-Padilla, J.M., Galván-Tejada, J.I., Treviño, V., Tamez-Peña, J.: Magnetization-prepared rapid acquisition with gradient echo magnetic resonance imaging signal and texture features for the prediction of mild cognitive impairment to Alzheimer’s disease progression. J. Med. Imaging 1(3), 031005 (2014)CrossRefGoogle Scholar
  17. 17.
    Napierała, K., Stefanowski, J., Wilk, S.: Learning from imbalanced data in presence of noisy and borderline examples. In: International Conference on Rough Sets and Current Trends in Computing, pp. 158–167. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Nixon, M.: Feature Extraction & Image Processing. Academic Press, London (2008)Google Scholar
  19. 19.
    Ortiz, A., Górriz, J.M., Ramírez, J., Martinez-Murcia, F.J., Initiative, A.D.N., et al.: Automatic ROI selection in structural brain MRI using SOM 3D projection. PLOS ONE 9(4), e93851 (2014)CrossRefGoogle Scholar
  20. 20.
    Ortiz, A., Górriz, J.M., Ramírez, J., Martínez-Murcia, F.J.: LVQ-SVM based CAD tool applied to structural MRI for the diagnosis of the Alzheimer’s disease. Pattern Recogn. Lett. 34(14), 1725–1733 (2013)CrossRefGoogle Scholar
  21. 21.
    Ortiz, A., Martínez-Murcia, F.J., García-Tarifa, M.J., Lozano, F., Górriz, J.M., Ramírez, J.: Automated diagnosis of parkinsonian syndromes by deep sparse filtering-based features. In: Innovation in Medicine and Healthcare 2016, pp. 249–258. Springer, Cham (2016)CrossRefGoogle Scholar
  22. 22.
    Ortiz, A., Munilla, J., Martínez-Murcia, F.J., Górriz, J.M., Ramírez, J., for the Alzheimer’s Disease Neuroimaging Initiative, et al.: Learning longitudinal MRI patterns by SICE and deep learning: assessing the alzheimers disease progression. In: Annual Conference on Medical Image Understanding and Analysis, pp. 413–424. Springer, Cham (2017)Google Scholar
  23. 23.
    Powers, D.M.: Evaluation: from precision, recall and f-measure to ROC, informedness, markedness and correlation (2011)Google Scholar
  24. 24.
    Quackenbush, J.: Computational analysis of microarray data. Nat. Rev. Genet. 2(6), 418–427 (2001)CrossRefGoogle Scholar
  25. 25.
    Segovia, F., Górriz, J.M., Ramírez, J., Chaves, R., Illán, I.Á.: Automatic differentiation between controls and Parkinson’s Disease DaTSCAN images using a partial least squares scheme and the fisher discriminant ratio. In: KES, pp. 2241–2250 (2012)Google Scholar
  26. 26.
    Sonka, M., Hlavac, V., Boyle, R.: Image processing, analysis, and machine vision. Cengage Learning (2014)Google Scholar
  27. 27.
    Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: The all convolutional net (2014). arXiv preprint: arXiv:1412.6806
  28. 28.
    Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. 4(2), 26–31 (2012)Google Scholar
  29. 29.
    Wang, X., Yang, W., Weinreb, J., Han, J., Li, Q., Kong, X., Yan, Y., Ke, Z., Luo, B., Liu, T., Wang, L.: Searching for prostate cancer by fully automated magnetic resonance imaging classification: deep learning versus non-deep learning. Sci. Rep. 7(1), 15415 (2017)CrossRefGoogle Scholar
  30. 30.
    Weiner, M.W., Veitch, D.P., Aisen, P.S., Beckett, L.A., Cairns, N.J., Green, R.C., Harvey, D., Jack, C.R., Jagust, W., Liu, E., Morris, J.C., Petersen, R.C., Saykin, A.J., Schmidt, M.E., Shaw, L., Siuciak, J.A., Soares, H., Toga, A.W., Trojanowski, J.Q.: The Alzheimer’s disease neuroimaging initiative: a review of papers published since its inception. Alzheimer’s Dement. J. Alzheimer’s Assoc. 8(Suppl. 1), S1–S68 (2012). http://www.ncbi.nlm.nih.gov/pubmed/22047634, PMID: 22047634Google Scholar
  31. 31.
    Xu, J., Xiang, L., Liu, Q., Gilmore, H., Wu, J., Tang, J., Madabhushi, A.: Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Trans. Med. Imaging 35(1), 119–130 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Francisco Jesús Martinez-Murcia
    • 1
    Email author
  • Andres Ortiz
    • 2
  • Juan Manuel Gorriz
    • 1
  • Javier Ramirez
    • 1
  • Diego Castillo-Barnes
    • 1
  • Diego Salas-Gonzalez
    • 1
  • Fermin Segovia
    • 1
  1. 1.Department of Signal Theory, Networking and CommunicationsUniversity of GranadaGranadaSpain
  2. 2.Department of Communications EngineeringUniversity of MálagaMálagaSpain

Personalised recommendations