World Scientific
Skip main navigation

Cookies Notification

We use cookies on this site to enhance your user experience. By continuing to browse the site, you consent to the use of our cookies. Learn More
Our website is made possible by displaying certain online content using javascript.
In order to view the full content, please disable your ad blocker or whitelist our website

System Upgrade on Mon, Jun 21st, 2021 at 1am (EDT)

During this period, the E-commerce and registration of new users may not be available for up to 6 hours.
For online purchase, please visit us again. Contact us at [email protected] for any enquiries.

Convolutional Neural Networks for Neuroimaging in Parkinson’s Disease: Is Preprocessing Needed?

    Spatial and intensity normalizations are nowadays a prerequisite for neuroimaging analysis. Influenced by voxel-wise and other univariate comparisons, where these corrections are key, they are commonly applied to any type of analysis and imaging modalities. Nuclear imaging modalities such as PET-FDG or FP-CIT SPECT, a common modality used in Parkinson’s disease diagnosis, are especially dependent on intensity normalization. However, these steps are computationally expensive and furthermore, they may introduce deformations in the images, altering the information contained in them. Convolutional neural networks (CNNs), for their part, introduce position invariance to pattern recognition, and have been proven to classify objects regardless of their orientation, size, angle, etc. Therefore, a question arises: how well can CNNs account for spatial and intensity differences when analyzing nuclear brain imaging? Are spatial and intensity normalizations still needed? To answer this question, we have trained four different CNN models based on well-established architectures, using or not different spatial and intensity normalization preprocessings. The results show that a sufficiently complex model such as our three-dimensional version of the ALEXNET can effectively account for spatial differences, achieving a diagnosis accuracy of 94.1% with an area under the ROC curve of 0.984. The visualization of the differences via saliency maps shows that these models are correctly finding patterns that match those found in the literature, without the need of applying any complex spatial normalization procedure. However, the intensity normalization — and its type — is revealed as very influential in the results and accuracy of the trained model, and therefore must be well accounted.


    • 1. Y. LeCun, Y. Bengio and G. Hinton, Deep learning, Nature 521 (2015) 436–444. Crossref, Medline, ISIGoogle Scholar
    • 2. K. Kim, H. Kim and J. Seo, A neural network model with feature selection for Korean speech act classification, Int. J. Neural Syst. 14(6) (2004) 407–414. LinkGoogle Scholar
    • 3. G. Hinton, L. Deng, D. Yu, G. E. Dahl, A.-R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath and B. Kingsbury, Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, IEEE Signal Process. Mag. 29(6) (2012) 82–97. Crossref, ISIGoogle Scholar
    • 4. J. A. Garrido, N. R. Luque, S. Tolu and E. Ďangelo, Oscillation-driven spike-timing dependent plasticity allows multiple overlapping pattern recognition in inhibitory interneuron networks, Int. J. Neural Syst. 26(5) (2016) 1650020. Link, ISIGoogle Scholar
    • 5. E. Gawehn, J. A. Hiss and G. Schneider, Deep learning in drug discovery, Mol. Inf. 35(1) (2016) 3–14. Crossref, MedlineGoogle Scholar
    • 6. B. Alipanahi, A. Delong, M. T. Weirauch and B. J. Frey, Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning, Nat. Biotechnol. 33(8) (2015) 831–838. Crossref, Medline, ISIGoogle Scholar
    • 7. S. Liao, Y. Gao, A. Oto and D. Shen, Representation learning: A unified deep learning framework for automatic prostate MR segmentation, in Proc. Int. Conf. Medical Image Computing and Computer-Assisted Intervention (Springer, 2013), pp. 254–261. Google Scholar
    • 8. L. D. Olson and M. S. Perry, Localization of epileptic foci using multimodality neuroimaging, Int. J. Neural syst. 23(1) (2013) 1230001. Link, ISIGoogle Scholar
    • 9. Y. Xu, T. Mo, Q. Feng, P. Zhong, M. Lai, I. Eric and C. Chang, Deep learning of feature representation with multiple instance learning for medical image analysis, in Proc. 2014 IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2014), pp. 1626–1630. Google Scholar
    • 10. H. Greenspan, B. van Ginneken and R. M. Summers, Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique, IEEE Trans. Med. Imaging 35(5) (2016) 1153–1159. CrossrefGoogle Scholar
    • 11. A. Ortiz, F. J. Martínez-Murcia, M. J. García-Tarifa, F. Lozano, J. M. Górriz and J. Ramírez, Automated diagnosis of Parkinsonian syndromes by deep sparse filtering-based features, in Innovation in Medicine and Healthcare 2016: InMed 2016, Smart innovation, Systems and Technologies, Vol. 60 (Springer, 2016), pp. 249–258. CrossrefGoogle Scholar
    • 12. D. Martín-López, D. Jiménez-Jiménez, L. Cabañés-Martínez, R. P. Selway, A. Valentín and G. Alarcón, The role of thalamus versus cortex in epilepsy: Evidence from human ictal centromedian recordings in patients assessed for deep brain stimulation, Int. J. Neural Syst. 27(7) (2017) 1750010. Link, ISIGoogle Scholar
    • 13. K. Friston, J. Ashburner, S. Kiebel, T. Nichols and W. Penny, Statistical Parametric Mapping: The Analysis of Functional Brain Images (Academic Press, 2007). CrossrefGoogle Scholar
    • 14. I. A. Illán, J. M. Górriz, J. Ramírez, D. Salas-Gonzalez, M. M. López, F. Segovia, R. Chaves, M. Gómez-Rio and C. G. Puntonet, 18F-FDG PET imaging analysis for computer aided Alzheimer’s diagnosis, Inf. Sci. 181(4) (2011) 903–916. Crossref, ISIGoogle Scholar
    • 15. F. Segovia, J. M. Górriz, J. Ramírez, R. Chaves and I. Á. Illán, Automatic differentiation between controls and Parkinson’s disease DaTSCAN images using a partial least squares scheme and the fisher discriminant ratio, in Advances in Knowledge-Based and Intelligent Information and Engineering Syslems (IOS Press, 2012), pp. 2241–2250. Google Scholar
    • 16. P. Saxena, D. G. Pavel, J. C. Quintana and B. Horwitz, An automatic threshold-based scaling method for enhancing the usefulness of Tc-HMPAO SPECT in the diagnosis of Alzheimer’s disease, in Medical Image Computing and Computer-Assisted Intervention MICCAI (Lecture Notes in Computer Science, 1998), Vol. 1496, (Springer, 1998), pp. 623–630. CrossrefGoogle Scholar
    • 17. J. M. Gorriz, J. Ramirez, J. Suckling, I. Illan, A. Ortiz, F. J. Martinez, F. Segovia, D. Salas-Gonzalez and S. Wang, Case-based statistical learning: A non parametric implementation with a conditional-error rate SVM, IEEE Access 5 (2017) 11468–11478. CrossrefGoogle Scholar
    • 18. F. Martinez-Murcia, J. Górriz and J. Ramírez, Computer-aided diagnosis in Neuroimaging, in Computer Aided Diagnosis in Neuroimaging, Computer-aided Technologies: Applications in Engineering and Medicine, ed. R. Udroiu (InTech, 2016), pp. 137–160. CrossrefGoogle Scholar
    • 19. M. López, J. Ramírez, J. Górriz, I. Álvarez, D. Salas-Gonzalez, F. Segovia, R. Chaves, P. Padilla and M. Gómez-Río, Principal component analysis-based techniques and supervised classification schemes for the early detection of Alzheimer’s disease, Neurocomputing 74(8) (2011) 1260–1271. Crossref, ISIGoogle Scholar
    • 20. F. Martínez-Murcia, J. Górriz, J. Ramírez, M. Moreno-Caballero and M. Gómez-Río, Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of parkinsonism, Med. Phys. 41(1) (2014) 012502. Crossref, Medline, ISIGoogle Scholar
    • 21. J. Ramírez, J. M. Górriz, F. Segovia, R. Chaves, D. Salas-Gonzalez, M. López, I. Álvarez and P. Padilla, Computer aided diagnosis system for the Alzheimer’s disease based on partial least squares and random forest SPECT image classification, Neurosci. Lett. 472(2) (2010) 99–103. Crossref, MedlineGoogle Scholar
    • 22. K. Ishii, F. Willoch, S. Minoshima, A. Drzezga, E. P. Ficaro, D. J. Cross, D. E. Kuhl and M. Schwaiger, Statistical brain mapping of 18F-FDG PET in alzheimers disease: validation of anatomic standardization for atrophied brains, J. Nucl. Med. 42(4) (2001) 548–557. MedlineGoogle Scholar
    • 23. S. Reig, M. Penedo, J. Gispert, J. Pascau, J. Sánchez-González, P. García-Barreno and M. Desco, Impact of ventricular enlargement on the measurement of metabolic activity in spatially normalized PET, NeuroImage 35 (2007) 748–758. Crossref, MedlineGoogle Scholar
    • 24. M. E. Martino, J. G. de Villoria, M. Lacalle-Aurioles, J. Olazarán, I. Cruz, E. Navarro, V. García-Vázquez, J. L. Carreras and M. Desco, Comparison of different methods of spatial normalization of FDG-PET brain images in the voxel-wise analysis of MCI patients and controls, Ann. Nucl. Med. 27 (2013) 600–609. Crossref, MedlineGoogle Scholar
    • 25. D. Salas-Gonzalez, J. Gorriz, J. Ramirez, F. Martinez, R. Chaves, F. Segovia and I. Illan, Intensity normalization of FP-CIT SPECT in patients with parkinsonism using the α-stable distribution, in Proc. 2012 IEEE Nuclear Science Symp. and Medical Imaging Conf. (NSS/MIC), (IEEE, 2012), pp. 3944–3946. Google Scholar
    • 26. R. Yuvaraj, M. Murugappan, U. R. Acharya, H. Adeli, N. M. Ibrahim and E. Mesquita, Brain functional connectivity patterns for emotional state classification in Parkinson’s disease patients without dementia, Behav. Brain Res. 298 (2016) 248–260. Crossref, Medline, ISIGoogle Scholar
    • 27. F. J. Martinez-Murcia, A. Ortiz, J. M. Górriz, J. Ramírez, F. Segovia, D. Salas-Gonzalez, D. Castillo-Barnes and I. A. Illán, A 3D convolutional neural network approach for the diagnosis of Parkinson’s disease, in Natural and Artificial Computation for Biomedicine and Neuroscience (Springer International Publishing, 2017), pp. 324–333. CrossrefGoogle Scholar
    • 28. T. J. Hirschauer, H. Adeli and J. A. Buford, Computer-aided diagnosis of Parkinsons disease using enhanced probabilistic neural network, J. Med. Syst. 39(11) (2015) 179. Crossref, Medline, ISIGoogle Scholar
    • 29. F. C. Morabito, M. Campolo, N. Mammone, M. Versaci, S. Franceschetti, F. Tagliavini, V. Sofia, D. Fatuzzo, A. Gambardella, A. Labate, L. Mumoli, G. G. Tripodi, S. Gasparini, V. Ganci, C. Sueri, E. Ferlazzo and U. Aguglia, Deep learning representation from electroencephalography of early-stage creutzfeldt-jakob disease and features for differentiation from rapidly progressive dementia, Int. J. Neural Syst. 27(2) (2017) 1650039. Link, ISIGoogle Scholar
    • 30. M. Koziarski and B. Cyganek, Image recognition with deep neural networks in presence of noise:Dealing with and taking advantage of distortions, Integr. Comput.-Aided Eng. 24(4) (2017) 337–349. Crossref, ISIGoogle Scholar
    • 31. F. Ortega-Zamorano, J. M. Jerez, I. Gómez and L. Franco, Layer multiplexing FPGA implementation for deep back-propagation learning, Integr. Comput.-Aided Eng. 24(2) (2017) 171–185. Crossref, ISIGoogle Scholar
    • 32. Y.-Z. Lin, Z.-H. Nie and H.-W. Ma, Structural damage detection with automatic feature-extraction through deep learning, Comput.-Aided Civil and Infrastruct. Eng. 32(12) (2017) 1025–1046. CrossrefGoogle Scholar
    • 33. A. Zhang, K. C. Wang, B. Li, E. Yang, X. Dai, Y. Peng, Y. Fei, Y. Liu, J. Q. Li and C. Chen, Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network, Comput.-Aided Civil Infrastruct. Eng. 32(10) (2017) 805–819. Crossref, ISIGoogle Scholar
    • 34. Y.-J. Cha, W. Choi and O. Büyüköztürk, Deep learning-based crack damage detection using convolutional neural networks, Comput.-Aided Civil Infrastruct. Eng. 32(5) (2017) 361–378. CrossrefGoogle Scholar
    • 35. M. H. Rafiei and H. Adeli, A novel machine learning model for estimation of sale prices of real estate units, J. Constr. Eng. Management 142(2) (2015) 04015066. CrossrefGoogle Scholar
    • 36. M. H. Rafiei, W. H. Khushefati, R. Demirboga and H. Adeli, Supervised deep restricted Boltzmann machine for estimation of concrete, ACI Mater. J. 114(2) (2017) 237–244. Crossref, ISIGoogle Scholar
    • 37. M. H. Rafiei and H. Adeli, A novel machine learning-based algorithm to detect damage in high-rise building structures, Struct. Des. Tall Spec. Build. 26(18) (2017) e1400. Crossref, ISIGoogle Scholar
    • 38. M. H. Rafiei and H. Adeli, A novel unsupervised deep learning model for global and local health condition assessment of structures, Eng. Struct. 156 (2018) 598–607. Crossref, ISIGoogle Scholar
    • 39. U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan and H. Adeli, Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals, Comput. Biol. Med. (2017). Google Scholar
    • 40. Parkinson’s Progression Markeres Initiative, PPMI: Imaging Technical Operations Manual, 2 edn. (PPMI, 2010). Google Scholar
    • 41. J. Mazziotta, et al., A probabilistic atlas and reference system for the human brain: International consortium for Brain Mapping (ICBM), Philos. Trans. R. Soc. Lond. B, Biol. Sci. 356(1412) (2001) 1293–1322. Crossref, Medline, ISIGoogle Scholar
    • 42. M. Reuter, H. D. Rosas and B. Fischl, Highly accurate inverse consistent registration: A robust approach, NeuroImage 53(4) (2010) 1181–1196. Crossref, MedlineGoogle Scholar
    • 43. D. Salas-Gonzalez, J. M. Górriz, J. Ramírez, I. A. Illán, P. Padilla, F. J. Martínez-Murcia and E. W. Lang, Building a FP-CIT SPECT brain template using a posterization approach, Neuroinformatics 13(4) (2015) 391–402. Crossref, MedlineGoogle Scholar
    • 44. F. Martínez-Murcia, J. Górriz, J. Ramírez, C. Puntonet and D. Salas-González, Computer aided diagnosis tool for Alzheimer’s disease based on Mann–Whitney–Wilcoxon U-test, Expert Syst. Appl. 39 (2012) 9676–9685. CrossrefGoogle Scholar
    • 45. I. Illán, J. Górriz, J. Ramírez, F. Segovia, J. Jiménez-Hoyuela and S. Ortega-Lozano, Automatic assistance to Parkinson’s disease diagnosis in DaTSCAN SPECT imaging, Med. Phys. 39(10) (2012) 5971–5980. Crossref, Medline, ISIGoogle Scholar
    • 46. A. Krizhevsky, I. Sutskever and G. E. Hinton, ImageNet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (NIPS), (2012), pp. 1097–1105. Google Scholar
    • 47. D. C. Ciresan, U. Meier, J. Masci, L. Maria Gambardella and J. Schmidhuber, Flexible, high performance convolutional neural networks for image classification, in IJCAI Proc: Int. Joint Conf. Artificial Intelligence (2011), pp. 1237–1242. Google Scholar
    • 48. F. Segovia, M. García-Pérez, J. M. Górriz, J. Ramírez and F. J. Martínez-Murcia, Assisting the diagnosis of neurodegenerative disorders using principal component analysis and tensorflow, in Proc. Int. Conf. European Transnational Education (Springer, 2016), pp. 43–52. Google Scholar
    • 49. S. Sabour, N. Frosst and G. E. Hinton, Dynamic routing between capsules, in Advances in Neural Information Processing Systems (NIPS), (2017), pp. 3857–3867. Google Scholar
    • 50. J. Schmidhuber, Deep learning in neural networks: An overview, Neural Netw. 61 (2015) 85–117. Crossref, Medline, ISIGoogle Scholar
    • 51. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mané, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viégas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu and X. Zheng, TensorFlow: Large-scale machine learning on heterogeneous systems (2015), arXiv:1603.04467 [cs.DC]. Google Scholar
    • 52. A. Payan and G. Montana, Predicting Alzheimer’s disease: A neuroimaging study with 3D convolutional neural networks, arXiv:1502.02506 [cs.CV]. Google Scholar
    • 53. J. T. Springenberg, A. Dosovitskiy, T. Brox and M. Riedmiller, Striving for simplicity: The all convolutional net, arXiv:1412.6806 [cs.LG]. Google Scholar
    • 54. Y. LeCun, L. Bottou, Y. Bengio and P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86(11) (1998) 2278–2324. Crossref, ISIGoogle Scholar
    • 55. G. Klambauer, T. Unterthiner, A. Mayr and S. Hochreiter, Self-normalizing neural networks, arXiv:1706.02515 [cs.LG]. Google Scholar
    • 56. R. Kohavi and G. H. John, Wrappers for feature subset selection, Artif. Intell. 97(1–2) (1997) 273–324. Crossref, ISIGoogle Scholar
    • 57. J. A. Hanley and B. J. McNeil, The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology 143(1) (1982) 29–36. Crossref, Medline, ISIGoogle Scholar
    • 58. F. Segovia, J. M. Górriz, J. Ramírez, I. Álvarez, J. M. Jiménez-Hoyuela and S. J. Ortega, Improved Parkinsonism diagnosis using a partial least squares based approach, Med. phys. 39(7) (2012) 4395–4403. Crossref, Medline, ISIGoogle Scholar
    • 59. K. Simonyan, A. Vedaldi and A. Zisserman, Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv:1312.6034 [cs.CV]. Google Scholar
    • 60. R. Kotikalapudi et al., keras-vis (2017), Google Scholar
    • 61. Y.-L. Boureau, J. Ponce and Y. LeCun, A theoretical analysis of feature pooling in visual recognition, in Proc. 27th Int. Conf. Machine Learning (ICML-10) (2010), pp. 111–118. Google Scholar
    • 62. D. Salas-Gonzalez, J. M. Górriz, J. Ramírez, M. López, I. A. Illan, F. Segovia, C. G. Puntonet and M. Gómez-Río, Analysis of SPECT brain images for the diagnosis of Alzheimer’s disease using moments and support vector machines, Neurosci. Lett. 461 (2009) 60–64. Crossref, MedlineGoogle Scholar
    • 63. J. M. Górriz, F. Segovia, J. Ramírez, A. Lassl and D. Salas-Gonzalez, GMM based SPECT image classification for the diagnosis of Alzheimer’s disease, Appl. Soft Comput. 11(2) (2011) 2313–2325. CrossrefGoogle Scholar
    • 64. D. Salas-Gonzalez, J. M. Górriz, J. Ramírez, I. A. Illán and E. W. Lang, Linear intensity normalization of FP-CIT SPECT brain images using the α-stable distribution, NeuroImage 65 (2013) 449–455. Crossref, Medline, ISIGoogle Scholar
    • 65. G. Iacca, F. Neri, E. Mininno, Y.-S. Ong and M.-H. Lim, Ockhams razor in memetic computing: Three stage optimal memetic exploration, Inf. Sci. 188 (2012) 17–43. Crossref, ISIGoogle Scholar
    • 66. L. Pan, G. Păun, G. Zhang and F. Neri, Spiking neural P systems with communication on request, Int. J. Neural Syst. 27(8) (2017) 1750042. Link, ISIGoogle Scholar
    • 67. S. S. Keller and N. Roberts, Voxel-based morphometry of temporal lobe epilepsy: An introduction and review of the literature, Epilepsia 49(5) (2008) 741–757. Crossref, MedlineGoogle Scholar
    Published: 12 September 2018
    Remember to check out the Most Cited Articles!

    Check out our titles in neural networks today!