Research ArticleNo Access

Quantifying Differences Between Affine and Nonlinear Spatial Normalization of FP-CIT Spect Images

Department of Signal Theory, Telematics and Communications, University of Granada, Periodista Daniel Saucedo Aranda, 18071 Granada, Spain

E-mail Address: [email protected]

Corresponding author.

Search for more papers by this author

Carmen Jimenez-Mesa

Department of Signal Theory, Telematics and Communications, University of Granada, Periodista Daniel Saucedo Aranda, 18071 Granada, Spain

Search for more papers by this author

Francisco J. Martinez-Murcia

Department of Signal Theory, Telematics and Communications, University of Granada, Periodista Daniel Saucedo Aranda, 18071 Granada, Spain

Search for more papers by this author

Diego Salas-Gonzalez

Department of Signal Theory, Telematics and Communications, University of Granada, Periodista Daniel Saucedo Aranda, 18071 Granada, Spain

Search for more papers by this author

Javier Ramírez

Department of Signal Theory, Telematics and Communications, University of Granada, Periodista Daniel Saucedo Aranda, 18071 Granada, Spain

Search for more papers by this author

, and

Juan M. Górriz

Department of Signal Theory, Telematics and Communications, University of Granada, Periodista Daniel Saucedo Aranda, 18071 Granada, Spain

Department of Psychiatry, University of Cambridge, Herchel Smith Buidling for Brain & Mind Sciences, Forvie Site Robinson Way, Cambridge CB2 0SZ, UK

Search for more papers by this author

https://doi.org/10.1142/S0129065722500198Cited by:12 (Source: Crossref)

Abstract

Spatial normalization helps us to compare quantitatively two or more input brain scans. Although using an affine normalization approach preserves the anatomical structures, the neuroimaging field is more common to find works that make use of nonlinear transformations. The main reason is that they facilitate a voxel-wise comparison, not only when studying functional images but also when comparing MRI scans given that they fit better to a reference template. However, the amount of bias introduced by the nonlinear transformations can potentially alter the final outcome of a diagnosis especially when studying functional scans for neurological disorders like Parkinson’s Disease. In this context, we have tried to quantify the bias introduced by the affine and the nonlinear spatial registration of FP-CIT SPECT volumes of healthy control subjects and patients with PD. For that purpose, we calculated the deformation fields of each participant and applied these deformation fields to a 3D-grid. As the space between the edges of small cubes comprising the grid change, we can quantify which parts from the brain have been enlarged, compressed or just remain the same. When the nonlinear approach is applied, scans from PD patients show a region near their striatum very similar in shape to that of healthy subjects. This artificially increases the interclass separation between patients with PD and healthy subjects as the local intensity is decreased in the latter region, and leads machine learning systems to biased results due to the artificial information introduced by these deformations.

Keywords:

References

1. J. Seibyl et al., Impact of training method on the robustness of the visual assessment of 18f-florbetaben PET scans: Results from a phase-3 study, J. Nucl. Med. 57 (2016) 900–906. Crossref, Medline, Web of Science, Google Scholar
2. R. W. Cox , AFNI: Software for analysis and visualization of functional magnetic resonance neuroimages, Comput. Biomed. Res. 29 (1996) 162–173. Crossref, Medline, Google Scholar
3. M. W. Woolrich et al., Bayesian analysis of neuroimaging data in FSL, NeuroImage 45 (2009) S173–S186. Crossref, Medline, Web of Science, Google Scholar
4. T. J. Hirschauer, H. Adeli and J. A. Buford , Computer-aided diagnosis of Parkinson’s disease using enhanced probabilistic neural network, J. Med. Syst. 39 (2015) 179. Crossref, Medline, Web of Science, Google Scholar
5. 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, Web of Science, Google Scholar
6. S. Bhat, U. R. Acharya, Y. Hagiwara, N. Dadmehr and H. Adeli , Parkinson’s disease: Cause factors, measurable indicators, and early diagnosis, Comput. Biol. Med. 102 (2018) 234–241. Crossref, Medline, Web of Science, Google Scholar
7. M. Ahmadlou, H. Adeli and A. Adeli , Spatiotemporal analysis of relative convergence of EEGs reveals differences between brain dynamics of depressive women and men, Clin. EEG Neurosci. 44 (2013) 175–181. Crossref, Medline, Web of Science, Google Scholar
8. M. Ahmadlou, A. Adeli, R. Bajo and H. Adeli , Complexity of functional connectivity networks in mild cognitive impairment subjects during a working memory task, Clin. Neurophysiol. 125 (2014) 694–702. Crossref, Medline, Web of Science, Google Scholar
9. M. Ahmadlou and H. Adeli , Complexity of weighted graph: A new technique to investigate structural complexity of brain activities with applications to aging and autism, Neurosci. Lett. 650 (2017) 103–108. Crossref, Medline, Web of Science, Google Scholar
10. J. delEtoile and H. Adeli , Graph theory and brain connectivity in Alzheimer’s disease, Neuroscientist 23 (2017) 616–626. Crossref, Medline, Web of Science, Google Scholar
11. J.-S. Kim et al., Intensity based affine registration including feature similarity for spatial normalization, Comput. Biol. Med. 32 (2002) 389–402. Crossref, Medline, Web of Science, Google Scholar
12. J.-F. Mangin et al., Spatial normalization of brain images and beyond, Med. Image Anal. 33 (2016) 127–133. Crossref, Medline, Web of Science, Google Scholar
13. J. Rosenblatt, M. Vink and Y. Benjamini , Revisiting multi-subject random effects in fMRI: Advocating prevalence estimation, NeuroImage 84 (2014) 113–121. Crossref, Medline, Web of Science, Google Scholar
14. R. Heller, Y. Golland, R. Malach and Y. Benjamini , Conjunction group analysis: An alternative to mixed/random effect analysis, NeuroImage 37 (2007) 1178–1185. Crossref, Medline, Web of Science, Google Scholar
15. E. Moulton et al., Comparison of spatial normalization strategies of diffusion MRI data for studying motor outcome in subacute-chronic and acute stroke, NeuroImage 183 (2018) 186–199. Crossref, Medline, Web of Science, Google Scholar
16. D. Castillo-Barnes et al., Autosomal dominantly inherited alzheimer disease: Analysis of genetic subgroups by machine learning, Inf. Fusion 58 (2020) 153–167. Crossref, Medline, Web of Science, Google Scholar
17. A. M. Pietroboni, F. S. di Cola, A. Colombi, T. Carandini, C. Fenoglio, L. Ghezzi, M. A. D. Riz, F. Triulzi, E. Scarpini, A. Padovani and D. Galimberti , CSF $β$ -amyloid predicts early cerebellar atrophy and is associated with a poor prognosis in multiple sclerosis, Mult. Scler. Relat. Disord. 37 (2020) 101462. Crossref, Medline, Web of Science, Google Scholar
18. S. Pirzada et al., Spatial normalization of multiple sclerosis brain MRI data depends on analysis method and software package, Magn. Reson. Imaging 68 (2020) 83–94. Crossref, Medline, Web of Science, Google Scholar
19. K. Ikeda et al., Dopamine transporter imaging in parkinson disease: Progressive changes and therapeutic modification after anti-parkinsonian medications, Intern. Med. 58 (2019) 1665–1672. Crossref, Medline, Web of Science, Google Scholar
20. K. Marek et al., [123i]-CIT SPECT imaging assessment of the rate of Parkinson’s disease progression, Neurology 57 (2001) 2089–2094. Crossref, Medline, Web of Science, Google Scholar
21. J. Dukart et al., Distinct role of striatal functional connectivity and dopaminergic loss in Parkinson’s symptoms, Front. Aging Neurosci. 9 (2017) 151. Crossref, Medline, Web of Science, Google Scholar
22. D. Salas-Gonzalez et al., Building a FP-CIT SPECT brain template using a posterization approach, Neuroinformatics 13 (2015) 391–402. Crossref, Medline, Web of Science, Google Scholar
23. F. J. Martinez-Murcia et al., Parametrization of textural patterns in 123i-ioflupane imaging for the automatic detection of parkinsonism, Med. Phys. 41 (2013) 012502. Crossref, Web of Science, Google Scholar
24. R. Wang et al., Suite PET/CT neuroimaging for the diagnosis of Parkinson’s disease, Nucl. Med. Commun. 38 (2017) 164–169. Crossref, Medline, Web of Science, Google Scholar
25. F. Segovia et al., Multivariate analysis of 18f-DMFP PET data to assist the diagnosis of parkinsonism, Front. Neuroinform. 11 (2017) 23. Crossref, Medline, Web of Science, Google Scholar
26. M. Leming et al., Ensemble deep learning on large, mixed-site fMRI datasets in autism and other tasks, Int. J. Neural Syst. 30 (2020) 2050012. Link, Web of Science, Google Scholar
27. W. Feng et al., Automated MRI-based deep learning model for detection of Alzheimer’s disease process, Int. J. Neural Syst. 30 (2020) 2050032. Link, Web of Science, Google Scholar
28. M. Graña and M. Silva , Impact of machine learning pipeline choices in autism prediction from functional connectivity data, Int. J. Neural Syst. 31 (2021) 2150009. Link, Web of Science, Google Scholar
29. D. Castillo-Barnes et al., Morphological characterization of functional brain imaging by isosurface analysis in Parkinson’s disease, Int. J. Neural Syst. 30 (2020) 2050044. Link, Web of Science, Google Scholar
30. J. Ashburner and K. J. Friston , Unified segmentation, NeuroImage 26 (2005) 839–851. Crossref, Medline, Web of Science, Google Scholar
31. L. Palumbo et al., Evaluation of the intra- and inter-method agreement of brain MRI segmentation software packages: A comparison between SPM12 and FreeSurfer v6.0, Phys. Medica 64 (2019) 261–272. Crossref, Medline, Web of Science, Google Scholar
32. A. Klein et al., Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration, NeuroImage 46 (2009) 786–802. Crossref, Medline, Web of Science, Google Scholar
33. B. Thirion et al., Analysis of a large fMRI cohort: Statistical and methodological issues for group analyses, NeuroImage 35 (2007) 105–120. Crossref, Medline, Web of Science, Google Scholar
34. E. Fedorenko et al., New method for fMRI investigations of language: Defining ROIs functionally in individual subjects, J. Neurophysiol. 104 (2010) 1177–1194. Crossref, Medline, Web of Science, Google Scholar
35. M. R. Sabuncu et al., Function-based intersubject alignment of human cortical anatomy, Cereb. Cortex 20 (2009) 130–140. Crossref, Web of Science, Google Scholar
36. Y.-J. Tsai et al., Effective anatomical priors for emission tomographic reconstruction, J. Med. Biol. Eng. 35 (2015) 52–61. Crossref, Web of Science, Google Scholar
37. N. Eshghi et al., Regional changes in brain 18f-FDG uptake after prophylactic cranial irradiation and chemotherapy in small cell lung cancer may reflect functional changes, J. Nucl. Med. Technol. 46 (2018) 355–358. Crossref, Medline, Web of Science, Google Scholar
38. T. Hastie, R. Tibshirani and J. Friedman , The Elements of Statistical Learning (Springer-Verlag GmbH, New York, 2009). Crossref, Google Scholar
39. K. Friston et al., Classical and Bayesian inference in neuroimaging: Theory, NeuroImage 16 (2002) 465–483. Crossref, Medline, Web of Science, Google Scholar
40. J. Gorriz et al., Statistical agnostic mapping: A framework in neuroimaging based on concentration inequalities, Inf. Fusion 66 (2021) 198–212. Crossref, Web of Science, Google Scholar
41. L. Khedher et al., Early diagnosis of Alzheimer’s disease based on partial least squares, principal component analysis and support vector machine using segmented MRI images, Neurocomputing 151 (2015) 139–150. Crossref, Web of Science, Google Scholar
42. A. Ortiz et al., Ensembles of deep learning architectures for the early diagnosis of the Alzheimer’s disease, Int. J. Neural Syst. 26 (2016) 1650025. Link, Web of Science, Google Scholar
43. A. H. Gee and G. M. Treece , Systematic misregistration and the statistical analysis of surface data, Med. Image Anal. 18 (2014) 385–393. Crossref, Medline, Web of Science, Google Scholar
44. U. R. Acharya, S. Bhat, O. Faust, H. Adeli, E. C.-P. Chua, W. J. E. Lim and J. E. W. Koh , Nonlinear dynamics measures for automated EEG-based sleep stage detection, Eur. Neurol. 74 (2015) 268–287. Crossref, Medline, Web of Science, Google Scholar
45. J. M. Górriz et al., Artificial intelligence within the interplay between natural and artificial computation: Advances in data science, trends and applications, Neurocomputing 410 (2020) 237–270. Crossref, Web of Science, Google Scholar
46. J. Ashburner , A fast diffeomorphic image registration algorithm, NeuroImage 38 (2007) 95–113. Crossref, Medline, Web of Science, Google Scholar
47. V. Frouin, C. Comtat, A. Reilhac and M.-C. Grgoire , Correction of partial-volume effect for pet striatal imaging: Fast implementation and study of robustness, J. Nucl. Med. 43 (2002) 1715–1726. Medline, Web of Science, Google Scholar
48. K. J. Friston et al., Spatial registration and normalization of images, Hum. Brain Mapp. 3(3) (1995) 165–189. Crossref, Web of Science, Google Scholar
49. R. P. Woods et al., Automated image registration: I. general methods and intrasubject, intramodality validation, J. Comput. Assist. Tomogr. 22 (1998) 139–152. Crossref, Medline, Web of Science, Google Scholar
50. K. J. Friston , Statistical Parametric Mapping: The Analysis of Functional Brain Images (Academic PR, Inc., Cambridge, 2006). Google Scholar
51. J. Ashburner and K. J. Friston , Diffeomorphic registration using geodesic shooting and gauss-newton optimisation, NeuroImage 55 (2011) 954–967. Crossref, Medline, Web of Science, Google Scholar
52. J. Ashburner and K. J. Friston , Nonlinear spatial normalization using basis functions, Hum. Brain Mapp. 7(4) (1999) 254–266. Crossref, Medline, Web of Science, Google Scholar
53. W. Press et al., Numerical Recipes in Fortran 77, Fortran Numerical Recipes: The Art of Scientific Computing, Vol. 1 (Cambridge University Press, Cambridge, 1992). Google Scholar
54. B. Avants, C. Epstein, M. Grossman and J. Gee , Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain, Med. Image Anal. 12 (2008) 26–41. Crossref, Medline, Web of Science, Google Scholar
55. B. B. Avants, N. J. Tustison, M. Stauffer, G. Song, B. Wu and J. C. Gee , The insight toolKit image registration framework, Front. Neuroinform. 8 (2014) 44. Crossref, Medline, Web of Science, Google Scholar
56. M. Jenkinson, C. F. Beckmann, T. E. Behrens, M. W. Woolrich and S. M. Smith , FSL, Neuro Image 62 (2012) 782–790. Crossref, Medline, Web of Science, Google Scholar
57. S. Gorthi et al., Active deformation fields: Dense deformation field estimation for atlas-based segmentation using the active contour framework, Med. Image Anal. 15 (2011) 787–800. Crossref, Medline, Web of Science, Google Scholar
58. H. Edelsbrunner and E. P. Mcke , Three-dimensional alpha shapes, ACM Trans. Graph. 13 (1994) 43–72. Crossref, Web of Science, Google Scholar
59. X. Xu and K. Harada , Automatic surface reconstruction with alpha-shape method, Vis. Comput. 19 (2003) 431–443. Crossref, Web of Science, Google Scholar
60. N. Tzourio-Mazoyer et al., Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain, NeuroImage 15 (2002) 273–289. Crossref, Medline, Web of Science, Google Scholar
61. N. Mohd Razali and B. Yap , Power comparisons of shapiro-wilk, kolmogorov-smirnov, lilliefors and anderson-darling tests, J. Stat. Model. Anal. 2 (2011) 21–33. Google Scholar
62. H. Mann and D. Whitney , On a test of whether one of two random variables is stochastically larger than the other, Ann. Math. Stat. 18(1) (1947) 50–60. Crossref, Web of Science, Google Scholar
63. M. M. Chakravarty et al., Towards a validation of atlas warping techniques, Med. Image Anal. 12 (2008) 713–726. Crossref, Medline, Web of Science, Google Scholar
64. J. Blesa , Inter-hemispheric asymmetry of nigrostriatal dopaminergic lesion: A possible compensatory mechanism in Parkinson’s disease, Front. Syst. Neurosci. 5 (2011) 92. Crossref, Medline, Google Scholar
65. K. J. Friston et al., Statistical parametric maps in functional imaging: A general linear approach, Hum. Brain Mapp. 2(4) (1994) 189–210. Crossref, Google Scholar
66. A. Eloyan, H. Shou, R. T. Shinohara, E. M. Sweeney, M. B. Nebel, J. L. Cuzzocreo, P. A. Calabresi, D. S. Reich, M. A. Lindquist and C. M. Crainiceanu , Health effects of lesion localization in multiple sclerosis: Spatial registration and confounding adjustment, PLoS One 9 (2014) e107263. Crossref, Medline, Web of Science, Google Scholar
67. M. Reuter, M. D. Tisdall, A. Qureshi, R. L. Buckner, A. J. van der Kouwe and B. Fischl , Head motion during MRI acquisition reduces gray matter volume and thickness estimates, NeuroImage 107 (2015) 107–115. Crossref, Medline, Web of Science, Google Scholar
68. S. Ewert, A. Horn, F. Finkel, N. Li, A. A. Kühn and T. M. Herrington , Optimization and comparative evaluation of nonlinear deformation algorithms for atlas-based segmentation of DBS target nuclei, NeuroImage 184 (2019) 586–598. Crossref, Medline, Web of Science, Google Scholar
69. A. Horn , The impact of modern-day neuroimaging on the field of deep brain stimulation, Curr. Opin. Neurol. 32 (2019) 511–520. Crossref, Medline, Web of Science, Google Scholar
70. T. Schnecker et al., Automated optimization of subcortical cerebral MR imaging-atlas coregistration for improved postoperative electrode localization in deep brain stimulation, Am. J. Neuroradiol. 30 (2009) 1914–1921. Crossref, Medline, Web of Science, Google Scholar
71. A. Horn et al., Toward an electrophysiological “sweet spot” for deep brain stimulation in the subthalamic nucleus, Hum. Brain Mapp. 38(7) (2017) 3377–3390. Crossref, Medline, Web of Science, Google Scholar
72. Y. Xiao, V. Fonov, S. Bériault, F. A. Subaie, M. M. Chakravarty, A. F. Sadikot, G. B. Pike and D. L. Collins , Multi-contrast unbiased MRI atlas of a Parkinson’s disease population, Int. J. Comput. Assist. Radiol. Surg. 10 (2014) 329–341. Crossref, Medline, Web of Science, Google Scholar
73. O. M. Manzanera et al., Scaled subprofile modeling and convolutional neural networks for the identification of Parkinson’s disease in 3D nuclear imaging data, Int. J. Neural Syst. 29 (2019) 1950010. Link, Web of Science, Google Scholar
74. P. Peng et al., A deep fourier neural network for seizure prediction using convolutional neural network and ratios of spectral power, Int. J. Neural Syst. 31(8) (2021) 2150022. Link, Web of Science, Google Scholar
75. F. J. Martinez-Murcia et al., Convolutional neural networks for neuroimaging in parkinson’s disease: Is preprocessing needed? Int. J. Neural Syst. 28 (2018) 1850035. Link, Web of Science, Google Scholar