The Annals of Applied Statistics

Probabilistic prediction of neurological disorders with a statistical assessment of neuroimaging data modalities

M. Filippone, A. F. Marquand, C. R. V. Blain, S. C. R. Williams, J. Mourão-Miranda, and M. Girolami

Full-text: Open access

Abstract

For many neurological disorders, prediction of disease state is an important clinical aim. Neuroimaging provides detailed information about brain structure and function from which such predictions may be statistically derived. A multinomial logit model with Gaussian process priors is proposed to: (i) predict disease state based on whole-brain neuroimaging data and (ii) analyze the relative informativeness of different image modalities and brain regions. Advanced Markov chain Monte Carlo methods are employed to perform posterior inference over the model. This paper reports a statistical assessment of multiple neuroimaging modalities applied to the discrimination of three Parkinsonian neurological disorders from one another and healthy controls, showing promising predictive performance of disease states when compared to nonprobabilistic classifiers based on multiple modalities. The statistical analysis also quantifies the relative importance of different neuroimaging measures and brain regions in discriminating between these diseases and suggests that for prediction there is little benefit in acquiring multiple neuroimaging sequences. Finally, the predictive capability of different brain regions is found to be in accordance with the regional pathology of the diseases as reported in the clinical literature.

Article information

Source
Ann. Appl. Stat., Volume 6, Number 4 (2012), 1883-1905.

Dates
First available in Project Euclid: 27 December 2012

Permanent link to this document
https://projecteuclid.org/euclid.aoas/1356629064

Digital Object Identifier
doi:10.1214/12-AOAS562

Mathematical Reviews number (MathSciNet)
MR3058687

Zentralblatt MATH identifier
1257.62103

Keywords
Multi-modality multinomial logit model Gaussian process hierarchical model high-dimensional data Markov chain Monte Carlo Parkinsonian diseases prediction of disease state

Citation

Filippone, M.; Marquand, A. F.; Blain, C. R. V.; Williams, S. C. R.; Mourão-Miranda, J.; Girolami, M. Probabilistic prediction of neurological disorders with a statistical assessment of neuroimaging data modalities. Ann. Appl. Stat. 6 (2012), no. 4, 1883--1905. doi:10.1214/12-AOAS562. https://projecteuclid.org/euclid.aoas/1356629064


Export citation

References

  • Basser, P. J. and Jones, D. K. (2002). Diffusion-tensor MRI: Theory, experimental design and data analysis—a technical review. NMR Biomed. 15 456–467.
  • Blain, C. R. V., Barker, G. J., Jarosz, J. M., Coyle, N. A., Landau, S., Brown, R. G., Chaudhuri, K. R., Simmons, A., Jones, D. K., Williams, S. C. R. and Leigh, P. N. (2006). Measuring brain stem and cerebellar damage in Parkinsonian syndromes using diffusion tensor MRI. Neurology 67 2199–2205.
  • Cuingnet, R., Gerardin, E., Tessieras, J., Auzias, G., Lehéricy, S., Habert, M.-O. O., Chupin, M., Benali, H. and Colliot, O. (2011). Automatic classification of patients with Alzheimer’s disease from structural MRI: A comparison of ten methods using the ADNI database. NeuroImage 56 766–781.
  • Farrall, A. J. (2006). Magnetic resonance imaging. Practical Neurology 6 318–325.
  • Filippone, M., Zhong, M. and Girolami, M. (2012). On the fully Bayesian treatment of latent Gaussian models using stochastic simulations. Technical Report TR-2012-329, School of Computing Science, Univ. Glasgow.
  • Focke, N. K., Helms, G., Scheewe, S., Pantel, P. M., Bachmann, C. G., Dechent, P., Ebentheuer, J., Mohr, A., Paulus, W. and Trenkwalder, C. (2011). Individual voxel-based subtype prediction can differentiate progressive supranuclear palsy from idiopathic Parkinson syndrome and healthy controls. Hum. Brain Mapp. 32 1905–1915.
  • Gelman, A. and Rubin, D. B. (1992). Inference from iterative simulation using multiple sequences. Statist. Sci. 7 457–472.
  • Geweke, J. (2004). Getting it right: Joint distribution tests of posterior simulators. J. Amer. Statist. Assoc. 99 799–804.
  • Geyer, C. J. (1992). Practical Markov chain Monte Carlo. Statist. Sci. 7 473–483.
  • Girolami, M. and Calderhead, B. (2011). Riemann manifold Langevin and Hamiltonian Monte Carlo methods. J. R. Stat. Soc. Ser. B Stat. Methodol. 73 123–214.
  • Gneiting, T. and Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. J. Amer. Statist. Assoc. 102 359–378.
  • Goel, P. K. and DeGroot, M. H. (1981). Information about hyperparameters in hierarchical models. J. Amer. Statist. Assoc. 76 140–147.
  • Hauw, J. J., Daniel, S. E., Dickson, D., Horoupian, D. S., Jellinger, K., Lantos, P. L., McKee, A., Tabaton, M. and Litvan, I. (1994). Preliminary NINDS neuropathologic criteria for Steele–Richardson–Olszewski syndrome (progressive supranuclear palsy). Neurology 44 2015–2019.
  • Klöppel, S., Stonnington, C. M., Chu, C., Draganski, B., Scahill, R. I., Rohrer, J. D., Fox, N. C., Jack, C. R., Ashburner, J. and Frackowiak, R. S. J. (2008). Automatic classification of MR scans in Alzheimer’s disease. Brain 131 681–689.
  • Lanckriet, G. R. G., Cristianini, N., Bartlett, P., El Ghaoui, L. and Jordan, M. I. (2004). Learning the kernel matrix with semidefinite programming. J. Mach. Learn. Res. 5 27–72.
  • Litvan, I., Bhatia, K. P., Burn, D. J., Goetz, C. G., Lang, A. E., McKeith, I., Quinn, N., Sethi, K. D., Shults, C. and Wenning, G. K. (2003). SIC task force appraisal of clinical diagnostic criteria for Parkinsonian disorders. Mov. Disord. 18 467–486.
  • Marquand, A. F., Mourão-Miranda, J., Brammer, M. J., Cleare, A. J. and Fu, C. H. Y. (2008). Neuroanatomy of verbal working memory as a diagnostic biomarker for depression. Neuroreport 19 1507–1511.
  • Murray, I. and Adams, R. P. (2010). Slice sampling covariance hyperparameters of latent Gaussian models. In Advances in Neural Information Processing Systems 23 (J. Lafferty, C. K. I. Williams, R. Zemel, J. Shawe-Taylor and A. Culotta, eds.) 1723–1731. Curran Associates, Inc.
  • Neal, R. M. (1993). Probabilistic inference using Markov chain Monte Carlo methods. Technical Report CRG-TR-93-1, Dept. of Computer Science, Univ. Toronto.
  • Neal, R. M. (1999). Regression and classification using Gaussian process priors. In Bayesian Statistics 6 (Alcoceber, 1998) 475–501. Oxford Univ. Press, New York.
  • Papaspiliopoulos, O., Roberts, G. O. and Sköld, M. (2007). A general framework for the parametrization of hierarchical models. Statist. Sci. 22 59–73.
  • Rakotomamonjy, A., Bach, F. R., Canu, S. and Grandvalet, Y. (2008). SimpleMKL. J. Mach. Learn. Res. 9 2491–2521.
  • Schölkopf, B. and Smola, A. J. (2001). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge, MA.
  • Seppi, K. (2007). MRI for the differential diagnosis of neurodegenerative Parkinsonism in clinical practice. Parkinsonism and Related Disorders 13 S400–S405.
  • Shattuck, D. W., Mirza, M., Adisetiyo, V., Hojatkashani, C., Salamon, G., Narr, K. L., Poldrack, R. A., Bilder, R. M. and Toga, A. W. (2008). Construction of a 3D probabilistic atlas of human cortical structures. Neuroimage 39 1064–1080.
  • Sonnenburg, S., Rätsch, G., Schäfer, C. and Schölkopf, B. (2006). Large scale multiple kernel learning. J. Mach. Learn. Res. 7 1531–1565.
  • Wenning, G. K., Tison, F., Shlomo, Y. B., Daniel, S. E. and Quinn, N. P. (1997). Multiple system atrophy: A review of 203 pathologically proven cases. Mov. Disord. 12 133–147.
  • Williams, C. K. I. and Barber, D. (1998). Bayesian classification with Gaussian processes. IEEE Transactions on Pattern Analysis and Machine Intelligence 20 1342–1351.
  • Yoshikawa, K., Nakata, Y., Yamada, K. and Nakagawa, M. (2004). Early pathological changes in the Parkinsonian brain demonstrated by diffusion tensor MRI. Journal of Neurology, Neurosurgery and Psychiatry 75 481–484.
  • Yu, Y. and Meng, X.-L. (2011). To center or not to center: That is not the question—an Ancillarity–Sufficiency Interweaving Strategy (ASIS) for boosting MCMC efficiency. J. Comput. Graph. Statist. 20 531–570.