1
|
Schrouff J, Monteiro JM, Portugal L, Rosa MJ, Phillips C, Mourão-Miranda J. Embedding Anatomical or Functional Knowledge in Whole-Brain Multiple Kernel Learning Models. Neuroinformatics 2018; 16:117-143. [PMID: 29297140 PMCID: PMC5797202 DOI: 10.1007/s12021-017-9347-8] [Citation(s) in RCA: 41] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022]
Abstract
Pattern recognition models have been increasingly applied to neuroimaging data over the last two decades. These applications have ranged from cognitive neuroscience to clinical problems. A common limitation of these approaches is that they do not incorporate previous knowledge about the brain structure and function into the models. Previous knowledge can be embedded into pattern recognition models by imposing a grouping structure based on anatomically or functionally defined brain regions. In this work, we present a novel approach that uses group sparsity to model the whole brain multivariate pattern as a combination of regional patterns. More specifically, we use a sparse version of Multiple Kernel Learning (MKL) to simultaneously learn the contribution of each brain region, previously defined by an atlas, to the decision function. Our application of MKL provides two beneficial features: (1) it can lead to improved overall generalisation performance when the grouping structure imposed by the atlas is consistent with the data; (2) it can identify a subset of relevant brain regions for the predictive model. In order to investigate the effect of the grouping in the proposed MKL approach we compared the results of three different atlases using three different datasets. The method has been implemented in the new version of the open-source Pattern Recognition for Neuroimaging Toolbox (PRoNTo).
Collapse
Affiliation(s)
- Jessica Schrouff
- Laboratory of Behavioral and Cognitive Neuroscience, Stanford University, Stanford, CA, USA.
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.
- GIGA Research, University of Liège, Liège, Belgium.
| | - J M Monteiro
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Max Planck UCL Centre for Computational Psychiatry and Ageing Research, University College London, UK
| | - L Portugal
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Department of Physiology and Pharmacology, Federal Fluminense University, Niterói, RJ, Brazil
| | - M J Rosa
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Max Planck UCL Centre for Computational Psychiatry and Ageing Research, University College London, UK
| | - C Phillips
- GIGA Research, University of Liège, Liège, Belgium
- Department of Electrical Engineering and Computer Science, University of Liège, Liège, Belgium
| | - J Mourão-Miranda
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Max Planck UCL Centre for Computational Psychiatry and Ageing Research, University College London, UK
| |
Collapse
|
2
|
Vincent M, Pedra E, Mourão-Miranda J, Bramati IE, Henrique AR, Moll J. Enhanced Interictal Responsiveness of the Migraineous Visual Cortex to Incongruent Bar Stimulation: A Functional MRI Visual Activation Study. Cephalalgia 2016; 23:860-8. [PMID: 14616927 DOI: 10.1046/j.1468-2982.2003.00609.x] [Citation(s) in RCA: 63] [Impact Index Per Article: 7.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
Abstract
Since visual aura is usually described as expanding zigzag lines, neurones involved with the perception of line orientation may initiate this phenomenon. A visual incongruent line stimulation protocol was developed to obtain functional magnetic resonance images (fMRI) interictally in 5 female migraine patients with typical fortification spectra and in 5 normal matched controls. Activation in the visual cortex was present contralateral to the side of stimulation in 4 of 5 patients, notably in the extrastriate visual cortex. In 4 of 5 controls activation was observed in the medial and anterior orbitofrontal cortex. In one of them additional activation at the right nucleus accumbens/ventral striatum and right ventral pallidum was present. In the remaining control subject activation was present in the left primary visual cortex. The enhanced interictal reactivity of the visual cortex in migraineurs supports the hypothesis of abnormal cortical excitability as an important pathophysiological mechanism in migraine aura, though the role of specific regions of the visual cortex remains to be explored.
Collapse
Affiliation(s)
- M Vincent
- Department of Neurology, Hospital Universitário Clementino Fraga Filho, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil.
| | | | | | | | | | | |
Collapse
|
3
|
Abstract
In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these allow an increased sensitivity for the detection of spatially distributed effects compared to univariate techniques, they lack an established and accessible software framework. The goal of this work was to build a toolbox comprising all the necessary functionalities for multivariate analyses of neuroimaging data, based on machine learning models. The “Pattern Recognition for Neuroimaging Toolbox” (PRoNTo) is open-source, cross-platform, MATLAB-based and SPM compatible, therefore being suitable for both cognitive and clinical neuroscience research. In addition, it is designed to facilitate novel contributions from developers, aiming to improve the interaction between the neuroimaging and machine learning communities. Here, we introduce PRoNTo by presenting examples of possible research questions that can be addressed with the machine learning framework implemented in PRoNTo, and cannot be easily investigated with mass univariate statistical analysis.
Collapse
Affiliation(s)
- J. Schrouff
- Cyclotron Research Centre, University of Liège, Liège, Belgium
| | - M. J. Rosa
- Department of Computer Science, Centre for Computational Statistics and Machine Learning, University College London, Gower Street, WC1E 6BT London, UK
| | - J. M. Rondina
- Department of Computer Science, Centre for Computational Statistics and Machine Learning, University College London, Gower Street, WC1E 6BT London, UK
- Neuroimaging Laboratory, Department and Institute of Psychiatry, Faculty of Medicine, University of São Paulo, São Paulo, Brazil
| | - A. F. Marquand
- Department of Neuroimaging, Centre for Neuroimaging Sciences, Institute of Psychiatry, King’s College London, London, UK
| | - C. Chu
- Section on Functional Imaging Methods, Laboratory of Brain and Cognition, NIMH, NIH, Bethesda, USA
| | - J. Ashburner
- Wellcome Trust Centre for NeuroImaging, University College London, London, UK
| | - C. Phillips
- Cyclotron Research Centre, University of Liège, Liège, Belgium
- Department of Electrical Engineering and Computer Science, University of Liège, Liège, Belgium
| | - J. Richiardi
- Functional Imaging in Neuropsychiatric Disorders Lab, Department of Neurology and Neurological Sciences, Stanford University, Stanford, USA
- Laboratory for Neurology & Imaging of Cognition, Departments of Neurosciences and Clinical Neurology, University of Geneva, Geneva, Switzerland
| | - J. Mourão-Miranda
- Department of Computer Science, Centre for Computational Statistics and Machine Learning, University College London, Gower Street, WC1E 6BT London, UK
- Department of Neuroimaging, Centre for Neuroimaging Sciences, Institute of Psychiatry, King’s College London, London, UK
| |
Collapse
|
4
|
Evans S, Kyong JS, Rosen S, Golestani N, Warren JE, McGettigan C, Mourão-Miranda J, Wise RJS, Scott SK. The pathways for intelligible speech: multivariate and univariate perspectives. Cereb Cortex 2013; 24:2350-61. [PMID: 23585519 PMCID: PMC4128702 DOI: 10.1093/cercor/bht083] [Citation(s) in RCA: 59] [Impact Index Per Article: 5.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022] Open
Abstract
An anterior pathway, concerned with extracting meaning from sound, has been identified in nonhuman primates. An analogous pathway has been suggested in humans, but controversy exists concerning the degree of lateralization and the precise location where responses to intelligible speech emerge. We have demonstrated that the left anterior superior temporal sulcus (STS) responds preferentially to intelligible speech (Scott SK, Blank CC, Rosen S, Wise RJS. 2000. Identification of a pathway for intelligible speech in the left temporal lobe. Brain. 123:2400–2406.). A functional magnetic resonance imaging study in Cerebral Cortex used equivalent stimuli and univariate and multivariate analyses to argue for the greater importance of bilateral posterior when compared with the left anterior STS in responding to intelligible speech (Okada K, Rong F, Venezia J, Matchin W, Hsieh IH, Saberi K, Serences JT,Hickok G. 2010. Hierarchical organization of human auditory cortex: evidence from acoustic invariance in the response to intelligible speech. 20: 2486–2495.). Here, we also replicate our original study, demonstrating that the left anterior STS exhibits the strongest univariate response and, in decoding using the bilateral temporal cortex, contains the most informative voxels showing an increased response to intelligible speech. In contrast, in classifications using local “searchlights” and a whole brain analysis, we find greater classification accuracy in posterior rather than anterior temporal regions. Thus, we show that the precise nature of the multivariate analysis used will emphasize different response profiles associated with complex sound to speech processing.
Collapse
Affiliation(s)
- S Evans
- Institute of Cognitive Neuroscience, MRC Cognition and Brain Sciences Unit, Cambridge CB2 7EF, UK
| | - J S Kyong
- Department of Speech, Hearing and Phonetic Sciences
| | - S Rosen
- Department of Speech, Hearing and Phonetic Sciences
| | - N Golestani
- Institute of Cognitive Neuroscience, Department of Clinical Neuroscience, University Medical School, Geneva CH-1211, Switzerland
| | - J E Warren
- Computational, Cognitive and Clinical Neuroimaging Laboratory, Imperial College London, London W12 0NN, UK
| | - C McGettigan
- Institute of Cognitive Neuroscience, Department of Psychology, Royal Holloway University, University of London, Egham TW20 0EX, UK and
| | - J Mourão-Miranda
- Department of Computer Science, Centre for Computational Statistics and Machine Learning, University College London, London WC1E 6BT, UK Centre for Neuroimaging Sciences, Institute of Psychiatry, King's College, London SE5 8AF, UK
| | - R J S Wise
- Computational, Cognitive and Clinical Neuroimaging Laboratory, Imperial College London, London W12 0NN, UK
| | | |
Collapse
|
5
|
Filippone M, Marquand AF, Blain CRV, Williams SCR, Mourão-Miranda J, Girolami M. PROBABILISTIC PREDICTION OF NEUROLOGICAL DISORDERS WITH A STATISTICAL ASSESSMENT OF NEUROIMAGING DATA MODALITIES. Ann Appl Stat 2012; 6:1883-1905. [PMID: 24523851 DOI: 10.1214/12-aoas562] [Citation(s) in RCA: 30] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
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.
Collapse
Affiliation(s)
- M Filippone
- School of Computing Science, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - A F Marquand
- Institute of Psychiatry, King's College London, London, United Kingdom
| | - C R V Blain
- Institute of Psychiatry, King's College London, London, United Kingdom
| | - S C R Williams
- Institute of Psychiatry, King's College London, London, United Kingdom
| | - J Mourão-Miranda
- University College and King's College London, London, United Kingdom
| | - M Girolami
- Department of Satistical Science, Centre for Computational Statistics and Machine Learning, University College London, London, United Kingdom
| |
Collapse
|
6
|
Mourão-Miranda J, Volchan E, Moll J, de Oliveira-Souza R, Oliveira L, Bramati I, Gattass R, Pessoa L. Contributions of stimulus valence and arousal to visual activation during emotional perception. Neuroimage 2004; 20:1955-63. [PMID: 14683701 DOI: 10.1016/j.neuroimage.2003.08.011] [Citation(s) in RCA: 79] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022] Open
Abstract
Neuroimaging experiments have revealed that the visual cortex is involved in the processing of affective stimuli: seeing emotional pictures leads to greater activation than seeing neutral ones. It is unclear, however, whether such differential activation is due to stimulus valence or whether the results are confounded by arousal level. In order to investigate the contributions of valence and arousal to visual activation, we created a new category of "interesting" stimuli designed to have high arousal, but neutral valence, and employed standard neutral, unpleasant, and pleasant picture categories. Arousal ratings for pleasant and neutral pictures were equivalent, as were valence ratings for interesting and neutral pictures. Differential activation for conditions matched for arousal (pleasant vs neutral) as well as matched for valence (interesting vs neutral) indicated that both stimulus valence and arousal contributed to visual activation.
Collapse
Affiliation(s)
- J Mourão-Miranda
- Institute of Biophysics Carlos Chagas Filho, Federal University of Rio de Janeiro, Brazil
| | | | | | | | | | | | | | | |
Collapse
|