Please use this identifier to cite or link to this item:
https://olympias.lib.uoi.gr/jspui/handle/123456789/10940Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Lukic, A. S. | en |
| dc.contributor.author | Wernick, M. N. | en |
| dc.contributor.author | Tzikas, D. G. | en |
| dc.contributor.author | Chen, X. | en |
| dc.contributor.author | Likas, A. | en |
| dc.contributor.author | Galatsanos, N. P. | en |
| dc.contributor.author | Yang, Y. Y. | en |
| dc.contributor.author | Zhao, F. | en |
| dc.contributor.author | Strother, S. C. | en |
| dc.date.accessioned | 2015-11-24T17:01:32Z | - |
| dc.date.available | 2015-11-24T17:01:32Z | - |
| dc.identifier.issn | 0278-0062 | - |
| dc.identifier.uri | https://olympias.lib.uoi.gr/jspui/handle/123456789/10940 | - |
| dc.rights | Default Licence | - |
| dc.subject | functional neuroimaging | en |
| dc.subject | kernel methods | en |
| dc.subject | relevance vector machine (rvm) | en |
| dc.subject | reversible-jump markov-chain monte-carlo (rjmcmc) | en |
| dc.subject | magnetic-resonance images | en |
| dc.subject | chain monte-carlo | en |
| dc.subject | fmri data | en |
| dc.subject | statistical-analysis | en |
| dc.subject | brain | en |
| dc.subject | activation | en |
| dc.subject | maps | en |
| dc.subject | model | en |
| dc.subject | resolution | en |
| dc.subject | machine | en |
| dc.title | Bayesian kernel methods for analysis of functional neuroimages | en |
| heal.type | journalArticle | - |
| heal.type.en | Journal article | en |
| heal.type.el | Άρθρο Περιοδικού | el |
| heal.identifier.primary | Doi 10.1109/Tmi.2007.896934 | - |
| heal.language | en | - |
| heal.access | campus | - |
| heal.recordProvider | Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικής | el |
| heal.publicationDate | 2007 | - |
| heal.abstract | We propose an approach to analyzing functional neuroimages in which 1) regions of neuronal activation are described by a superposition of spatial kernel functions, the parameters of which are estimated from the data and 2) the presence of activation is detected by means of a generalized likelihood ratio test (GLRT). Kernel methods have become a staple of modern machine learning. Herein, we show that these techniques show promise for neuroimage analysis. In an on-off design, we model the spatial activation pattern as a sum of an unknown number of kernel functions of unknown location, amplitude, and/or size. We employ two Bayesian methods of estimating the kernel functions. The first is a maximum a posteriori (MAP) estimation method based on a Reversible-Jump Markov-chain Monte-Carlo (RJMCMC) algorithm that searches for both the appropriate model complexity and parameter values. The second is a relevance vector machine (RVM), a kernel machine that is known to be effective in controlling model complexity (and thus discouraging overfitting). In each method, after estimating the activation pattern, we test for local activation using a GLRT. We evaluate the results using receiver operating characteristic (ROC) curves for simulated neuroimaging data and example results for real fMRI data. We find that, while RVM and RJMCMC both produce good results, RVM requires far less computation time, and thus appears to be the more promising of the two approaches. | en |
| heal.journalName | IEEE Trans Med Imaging | en |
| heal.journalType | peer reviewed | - |
| heal.fullTextAvailability | TRUE | - |
| Appears in Collections: | Άρθρα σε επιστημονικά περιοδικά ( Ανοικτά) | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Likas-2007-Bayesian kernel methods for analysis of functional neuroimages.pdf | 3.23 MB | Adobe PDF | View/Open Request a copy |
This item is licensed under a Creative Commons License
