Bayesian kernel methods for analysis of functional neuroimages.

Bayesian kernel methods for analysis of functional neuroimages. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Bayesian kernel methods for analysis of functional neuroimages. Abstract Text:

Ana S Lukic,Miles N Wernick,Dimitris G Tzikas,Xu Chen,Aristidis Likas,Nikolas P Galatsanos,Yongyi Yang,Fuqiang Zhao,Stephen C Strother,

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.

Bayesian kernel methods for analysis of functional neuroimages. Publishing Authors By Initials

AS Lukic,MN Wernick,DG Tzikas,X Chen,A Likas,NP Galatsanos,Y Yang,F Zhao,SC Strother,

For similar abstracts research abstracts see: abstracts research

PUBMED ID PMID:

MEDLINE DATE:

Bayesian kernel methods for analysis of functional neuroimages. Journal Published:

PUBLICATION TYPE: Research Support, N.I.H., Extr

Journal: IEEE transactions on medical imaging

VOLUME: 26

Page Numbers: 1613-24

Journal Abbreviation:

ISSN: 0278-0062

DAY: 20

MONTH: Dec

YEAR: 2007

Bayesian kernel methods for analysis of functional neuroimages. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 8310780

Bayesian kernel methods for analysis of functional neuroimages. Keywords Mesh Terms:

KEYWORDS:

MESH TERMS:

Chemical & Substance for Abstract: Bayesian kernel methods for analysis of functional neuroimages. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Bayesian kernel methods for analysis of functional neuroimages.

AFFILIATION: Department of Biomedical Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA.

Country: United States

AGENCY: United States NINDS

GRANT: NS35273

ACRONYM: NS

MEDLINETA: IEEE Trans Med Imaging

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Bayesian kernel methods for analysis of functional neuroimages Related Publications

• A technique for improved quantitative characterization of intracranial aneurysms.
• Angiographic and histological comparison of canine bifurcation aneurysms treated with first generation matrix and standard GDC coils.
• Anomalous origin of the posterior inferior cerebellar artery from the internal carotid artery.
• Atypical teratoid rhabdoid tumors of childhood: diagnosis, treatment and challenges.
• Bayesian kernel methods for analysis of functional neuroimages.
• CT angiographic appearance of in-stent restenosis of intracranial arteries treated with the Wingspan stent.
• Comparison of platinum and first-generation Matrix coils in under-packed canine side-wall aneurysms: evaluation of progressive thrombosis.
• Continued progress in the evolution of endovascular therapy.
• Does reduction in vascular trauma during treatment of acutely ruptured saccular aneurysms reduce the incidence of vasospasm?
• Effect of Guglielmi detachable coil placement on intraaneurysmal pressure: experimental study in canines.
• Effect of Guglielmi detachable coils on intraaneurysmal flow: experimental study in canines.
• Effect of carotid artery stenting on cognitive function in patients with carotid artery stenosis: preliminary results.
• Effect of spatial alignment transformations in PCA and ICA of functional neuroimages.
• Endovascular treatment of high-flow carotid cavernous fistulas by stent-assisted coil placement.
• Hemodynamic versus hydrodynamic effects of Guglielmi detachable coils on intra-aneurysmal pressure and flow at varying pulse rate and systemic pressure.
• Highlights of the 30th Annual Meeting of the American Society of Neuroradiology.
• Intra-arterial thrombolysis for the treatment of patients with acute ischemic stroke.
• Intraoperative sonographic assessment of graft patency during extracranial-intracranial bypass.
• Measuring intraaneurysmal flow: risk of perforation.
• Osmotic disruption of the blood-ocular barriers.
• Practical tradeoffs between noise, quantitation, and number of iterations for maximum likelihood-based reconstructions.
• Spontaneous thrombosis of a traumatic posterior cerebral artery aneurysm in a child.
• The role of muscle action in interpretative reading.
• Thirty-ninth annual meeting of the American Society of Neuroradiology.
• Thirty-seventh annual meeting of the American Society of Neuroradiology.
• Training, experience, and evidence matter.
• Transcranial Doppler sonography: adding to the toolbox.
• Treatment of carotid artery aneurysms with platinum coils: an experimental study in dogs.
• Utility of CT angiography and MR angiography for the follow-up of experimental aneurysms treated with stents or Guglielmi detachable coils.
• Wall Shear Stress Variations in Basilar Tip Aneurysms investigated with Computational Fluid Dynamics.