Linked Life Data

19481161

Source:http://linkedlifedata.com/resource/pubmed/id/19481161

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
1
pubmed:dateCreated
2009-8-11
pubmed:abstractText
Structural and functional brain images are playing an important role in helping us understand the changes associated with neurological disorders such as Alzheimer's disease (AD). Recent efforts have now started investigating their utility for diagnosis purposes. This line of research has shown promising results where methods from machine learning (such as Support Vector Machines) have been used to identify AD-related patterns from images, for use in diagnosing new individual subjects. In this paper, we propose a new framework for AD classification which makes use of the Linear Program (LP) boosting with novel additional regularization based on spatial "smoothness" in 3D image coordinate spaces. The algorithm formalizes the expectation that since the examples for training the classifier are images, the voxels eventually selected for specifying the decision boundary must constitute spatially contiguous chunks, i.e., "regions" must be preferred over isolated voxels. This prior belief turns out to be useful for significantly reducing the space of possible classifiers and leads to substantial benefits in generalization. In our method, the requirement of spatial contiguity (of selected discriminating voxels) is incorporated within the optimization framework directly. Other methods have made use of similar biases as a pre- or post-processing step, however, our model incorporates this emphasis on spatial smoothness directly into the learning step. We report on extensive evaluations of our algorithm on MR and FDG-PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and discuss the relationship of the classification output with the clinical and cognitive biomarker data available within ADNI.
pubmed:grant
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:chemical
pubmed:status
MEDLINE
pubmed:month
Oct
pubmed:issn
1095-9572
pubmed:author
pubmed:issnType
Electronic
pubmed:day
15
pubmed:volume
48
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
138-49
pubmed:dateRevised
2011-1-25
pubmed:meshHeading
pubmed-meshheading:19481161-Aged, pubmed-meshheading:19481161-Algorithms, pubmed-meshheading:19481161-Alzheimer Disease, pubmed-meshheading:19481161-Brain, pubmed-meshheading:19481161-Databases, Factual, pubmed-meshheading:19481161-Female, pubmed-meshheading:19481161-Fluorodeoxyglucose F18, pubmed-meshheading:19481161-Humans, pubmed-meshheading:19481161-Image Processing, Computer-Assisted, pubmed-meshheading:19481161-Imaging, Three-Dimensional, pubmed-meshheading:19481161-Magnetic Resonance Imaging, pubmed-meshheading:19481161-Male, pubmed-meshheading:19481161-Neuropsychological Tests, pubmed-meshheading:19481161-Organ Size, pubmed-meshheading:19481161-Positron-Emission Tomography, pubmed-meshheading:19481161-Psychiatric Status Rating Scales, pubmed-meshheading:19481161-ROC Curve, pubmed-meshheading:19481161-Sensitivity and Specificity
pubmed:year
2009
pubmed:articleTitle
Spatially augmented LPboosting for AD classification with evaluations on the ADNI dataset.
pubmed:affiliation
Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI 53706, USA. hinrichs@cs.wisc.edu
pubmed:publicationType
Journal Article, Research Support, U.S. Gov't, Non-P.H.S., Research Support, Non-U.S. Gov't, Research Support, N.I.H., Extramural