"Spatially augmented LP Boosting for AD classification with evaluations on the ADNI dataset"
Chris Hinrichs, Vikas Singh, Lopamudra Mukherjee, Guofan Xu, Moo K. Chung, Sterling C.
Johnson, and the Alzheimer's Disease Neuroimaging Initiative
Accepted for publication in NeuroImage, 5/18/2009.
Spatially augmented LP Boosting is a machine learning technique with
special adaptations making it specially suited to 3D medical imaging
problems; the algorithm tries to produce a linear classifier which corresponds to "smooth" contiguous regions in the
brain. The "spatial augmentation" is achieved by penalizing certain variations between weights placed on neighboring
voxels concurrently with the rest of the learning phase, i.e., smoothness is injected into the trade-off between
L1-norm sparsity and training set clssification margin, leading to a 3-way trade-off.
This research was supported in part by NIH grants R21-AG034315
(Singh) and R01-AG021155 (Johnson). Hinrichs is funded via a
University of Wisconsin-Madison CIBM (Computation and Informatics
in Biology and Medicine) fellowship (National Library of Medicine
Award 5T15LM007359). Partial support for this research was also
provided by the University of Wisconsin-Madison UW ICTR through an
NIH Clinical and Translational Science Award (CTSA) 1UL1RR025011, a
Merit Review Grant from the Department of Veterans Affairs, the
Wisconsin Comprehensive Memory Program, and the Society for
Imaging Informatics in Medicine (SIIM).
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 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.
The Matlab code used in our experiments can be downloaded here. Please contact me at
email@example.com for the password. All rights reserved.