Authors:
Anna C. Carli
1
;
Mario A. T. Figueiredo
2
;
Manuele Bicego
3
and
Vittorio Murino
3
Affiliations:
1
Università di Verona, Italy
;
2
IST-Instituto Superior Técnico e IT-Instituto de Telecomunicações, Portugal
;
3
Università di Verona and Istituto Italiano di Tecnologia (IIT), Italy
Keyword(s):
Discriminative learning, Magnetic resonance images, Generative embedding, Information theory, Kernels, Rice distributions, Finite mixtures, EM algorithm.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Classification
;
Kernel Methods
;
Medical Imaging
;
Pattern Recognition
;
Software Engineering
;
Theory and Methods
Abstract:
Most approaches to classifier learning for structured objects (such as images or sequences) are based on probabilistic
generative models. On the other hand, state-of-the-art classifiers for vectorial data are learned discriminatively.
In recent years, these two dual paradigms have been combined via the use of generative embeddings
(of which the Fisher kernel is arguably the best known example); these embeddings are mappings from the
object space into a fixed dimensional score space, induced by a generative model learned from data, on which
a (maybe kernel-based) discriminative approach can then be used.
This paper proposes a new semi-parametric approach to build generative embeddings for classification of magnetic
resonance images (MRI). Based on the fact that MRI data is well described by Rice distributions, we
propose to use Rician mixtures as the underlying generative model, based on which several different generative
embeddings are built. These embeddings yield vectorial represen
tations on which kernel-based support vector
machines (SVM) can be trained for classification. Concerning the choice of kernel, we adopt the recently
proposed nonextensive information theoretic kernels.
The methodology proposed was tested on a challenging classification task, which consists in classifying MRI
images as belonging to schizophrenic or non-schizophrenic human subjects. The classification is based on
a set of regions of interest (ROIs) in each image, with the classifiers corresponding to each ROI being combined
via boosting. The experimental results show that the proposed methodology outperforms the previous
state-of-the-art methods on the same dataset.
(More)