Graph Based Classification of MRI Data Based on the Ventricular System

The ventricular system inside the brain is known to enlarge and change shape given conditions such as Alzheimer's disease. This change in shape may provide a way to assess the level of cognitive impairment of a patient, as well as other intellectual characteristics. This paper describes the use of trees to represent the 3D space containing the third and lateral ventricles, and classification of these trees using frequent sub graph mining and support vector machines. Level of cognitive impairment and years of education are shown to be predictable given a tree representation of the shape of the third and lateral ventricles, demonstrating that the shape of the ventricular system correlates with these attributes. These results were generated using a cross-sectional collection of 416 MR images of subjects ranging in age from 18 to 96 years, including 100 subjects diagnosed with Alzheimer's disease.

[1]  R. Bartha,et al.  Ventricular enlargement as a possible measure of Alzheimer's disease progression validated using the Alzheimer's disease neuroimaging initiative database. , 2008, Brain : a journal of neurology.

[2]  Tom M. Mitchell,et al.  Learning to Decode Cognitive States from Brain Images , 2004, Machine Learning.

[3]  Frans Coenen,et al.  Corpus callosum MR image classification , 2010, Knowl. Based Syst..

[4]  K. Jarrod Millman,et al.  Analysis of Functional Magnetic Resonance Imaging in Python , 2007, Computing in Science & Engineering.

[5]  Eileen Crimmins,et al.  Education and Cognitive Decline in Older Americans , 2007, Research on aging.

[6]  O. Sporns,et al.  Complex brain networks: graph theoretical analysis of structural and functional systems , 2009, Nature Reviews Neuroscience.

[7]  R S Wilson,et al.  Education and the course of cognitive decline in Alzheimer disease , 2004, Neurology.

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  Joost N. Kok,et al.  A quickstart in frequent structure mining can make a difference , 2004, KDD.

[10]  Lawrence B. Holder,et al.  Graph-Based Data Mining , 2000, IEEE Intell. Syst..

[11]  Marco Gori,et al.  Similarity learning for graph-based image representations , 2003, Pattern Recognit. Lett..

[12]  T. C. Chang,et al.  Graph-based heuristics for recognition of machined features from a 3D solid model , 1988 .

[13]  John G. Csernansky,et al.  Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults , 2007, Journal of Cognitive Neuroscience.

[14]  Lawrence B. Holder,et al.  Using Graphs to Improve Activity Prediction in Smart Environments Based on Motion Sensor Data , 2011, ICOST.

[15]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[16]  Thomas Gärtner,et al.  On Graph Kernels: Hardness Results and Efficient Alternatives , 2003, COLT.

[17]  George Karypis,et al.  Frequent Substructure-Based Approaches for Classifying Chemical Compounds , 2005, IEEE Trans. Knowl. Data Eng..

[18]  F Makedon,et al.  Statistical Methods in Medical Research Data Mining in Brain Imaging , 2022 .

[19]  P. Thiran,et al.  Mapping Human Whole-Brain Structural Networks with Diffusion MRI , 2007, PloS one.

[20]  Frans Coenen,et al.  Region of Interest Based Image Classification using time series analysis , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[21]  Jiawei Han,et al.  gSpan: graph-based substructure pattern mining , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[22]  G. Cecchi,et al.  Scale-free brain functional networks. , 2003, Physical review letters.