Nonlinear Graph Fusion for Multi-modal Classification of Alzheimer's Disease

Recent studies have demonstrated that biomarkers from multiple modalities contain complementary information for the diagnosis of Alzheimer's disease AD and its prodromal stage mild cognitive impairment MCI. In order to fuse data from multiple modalities, most previous approaches calculate a mixed kernel or a similarity matrix by linearly combining kernels or similarities from multiple modalities. However, the complementary information from multi-modal data are not necessarily linearly related. In addition, this linear combination is also sensitive to the weights assigned to each modality. In this paper, we propose a nonlinear graph fusion method to efficiently exploit the complementarity in the multi-modal data for the classification of AD. Specifically, a graph is first constructed for each modality individually. Afterwards, a single unified graph is obtained via a nonlinear combination of the graphs in an iterative cross diffusion process. Using the unified graphs, we achieved classification accuracies of 91.8% between AD subjects and normal controls NC, 79.5% between MCI subjects and NC and 60.2% in a three-way classification, which are competitive with state-of-the-art results.

[1]  Daoqiang Zhang,et al.  Manifold regularized multitask feature learning for multimodality disease classification , 2015, Human brain mapping.

[2]  Vikas Singh,et al.  Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population , 2011, NeuroImage.

[3]  Paul M. Thompson,et al.  Multi-source feature learning for joint analysis of incomplete multiple heterogeneous neuroimaging data , 2012, NeuroImage.

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  M. Jorge Cardoso,et al.  Accurate multimodal probabilistic prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment☆ , 2013, NeuroImage: Clinical.

[6]  Daniel Rueckert,et al.  Automatic morphometry in Alzheimer's disease and mild cognitive impairment☆☆☆ , 2011, NeuroImage.

[7]  Daniel Rueckert,et al.  Random forest-based similarity measures for multi-modal classification of Alzheimer's disease , 2013, NeuroImage.

[8]  Judea Pearl,et al.  Chapter 2 – BAYESIAN INFERENCE , 1988 .

[9]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[10]  C. Jack,et al.  Boosting power for clinical trials using classifiers based on multiple biomarkers , 2010, Neurobiology of Aging.

[11]  Dinggang Shen,et al.  Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer's Disease and mild cognitive impairment identification , 2014, NeuroImage.

[12]  Daoqiang Zhang,et al.  Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer's disease , 2012, NeuroImage.

[13]  Vladimir Fonov,et al.  Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge , 2015, NeuroImage.

[14]  Bo Wang,et al.  Unsupervised metric fusion by cross diffusion , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Kathryn Ziegler-Graham,et al.  Forecasting the global burden of Alzheimer’s disease , 2007, Alzheimer's & Dementia.

[16]  Dinggang Shen,et al.  Neurodegenerative disease diagnosis using incomplete multi-modality data via matrix shrinkage and completion , 2014, NeuroImage.

[17]  Daoqiang Zhang,et al.  Multimodal classification of Alzheimer's disease and mild cognitive impairment , 2011, NeuroImage.

[18]  Heikki Huttunen,et al.  Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects , 2015, NeuroImage.