DuSK: A Dual Structure-preserving Kernel for Supervised Tensor Learning with Applications to Neuroimages

He, Lifang; Kong, Xiangnan; Yu, Philip S.; Ragin, Ann B.; Zhang, Hao; Yang, Xiaowei

doi:10.1137/1.9781611973440.15

Cited by 61 publications

(84 citation statements)

References 19 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, m be a training set of instancelabeled pairs, X i ∈ R n 1 ×n 2 ×···×n N , and y i ∈ {−1, 1}. Given a tensor X i ∈ R n 1 ×n 2 ×···×n N , we assume that it may be mapped into a high dimensional tensor product feature space by a map function φ: X → φ(X) ∈ R h 1 ×h 2 ×···×h P , and then the optimization problem of tensor-based kernel learning may be written as [3]:…”

Section: Tensorial Kernel Functionmentioning

confidence: 99%

Tensorial Kernel Based on Spatial Structure Information for Neuroimaging Classification

Liu

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYRecently, a high dimensional classification framework has been proposed to introduce spatial structure information in classical single kernel support vector machine optimization scheme for brain image analysis. However, during the construction of spatial kernel in this framework, a huge adjacency matrix is adopted to determine the adjacency relation between each pair of voxels and thus it leads to very high computational complexity in the spatial kernel calculation. The method is improved in this manuscript by a new construction of tensorial kernel wherein a 3-order tensor is adopted to preserve the adjacency relation so that calculation of the above huge matrix is avoided, and hence the computational complexity is significantly reduced. The improvement is verified by experimental results on classification of Alzheimer patients and cognitively normal controls.

show abstract

Section: Tensorial Kernel Functionmentioning

confidence: 99%

Tensorial Kernel Based on Spatial Structure Information for Neuroimaging Classification

Liu

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…In [6,8], the neuroimage data are directly mined and represented as tensors to handle extremely high dimensionality within the data. In addition, many efforts have focused on mining important brain regions and estimating region/neuron connections [9,21,25].…”

Section: Related Workmentioning

confidence: 99%

“…The potential of mining the vast image data for the detection of alterations in neurological disorders has been demonstrated in many studies [3,8,15,16,19,24]. However, connectivities of brain regions are not investigated in these studies.…”

Section: Introductionmentioning

confidence: 99%

Identifying Connectivity Patterns for Brain Diseases via Multi-side-view Guided Deep Architectures

Zhang

Cao

Xie

et al. 2016

Proceedings of the 2016 SIAM International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

There is considerable interest in mining neuroimage data to discover clinically meaningful connectivity patterns to inform an understanding of neurological and neuropsychiatric disorders. Subgraph mining models have been used to discover connected subgraph patterns. However, it is difficult to capture the complicated interplay among patterns. As a result, classification performance based on these results may not be satisfactory.To address this issue, we propose to learn non-linear representations of brain connectivity patterns from deep learning architectures. This is non-trivial, due to the limited subjects and the high costs of acquiring the data. Fortunately, auxiliary information from multiple side views such as clinical, serologic, immunologic, cognitive and other diagnostic testing also characterizes the states of subjects from different perspectives. In this paper, we present a novel Multi-side-View guided AutoEncoder (MVAE) that incorporates multiple side views into the process of deep learning to tackle the bias in the construction of connectivity patterns caused by the scarce clinical data. Extensive experiments show that MVAE not only captures discriminative connectivity patterns for classification, but also discovers meaningful information for clinical interpretation.

show abstract

“…A common solution is to focus on the 3D spatial domain of the fMRI brain images [7,12]. For instance, in [12], the original 4D tensor of fMRI data is converted to a 3D tensor by averaging over the time dimension.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, in [12], the original 4D tensor of fMRI data is converted to a 3D tensor by averaging over the time dimension. classification.…”

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Tensor Analysis for Whole-Brain fMRI Classification

Ma¹,

He²,

Lu³

et al. 2016

Proceedings of the 2016 SIAM International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

Owing to prominence as a research and diagnostic tool in human brain mapping, whole-brain fMRI image analysis has been the focus of intense investigation. Conventionally, input fMRI brain images are converted into vectors or matrices and adapted in kernel based classifiers. fMRI data, however, are inherently coupled with sophisticated spatio-temporal tensor structure (i.e., 3D space × time). Valuable structural information will be lost if the tensors are converted into vectors. Furthermore, time series fMRI data are noisy, involving time shift and low temporal resolution. To address these analytic challenges, more compact and discriminative representations for kernel modeling are needed. In this paper, we propose a novel spatio-temporal tensor kernel (STTK) approach for whole-brain fMRI image analysis. Specifically, we design a volumetric time series extraction approach to model the temporal data, and propose a spatio-temporal tensor based factorization for feature extraction. We further leverage the tensor structure to encode prior knowledge in the kernel. Extensive experiments using real-world datasets demonstrate that our proposed approach effectively boosts the fMRI classification performance in diverse brain disorders (i.e., Alzheimer's disease, ADHD and HIV).

show abstract

DuSK: A Dual Structure-preserving Kernel for Supervised Tensor Learning with Applications to Neuroimages

Cited by 61 publications

References 19 publications

Tensorial Kernel Based on Spatial Structure Information for Neuroimaging Classification

Tensorial Kernel Based on Spatial Structure Information for Neuroimaging Classification

Identifying Connectivity Patterns for Brain Diseases via Multi-side-view Guided Deep Architectures

Spatio-Temporal Tensor Analysis for Whole-Brain fMRI Classification

Contact Info

Product

Resources

About