Frequent and Discriminative Subnetwork Mining for Mild Cognitive Impairment Classification

Fei, Fei; Jie, Biao; Zhang, Daoqiang

doi:10.1089/brain.2013.0214

Cited by 28 publications

(28 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The construction of the hyper-networks enabled us to identify the interaction information among brain regions. In addition, to show that the classification method based on subgraph features can better capture the topological information among brain regions, Fei et al ( 2014 ) adopted frequent subgraph mining technology to mine frequent sub-networks in an MCI dataset, then used a discriminative subgraph mining algorithm to mine discriminative sub-networks. Finally, they used SVM based on a graph kernel for the classification.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

et al. 2017

View full text Add to dashboard Cite

Exploring functional interactions among various brain regions is helpful for understanding the pathological underpinnings of neurological disorders. Brain networks provide an important representation of those functional interactions, and thus are widely applied in the diagnosis and classification of neurodegenerative diseases. Many mental disorders involve a sharp decline in cognitive ability as a major symptom, which can be caused by abnormal connectivity patterns among several brain regions. However, conventional functional connectivity networks are usually constructed based on pairwise correlations among different brain regions. This approach ignores higher-order relationships, and cannot effectively characterize the high-order interactions of many brain regions working together. Recent neuroscience research suggests that higher-order relationships between brain regions are important for brain network analysis. Hyper-networks have been proposed that can effectively represent the interactions among brain regions. However, this method extracts the local properties of brain regions as features, but ignores the global topology information, which affects the evaluation of network topology and reduces the performance of the classifier. This problem can be compensated by a subgraph feature-based method, but it is not sensitive to change in a single brain region. Considering that both of these feature extraction methods result in the loss of information, we propose a novel machine learning classification method that combines multiple features of a hyper-network based on functional magnetic resonance imaging in Alzheimer's disease. The method combines the brain region features and subgraph features, and then uses a multi-kernel SVM for classification. This retains not only the global topological information, but also the sensitivity to change in a single brain region. To certify the proposed method, 28 normal control subjects and 38 Alzheimer's disease patients were selected to participate in an experiment. The proposed method achieved satisfactory classification accuracy, with an average of 91.60%. The abnormal brain regions included the bilateral precuneus, right parahippocampal gyrus\hippocampus, right posterior cingulate gyrus, and other regions that are known to be important in Alzheimer's disease. Machine learning classification combining multiple features of a hyper-network of functional magnetic resonance imaging data in Alzheimer's disease obtains better classification performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Yetkin et al ( 2006 ) confirmed that AD was more active in the right middle frontal gyrus, left inferior temporal gyrus, left thalamus, and right lenticular putamen nucleus than the NC. Fei et al ( 2014 ) showed the difference of topological structures between the MCI, and NC were mainly in left rolandic operculum, insula, left supplementary motor area, left hippocampus, left parahippocampal gyrus, right parahippocampal gyrus, and so on.…”

Section: Discussionmentioning

confidence: 99%

“…Finally, the multi-kernel SVM was used to classify the two groups of subjects. Fei et al ( 2014 ) had constructed threshold connectivity networks of NC and MCI, and extracted frequent subgraphs, and subsequently selected a discriminative subgraph as a feature. Finally, SVM was used for the classification.…”

Section: Discussionmentioning

confidence: 99%

Integrating the Local Property and Topological Structure in the Minimum Spanning Tree Brain Functional Network for Classification of Early Mild Cognitive Impairment

et al. 2018

View full text Add to dashboard Cite

Abnormalities in the brain connectivity in patients with neurodegenerative diseases, such as early mild cognitive impairment (EMCI), have been widely reported. Current research shows that the combination of multiple features of the threshold connectivity network can improve the classification accuracy of diseases. However, in the construction of the threshold connectivity network, the selection of the threshold is very important, and an unreasonable setting can seriously affect the final classification results. Recent neuroscience research suggests that the minimum spanning tree (MST) brain functional network is helpful, as it avoids the methodological biases while comparing networks. In this paper, by employing the multikernel method, we propose a framework to integrate the multiple properties of the MST brain functional network for improving the classification performance. Initially, the Kruskal algorithm was used to construct an unbiased MST brain functional network. Subsequently, the vector kernel and graph kernel were used to quantify the two different complementary properties of the network, such as the local connectivity property and the topological property. Finally, the multikernel support vector machine (SVM) was adopted to combine the two different kernels for EMCI classification. We tested the performance of our proposed method for Alzheimer's Disease Neuroimaging Initiative (ANDI) datasets. The results showed that our method achieved a significant performance improvement, with the classification accuracy of 85%. The abnormal brain regions included the right hippocampus, left parahippocampal gyrus, left posterior cingulate gyrus, middle temporal gyrus, and other regions that are known to be important in the EMCI. Our results suggested that, combining the multiple features of the MST brain functional connectivity offered a better classification performance in the EMCI.

show abstract

“…脑网络一般表示为矩阵形式, 如何有效地抽取网络特征, 并利用其对不同被试进行比较一直是脑网络分析的热点问题. 在以往的研究中, 研究者多使用网络连接边权重、频繁模式, 以及一些图论中的经典度量方法 [23,24] , 但是这些方法并不能完整反映网络的整体特性. 因此在网络的特征表示问题上, 我们提出了一种使用有序子图模式来表示脑网络的方法 [25] , 其中有序子图模式是由一系列成对的由权值边组成的序关系构成, 具体如图 5 所示.…”

Section: 脑网络构建及特征表示unclassified

Intelligent analysis of brain images

Zhang¹,

Zhu²,

Hao³

et al. 2018

Sci. Sin.-Inf.

Self Cite

View full text Add to dashboard Cite

show abstract

Frequent and Discriminative Subnetwork Mining for Mild Cognitive Impairment Classification

Cited by 28 publications

References 77 publications

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

Integrating the Local Property and Topological Structure in the Minimum Spanning Tree Brain Functional Network for Classification of Early Mild Cognitive Impairment

Intelligent analysis of brain images

Contact Info

Product

Resources

About