Detecting and Analyzing Brain Networks of Adult ADHD Using Dual Temporal and Spatial Sparse Representation

被引：0
|
作者：
Gong J.-H. [1 ,2 ]
Liu X.-Y. [1 ]
Zhou J.-S. [3 ]
Sun G. [1 ]
机构：
[1] College of Electrical and Information Engineering, Hunan University, Changsha
[2] College of Electrical and Information Engineering, Hunan Institute of Engineering, Xiangtan
[3] Mental Health Institute of the Second Xiangya Hospital, Central South University, Changsha
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2019年 / 45卷 / 10期
基金：
中国国家自然科学基金;
关键词：
Activity of brain network; Attention deficit hyperactivity disorder (ADHD); Functional magnetic resonance imaging (fMRI); Sparse representation;
D O I：
10.16383/j.aas.c170680
中图分类号：
学科分类号：
摘要：
Attention deficit hyperactivity disorder (ADHD) is a highly prevalent psychiatric disorder, which is generally characterized by symptoms of inattentiveness, hyperactivity and impulsivity. As a popular functional imaging technique, the resting-state functional magnetic resonance imaging (rsfMRI) is frequently used to explore the neural mechanism of ADHD. However, after resting-state brain networks are obtained from the rsfMRI dataset with the traditional independent component analysis, it is difficult to detect reliable ADHD-related brain networks via voxel-level inference because of the high dimensions and relatively few samples of fMRI data. To address the problem, a novel framework and index using the dual temporal and spatial sparse representation (DTSSR) is proposed, which is able to detect the resting-state brain networks related to ADHD from a large scale network-level perspective in an rsfMRI dataset consisting of 22 adult ADHD patients. First, the group-wise brain networks and coupling parameters are inferred from the ADHD fMRI dataset via DTSSR. These coupling parameters are then processed by average-pooling as an index for activity of each group-wise network. Finally, the Spearman correlation analysis between those obtained indices and the ADHD rating scores is performed to detect the networks related to ADHD. Experiment demonstrates that the dorsal attention network and executive control network are significantly related to ADHD. The result shows high stability under different dictionary sizes and can be reasonably explained from brain science. The proposed framework can be used to explore the underlying neural mechanism of ADHD in a new perspective. Copyright © 2019 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：1903 / 1914
页数：11
相关论文
共 45 条
  • [1] Association A.P., Diagnostic and Statistical Manual of Mental Disorders: DSM-IV-TR, pp. 59-66, (2000)
  • [2] Fayyad J., De Graaf R., Kessler R., Alonso J., Angermeyer M., Demyttenaere K., Et al., Cross-national prevalence and correlates of adult attention-deficit hyperactivity disorder, British Journal of Psychiatry, 190, 5, pp. 402-409, (2007)
  • [3] Cao Q.-J., Wang X.-L., Qu S., Wang P., Wu Z.-M., Sun L., Et al., Effects of cognitive-behavioral therapy on regional homogeneity changes in adults with attention-deficit/hyperactivity disorder, Chinese Mental Health Journal, 31, 3, pp. 183-189, (2017)
  • [4] Tian L.X., Jiang T.Z., Liang M., Zang Y.F., He Y., Sui M.Q., Et al., Enhanced resting-state brain activities in ADHD patients: a fMRI study, Brain and Development, 30, 5, pp. 342-348, (2008)
  • [5] Zhu C.Z., Zang Y.F., Cao Q.J., Yan C.G., He Y., Jiang T.Z., Et al., Fisher discriminative analysis of resting-state brain function for attention-deficit/hyperactivity disorder, NeuroImage, 40, 1, pp. 110-120, (2008)
  • [6] Wang X.H., Jiao Y., Tang T.Y., Wang H., Lu Z.H., Altered regional homogeneity patterns in adults with attention-deficit hyperactivity disorder, European Journal of Radiology, 82, 9, pp. 1552-1557, (2013)
  • [7] Akdeniz G., Complexity analysis of resting-state fMRI in adult patients with attention deficit hyperactivity disorder: brain entropy, Computational Intelligence and Neuroscience, 2017, (2017)
  • [8] Zhao Q.H., Li H., Yu X.Y., Huang F., Wang Y.F., Liu L., Et al., Abnormal resting-state functional connectivity of insular subregions and disrupted correlation with working memory in adults with attention deficit/hyperactivity disorder, Frontiers in Psychiatry, 8, (2017)
  • [9] Du J.Q., Wang L.P., Jie B., Zhang D.Q., Network-based classification of ADHD patients using discriminative subnetwork selection and graph kernel PCA, Computerized Medical Imaging and Graphics, 52, pp. 82-88, (2016)
  • [10] Wang X.L., Cao Q.J., Wang J.H., Wu Z.M., Wang P., Sun L., Et al., The effects of cognitive-behavioral therapy on intrinsic functional brain networks in adults with attention-deficit/hyperactivity disorder, Behaviour Research and Therapy, 76, pp. 32-39, (2016)
12345