Frequent and discriminative subnetwork mining for mild cognitive impairment classification.

Fei Fei, Biao Jie, Daoqiang Zhang
Author Information
  1. Fei Fei: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics , Nanjing, China .

Abstract

Recent studies on brain networks have suggested that many brain diseases, such as Alzheimer's disease and mild cognitive impairment (MCI), are related to a large-scale brain network, rather than individual brain regions. However, it is challenging to find such a network from the whole brain network due to the complexity of brain networks. In this article, the authors propose a novel method to mine the discriminative subnetworks for classifying MCI patients from healthy controls (HC). Specifically, the authors first extract a set of frequent subnetworks from each of the two groups (i.e., MCI and HC), respectively. Then, measure the discriminative ability of those frequent subnetworks using the graph kernel-based classification method and select the most discriminative subnetworks for subsequent classification. The results on the functional connectivity networks of 12 MCI and 25 HC show that this method can obtain competitive results compared with state-of-the-art methods on MCI classification.

Keywords

References

  1. Neuroimage. 2007 Jul 1;36(3):645-60 [PMID: 17466539]
  2. Bioinformatics. 2005 Jun;21 Suppl 1:i47-56 [PMID: 15961493]
  3. J Neurosci. 2012 Mar 21;32(12):4307-18 [PMID: 22442092]
  4. Hum Brain Mapp. 2007 Oct;28(10):967-78 [PMID: 17133390]
  5. Neuroimage. 2012 Aug 15;62(2):881-6 [PMID: 21964480]
  6. IEEE Trans Med Imaging. 2002 Nov;21(11):1421-39 [PMID: 12575879]
  7. Neurology. 2011 Feb 8;76(6):511-7 [PMID: 21228297]
  8. Neuroimage. 2013 Jan 1;64:728-40 [PMID: 22939874]
  9. Front Psychiatry. 2012 Jan 05;2:77 [PMID: 22291664]
  10. Neurology. 2006 Sep 26;67(6):1011-7 [PMID: 17000970]
  11. Eur Neuropsychopharmacol. 2010 Aug;20(8):519-34 [PMID: 20471808]
  12. AJNR Am J Neuroradiol. 2001 Aug;22(7):1326-33 [PMID: 11498421]
  13. Lancet. 2006 Apr 15;367(9518):1262-70 [PMID: 16631882]
  14. Cereb Cortex. 2013 Apr;23(4):786-800 [PMID: 22490548]
  15. J Alzheimers Dis. 2011;24(3):455-74 [PMID: 21297259]
  16. PLoS One. 2010 Oct 28;5(10):e13701 [PMID: 21060892]
  17. Neuroimage. 2011 Feb 1;54(3):1812-22 [PMID: 20970508]
  18. Biol Psychiatry. 2013 Mar 1;73(5):472-81 [PMID: 22537793]
  19. Neuroimage. 2012 Sep;62(3):2021-33 [PMID: 22677149]
  20. Hum Brain Mapp. 2009 May;30(5):1511-23 [PMID: 18649353]
  21. J Neurosci. 2003 Feb 1;23(3):986-93 [PMID: 12574428]
  22. Neuroimage. 2002 Jan;15(1):273-89 [PMID: 11771995]
  23. Ann Neurol. 2009 Apr;65(4):403-13 [PMID: 19296504]
  24. Neuroimage. 2011 May 15;56(2):766-81 [PMID: 20542124]
  25. Neuroimage. 2010 May 1;50(4):1497-510 [PMID: 20083210]
  26. Neurology. 2005 Jun 14;64(11):1860-7 [PMID: 15955934]
  27. Alzheimers Dement. 2007 Jul;3(3):186-91 [PMID: 19595937]
  28. Phys Rev E Stat Nonlin Soft Matter Phys. 2008 Mar;77(3 Pt 2):036104 [PMID: 18517458]
  29. Neurobiol Aging. 2003 Mar-Apr;24(2):221-31 [PMID: 12498956]
  30. Neurobiol Aging. 2013 Aug;34(8):2023-36 [PMID: 23541878]
  31. Front Syst Neurosci. 2010 Jun 17;4:22 [PMID: 20592949]
  32. IEEE Trans Biomed Eng. 2014 Feb;61(2):576-89 [PMID: 24108708]
  33. Clin Neurophysiol. 2000 Nov;111(11):1961-7 [PMID: 11068230]
  34. Med Image Comput Comput Assist Interv. 2006;9(Pt 2):340-7 [PMID: 17354790]
  35. Neuroimage. 2010 Apr 15;50(3):910-9 [PMID: 20079440]
  36. Neuroimage. 2011 Mar 1;55(1):287-95 [PMID: 21118724]
  37. JAMA. 2009 Jul 22;302(4):385-93 [PMID: 19622817]
  38. Neuroimage. 2011 Apr 1;55(3):856-67 [PMID: 21236349]
  39. Sci Rep. 2012;2:630 [PMID: 22953051]
  40. Cereb Cortex. 2008 Oct;18(10):2374-81 [PMID: 18267952]
  41. Philos Trans R Soc Lond B Biol Sci. 2000 Jan 29;355(1393):111-26 [PMID: 10703047]
  42. Radiology. 2011 Apr;259(1):213-21 [PMID: 21248238]
  43. Conf Comput Vis Pattern Recognit Workshops. 2013;2013:2243-2250 [PMID: 25328915]
  44. Neuropsychologia. 2008;46(6):1648-56 [PMID: 18346763]
  45. Neurobiol Aging. 1998 May-Jun;19(3):173-89 [PMID: 9661992]
  46. Curr Opin Neurol. 2010 Aug;23(4):341-50 [PMID: 20581686]
  47. Neuroimage. 2012 Feb 1;59(3):2045-56 [PMID: 22019883]
  48. Neuroimage. 2010 Sep;52(3):1059-69 [PMID: 19819337]
  49. Radiology. 2009 Apr;251(1):195-205 [PMID: 19201945]
  50. Alzheimer Dis Assoc Disord. 2006 Jul-Sep;20(3 Suppl 2):S69-74 [PMID: 16917199]
  51. PLoS One. 2010 Nov 01;5(11):e13788 [PMID: 21072180]
  52. Neuroimage. 2010 Jan 15;49(2):1432-45 [PMID: 19782143]
  53. Hum Brain Mapp. 2014 Jul;35(7):2876-97 [PMID: 24038749]
  54. Arch Neurol. 2001 Mar;58(3):397-405 [PMID: 11255443]
  55. Arch Neurol. 2001 Dec;58(12):1985-92 [PMID: 11735772]
  56. J Biomed Semantics. 2011 Jul 29;2:3 [PMID: 21801410]
  57. Neuroimage. 2011 Aug 1;57(3):892-907 [PMID: 21605688]
  58. Cereb Cortex. 2007 Oct;17(10):2407-19 [PMID: 17204824]
  59. Neuroscience. 2006 Dec;143(3):793-803 [PMID: 17049178]
  60. J Neurol Neurosurg Psychiatry. 2003 Jan;74(1):44-50 [PMID: 12486265]
  61. Neurobiol Aging. 2011 Dec;32(12):2322.e19-27 [PMID: 20594615]
  62. PLoS One. 2011;6(9):e25278 [PMID: 21966479]
  63. Neurobiol Aging. 2011 Jul;32(7):1198-206 [PMID: 19683363]
  64. Cereb Cortex. 2007 Jan;17(1):92-9 [PMID: 16452642]
  65. PLoS Comput Biol. 2008 Jun 27;4(6):e1000100 [PMID: 18584043]
  66. PLoS One. 2011;6(7):e21935 [PMID: 21818280]
  67. Neuroimage. 2010 Apr 1;50(2):499-508 [PMID: 20026219]
  68. PLoS One. 2012;7(5):e37828 [PMID: 22666397]

MeSH Term

Aged
Aged, 80 and over
Algorithms
Brain
Brain Mapping
Case-Control Studies
Cognitive Dysfunction
Female
Humans
Magnetic Resonance Imaging
Male
Nerve Net
Neural Pathways
Reproducibility of Results

Word Cloud

Created with Highcharts 10.0.0brainMCInetworkdiscriminativesubnetworksclassificationnetworksmildcognitiveimpairmentmethodHCauthorsfrequentgraphresultsfunctionalconnectivityminingRecentstudiessuggestedmanydiseasesAlzheimer'sdiseaserelatedlarge-scaleratherindividualregionsHoweverchallengingfindwholeduecomplexityarticleproposenovelmineclassifyingpatientshealthycontrolsSpecificallyfirstextractsettwogroupsierespectivelymeasureabilityusingkernel-basedselectsubsequent1225showcanobtaincompetitivecomparedstate-of-the-artmethodsFrequentsubnetworkkernelsubgraph

Similar Articles

Cited By (9)