Multi-scale semi-supervised clustering of brain images: Deriving disease subtypes

Imagem de Miniatura
Arquivos
art_WEN_Multiscale_semisupervised_clustering_of_brain_images_Deriving_disease_2022.PDF (294.11 KB)
Citações na Scopus
23
Tipo de produção
article
Data de publicação
2022
DOI
Scopus
Web of Science
PubMed
Título da Revista
ISSN da Revista
Título do Volume
Editora
ELSEVIER
Autores
WEN, Junhao
VAROL, Erdem
SOTIRAS, Aristeidis
YANG, Zhijian
CHAND, Ganesh B.
ERUS, Guray
SHOU, Haochang
ABDULKADIR, Ahmed
HWANG, Gyujoon
DWYER, Dominic B.
Citação
MEDICAL IMAGE ANALYSIS, v.75, article ID 102304, 18p, 2022
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Disease heterogeneity is a significant obstacle to understanding pathological processes and delivering pre-cision diagnostics and treatment. Clustering methods have gained popularity for stratifying patients into subpopulations (i.e., subtypes) of brain diseases using imaging data. However, unsupervised clustering approaches are often confounded by anatomical and functional variations not related to a disease or pathology of interest. Semi-supervised clustering techniques have been proposed to overcome this and, therefore, capture disease-specific patterns more effectively. An additional limitation of both unsuper-vised and semi-supervised conventional machine learning methods is that they typically model, learn and infer from data using a basis of feature sets pre-defined at a fixed anatomical or functional scale (e.g., atlas-based regions of interest). Herein we propose a novel method, ""Multi-scAle heteroGeneity analysIs and Clustering"" (MAGIC), to depict the multi-scale presentation of disease heterogeneity, which builds on a previously proposed semi-supervised clustering method, HYDRA. It derives multi-scale and clinically interpretable feature representations and exploits a double-cyclic optimization procedure to effectively drive identification of inter-scale-consistent disease subtypes. More importantly, to understand the conditions under which the clustering model can estimate true heterogeneity related to diseases, we conducted extensive and systematic semi-simulated experiments to evaluate the proposed method on a sizeable healthy control sample from the UK Biobank ( N = 4403). We then applied MAGIC to imaging data from Alzheimer's disease (ADNI, N = 1728) and schizophrenia (PHENOM, N = 1166) patients to demonstrate its potential and challenges in dissecting the neuroanatomical heterogeneity of common brain diseases. Taken together, we aim to provide guidance regarding when such analyses can succeed or should be taken with caution. The code of the proposed method is publicly available at https://github.com/anbai106/MAGIC .
Palavras-chave
Semi-supervised, Clustering, Multi-scale, Heterogeneity, Semi-simulated
URI
https://observatorio.fm.usp.br/handle/OPI/44541
Referências
  1. Abdulkadir A, 2011, NEUROIMAGE, V58, P785, DOI 10.1016/j.neuroimage.2011.06.029
  2. Altman N, 2017, NAT METHODS, V14, P545, DOI 10.1038/nmeth.4299
  3. Ashburner J, 2000, NEUROIMAGE, V11, P805, DOI 10.1006/nimg.2000.0582
  4. Ashburner J, 1998, HUM BRAIN MAPP, V6, P348, DOI 10.1002/(SICI)1097-0193(1998)6:5/6<348::AID-HBM4>3.0.CO;2-P
  5. Bashyam VM, 2020, BRAIN, V143, P2312, DOI 10.1093/brain/awaa160
  6. Bassett D.S., 2013, MULTISCALE ANAL NONL, P179, DOI [10.1002/9783527671632.ch07, DOI 10.1002/9783527671632.CH07]
  7. Bauermeister S, 2020, EUR J EPIDEMIOL, V35, P601, DOI 10.1007/s10654-020-00633-4
  8. Betzel RF, 2017, NEUROIMAGE, V160, P73, DOI 10.1016/j.neuroimage.2016.11.006
  9. Brugger SP, 2017, JAMA PSYCHIAT, V74, P1104, DOI 10.1001/jamapsychiatry.2017.2663
  10. Chand GB, 2020, BRAIN, V143, P1027, DOI 10.1093/brain/awaa025
  11. Chang CC, 2011, ACM T INTEL SYST TEC, V2, DOI 10.1145/1961189.1961199
  12. Young AL, 2018, NAT COMMUN, V9, DOI 10.1038/s41467-018-05892-0
  13. Zhang TH, 2015, SCHIZOPHRENIA BULL, V41, P74, DOI 10.1093/schbul/sbu136
  14. Zhang WJ, 2015, AM J PSYCHIAT, V172, P995, DOI 10.1176/appi.ajp.2015.14091108
  15. Zhang XM, 2016, P NATL ACAD SCI USA, V113, pE6535, DOI 10.1073/pnas.1611073113
  16. Zhu JJ, 2016, SCI REP-UK, V6, DOI 10.1038/srep33857
  17. Zhuo CJ, 2016, PLOS ONE, V11, DOI 10.1371/journal.pone.0162656
  18. Chu C, 2012, NEUROIMAGE, V60, P59, DOI 10.1016/j.neuroimage.2011.11.066
  19. Climescu-Haulica A, 2007, STUD CLASS DATA ANAL, P15, DOI 10.1007/978-3-540-70981-7_2
  20. Cox M.A., 2008, HDB DATA VISUALIZATI, P315, DOI 10.1007/978-3-540-33037-0_14
  21. Cox Robert W, 2017, Proc Natl Acad Sci U S A, V114, pE3370, DOI 10.1073/pnas.1614961114
  22. Cox RW, 1996, COMPUT BIOMED RES, V29, P162, DOI 10.1006/cbmr.1996.0014
  23. Cui Z., 2016, ARXIV160306995
  24. Cuingnet R, 2011, NEUROIMAGE, V56, P766, DOI 10.1016/j.neuroimage.2010.06.013
  25. Davatzikos C, 2001, NEUROIMAGE, V14, P1361, DOI 10.1006/nimg.2001.0937
  26. Davatzikos C, 2019, NEUROIMAGE, V197, P652, DOI 10.1016/j.neuroimage.2018.10.003
  27. DAY WHE, 1984, J CLASSIF, V1, P7, DOI 10.1007/BF01890115
  28. DeTure MA, 2019, MOL NEURODEGENER, V14, DOI 10.1186/s13024-019-0333-5
  29. Dong A., BRAIN, DOI [10.1093/brain/ aww319, aww319, DOI 10.1093/BRAIN/AWW319,AWW319]
  30. Dong AY, 2016, IEEE T MED IMAGING, V35, P612, DOI 10.1109/TMI.2015.2487423
  31. Doshi J, 2016, NEUROIMAGE, V127, P186, DOI 10.1016/j.neuroimage.2015.11.073
  32. Dubey R, 2014, NEUROIMAGE, V87, P220, DOI 10.1016/j.neuroimage.2013.10.005
  33. Dwyer DB, 2018, SCHIZOPHRENIA BULL, V44, P1060, DOI 10.1093/schbul/sby008
  34. Ecker C, 2010, NEUROIMAGE, V49, P44, DOI 10.1016/j.neuroimage.2009.08.024
  35. Ezzati A, 2020, BRAIN IMAGING BEHAV, V14, P1792, DOI 10.1007/s11682-019-00115-6
  36. Filipovych R, 2012, IEEE T MED IMAGING, V31, P1124, DOI 10.1109/TMI.2012.2186977
  37. Franke K, 2010, NEUROIMAGE, V50, P883, DOI 10.1016/j.neuroimage.2010.01.005
  38. Friston KJ., 1994, HUM BRAIN MAPP, V2, P189, DOI [10.1002/hbm.460020402, DOI 10.1002/hbm.460020402, DOI 10.1002/HBM.460020402]
  39. Fu W, 2020, J COMPUT GRAPH STAT, V29, P162, DOI [10.6084/m9.figshare.9034343, 10.1080/10618600.2019.1647846]
  40. Gaonkar B, 2013, NEUROIMAGE, V78, P270, DOI 10.1016/j.neuroimage.2013.03.066
  41. Habes M, 2016, TRANSL PSYCHIAT, V6, DOI 10.1038/tp.2016.39
  42. Hanyu H, 1998, J NEUROL SCI, V156, P195, DOI 10.1016/S0022-510X(98)00043-4
  43. Hartigan J. A., 1979, Applied Statistics, V28, P100, DOI 10.2307/2346830
  44. Honnorat N, 2019, SCHIZOPHR RES, V214, P43, DOI 10.1016/j.schres.2017.12.008
  45. Hu K, 2016, NEUROCOMPUTING, V175, P132, DOI 10.1016/j.neucom.2015.10.043
  46. Insel TR, 2015, SCIENCE, V348, P499, DOI 10.1126/science.aab2358
  47. Jack CR, 2016, NEUROLOGY, V87, P539, DOI 10.1212/WNL.0000000000002923
  48. Jeon S, 2019, FRONT AGING NEUROSCI, V11, DOI 10.3389/fnagi.2019.00211
  49. Jung NY, 2016, NEUROBIOL AGING, V48, P53, DOI 10.1016/j.neurobiolaging.2016.08.010
  50. Kamnitsas K, 2017, MED IMAGE ANAL, V36, P61, DOI 10.1016/j.media.2016.10.004
  51. Koutsouleris N, 2015, BRAIN, V138, P2059, DOI 10.1093/brain/awv111
  52. Lao ZQ, 2004, NEUROIMAGE, V21, P46, DOI 10.1016/j.neuroimage.2003.09.027
  53. Lee DD, 2001, ADV NEUR IN, V13, P556
  54. Lubeiro A, 2016, PROG NEURO-PSYCHOPH, V64, P79, DOI 10.1016/j.pnpbp.2015.06.015
  55. McLachlan GJ., 1988, MIXTURE MODELS INFER
  56. Miller KL, 2016, NAT NEUROSCI, V19, P1523, DOI 10.1038/nn.4393
  57. Miotto R, 2018, BRIEF BIOINFORM, V19, P1236, DOI 10.1093/bib/bbx044
  58. Mirkin B, 2011, WIRES DATA MIN KNOWL, V1, P252, DOI 10.1002/widm.15
  59. Muller MJ, 2005, NEUROIMAGE, V28, P1033, DOI 10.1016/j.neuroimage.2005.06.029
  60. Murray ME, 2011, LANCET NEUROL, V10, P785, DOI 10.1016/S1474-4422(11)70156-9
  61. Nadeau C, 2003, MACH LEARN, V52, P239, DOI 10.1023/A:1024068626366
  62. Nettiksimmons J, 2014, ALZHEIMERS DEMENT, V10, P511, DOI 10.1016/j.jalz.2013.09.003
  63. Ng AY, 2002, ADV NEUR IN, V14, P849
  64. Noh Y, 2014, NEUROLOGY, V83, P1936, DOI 10.1212/WNL.0000000000001003
  65. Okada N, 2016, MOL PSYCHIATR, V21, P1460, DOI 10.1038/mp.2015.209
  66. Ota K, 2016, J ALZHEIMERS DIS, V52, P1385, DOI 10.3233/JAD-160145
  67. Ou YM, 2011, MED IMAGE ANAL, V15, P622, DOI 10.1016/j.media.2010.07.002
  68. Pan YZ, 2020, SCHIZOPHRENIA BULL, V46, P623, DOI 10.1093/schbul/sbz112
  69. Park JY, 2017, SCI REP-UK, V7, DOI [10.1038/srep43270, 10.1177/2158244016684912]
  70. Perl DP, 2010, MT SINAI J MED, V77, P32, DOI 10.1002/msj.20157
  71. Petersen RC, 2010, NEUROLOGY, V74, P201, DOI 10.1212/WNL.0b013e3181cb3e25
  72. Planchuelo-Gomez A, 2020, PROG NEURO-PSYCHOPH, V100, DOI 10.1016/j.pnpbp.2020.109907
  73. Pomponio R., 2019, BIOINFORMATICS, DOI [10.1101/784363, DOI 10.1101/784363]
  74. Poulakis K, 2018, NEUROBIOL AGING, V65, P98, DOI 10.1016/j.neurobiolaging.2018.01.009
  75. Rabinovici Gil D, 2017, Alzheimers Dement (N Y), V3, P83, DOI 10.1016/j.trci.2016.09.002
  76. Rathore S, 2017, NEUROIMAGE, V155, P530, DOI 10.1016/j.neuroimage.2017.03.057
  77. Rozycki M, 2018, SCHIZOPHRENIA BULL, V44, P1035, DOI 10.1093/schbul/sbx137
  78. Samper-Gonzalez J, 2018, NEUROIMAGE, V183, P504, DOI 10.1016/j.neuroimage.2018.08.042
  79. Satterthwaite TD, 2010, AM J PSYCHIAT, V167, P418, DOI 10.1176/appi.ajp.2009.09060808
  80. Schirner M, 2018, ELIFE, V7, DOI 10.7554/eLife.28927
  81. Schnack HG, 2014, NEUROIMAGE, V84, P299, DOI 10.1016/j.neuroimage.2013.08.053
  82. Schulz MA, 2020, NAT COMMUN, V11, DOI 10.1038/s41467-020-18037-z
  83. Schulz MA, 2020, SCI REP-UK, V10, DOI 10.1038/s41598-020-68858-7
  84. Selya AS, 2012, FRONT PSYCHOL, V3, DOI 10.3389/fpsyg.2012.00111
  85. Sotiras A, 2015, NEUROIMAGE, V108, P1, DOI 10.1016/j.neuroimage.2014.11.045
  86. Starck J.-.L., 1998, IMAGE PROCESSING DAT, DOI [10.1017/CBO9780511564352, DOI 10.1017/CBO9780511564352]
  87. Sugihara G, 2017, SCHIZOPHRENIA BULL, V43, P900, DOI 10.1093/schbul/sbw176
  88. ten Kate M, 2018, BRAIN, V141, P3443, DOI 10.1093/brain/awy264
  89. Tustison NJ, 2010, IEEE T MED IMAGING, V29, P1310, DOI 10.1109/TMI.2010.2046908
  90. van Erp TGM, 2016, MOL PSYCHIATR, V21, P547, DOI 10.1038/mp.2015.63
  91. Varghese T, 2013, NEUROL ASIA, V18, P239
  92. Varol E, 2018, NEUROIMAGE, V174, P111, DOI 10.1016/j.neuroimage.2018.02.060
  93. Varol E, 2017, NEUROIMAGE, V145, P346, DOI 10.1016/j.neuroimage.2016.02.041
  94. Vemuri P., 2020, FULLY BAYESIAN LONGI, V26
  95. Wen J., LECT NOTES COMPUTER, P678, DOI [10.1007/978-3-030-59728-3_6, DOI 10.1007/978-3-030-59728-3_6]
  96. Wen JH, 2020, MED IMAGE ANAL, V63, DOI 10.1016/j.media.2020.101694
  97. Whitwell JL, 2007, ARCH NEUROL-CHICAGO, V64, P1130, DOI 10.1001/archneur.64.8.1130
  98. Wolf DH, 2014, SCHIZOPHRENIA BULL, V40, P1328, DOI 10.1093/schbul/sbu026
  99. Wood SJ, 2001, SCHIZOPHR RES, V52, P37, DOI 10.1016/S0920-9964(01)00175-X
  100. Yang Z., 2020, ARXIV200615255CSEESS
  101. Yang Z., 2021, ARXIV210212582CSEESS
  102. Yang ZR, 2010, IEEE T NEURAL NETWOR, V21, P734, DOI 10.1109/TNN.2010.2041361

Coleções
Artigos e Materiais de Revistas Científicas - FM/MPS
Artigos e Materiais de Revistas Científicas - LIM/21