Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large-scale multi-sample study

Autor(es)

Pinaya, Walter H. L. ^{[1, 2, 3]} ; Mechelli, Andrea ^[1] ; Sato, Joao R. ^[2]

Afiliação do(s) autor(es)

^[1] Kings Coll London, Inst Psychiat Psychol & Neurosci, Dept Psychosis Studies, London - England

^[2] Univ Fed ABC, Ctr Math Comp & Cognit, Rua Arcturus 03, BR-09606070 Sao Bernardo Do Campo, SP - Brazil

^[3] Univ Fed ABC, Ctr Engn Modeling & Appl Social Sci, Sao Bernardo Do Campo, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Human Brain Mapping; v. 40, n. 3, p. 944-954, FEB 15 2019.
• Citações Web of Science: 3

Resumo

Machine learning is becoming an increasingly popular approach for investigating spatially distributed and subtle neuroanatomical alterations in brain-based disorders. However, some machine learning models have been criticized for requiring a large number of cases in each experimental group, and for resembling a black box that provides little or no insight into the nature of the data. In this article, we propose an alternative conceptual and practical approach for investigating brain-based disorders which aim to overcome these limitations. We used an artificial neural network known as deep autoencoder to create a normative model using structural magnetic resonance imaging data from 1,113 healthy people. We then used this model to estimate total and regional neuroanatomical deviation in individual patients with schizophrenia and autism spectrum disorder using two independent data sets (n =263). We report that the model was able to generate different values of total neuroanatomical deviation for each disease under investigation relative to their control group (p <.005). Furthermore, the model revealed distinct patterns of neuroanatomical deviations for the two diseases, consistent with the existing neuroimaging literature. We conclude that the deep autoencoder provides a flexible and promising framework for assessing total and regional neuroanatomical deviations in neuropsychiatric populations. (AU)

• Processo FAPESP: 13/10498-6 - Aprendizado de máquina em neuroimagem: desenvolvimento de métodos e aplicações clínicas em transtornos psiquiátricos
• Beneficiário: João Ricardo Sato
• Modalidade de apoio: Auxílio à Pesquisa - Regular