3D CNN for neuropsychiatry: Predicting Autism with interpretable Deep Learning applied to minimally preprocessed structural MRI data

PLoS One. 2024 Oct 21;19(10):e0276832. doi: 10.1371/journal.pone.0276832. eCollection 2024.

Abstract

Predictive modeling approaches are enabling progress toward robust and reproducible brain-based markers of neuropsychiatric conditions by leveraging the power of multivariate analyses of large datasets. While deep learning (DL) offers another promising avenue to further advance progress, there are challenges related to implementation in 3D (best for MRI) and interpretability. Here, we address these challenges and describe an interpretable predictive pipeline for inferring Autism diagnosis using 3D DL applied to minimally processed structural MRI scans. We trained 3D DL models to predict Autism diagnosis using the openly available ABIDE I and II datasets (n = 1329, split into training, validation, and test sets). Importantly, we did not perform transformation to template space, to reduce bias and maximize sensitivity to structural alterations associated with Autism. Our models attained predictive accuracies equivalent to those of previous machine learning (ML) studies, while side-stepping the time- and resource-demanding requirement to first normalize data to a template. Our interpretation step, which identified brain regions that contributed most to accurate inference, revealed regional Autism-related alterations that were highly consistent with the literature, encompassing a left-lateralized network of regions supporting language processing. We have openly shared our code and models to enable further progress towards remaining challenges, such as the clinical heterogeneity of Autism and site effects, and to enable the extension of our method to other neuropsychiatric conditions.

MeSH terms

  • Adolescent
  • Adult
  • Autistic Disorder* / diagnostic imaging
  • Brain* / diagnostic imaging
  • Brain* / pathology
  • Child
  • Deep Learning*
  • Female
  • Humans
  • Imaging, Three-Dimensional / methods
  • Magnetic Resonance Imaging* / methods
  • Male
  • Neural Networks, Computer
  • Neuropsychiatry / methods

Grants and funding

MG received an Irish Research Council Postgraduate Scholarship (Project ID: GOIPG/2021/1508). We also received a donation for this research project from a French non-profit endowment fund called the HyperCube Institute (IHC). The IHC had to terminate all activity in 2020 due to the impacts of COVID-19. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.