Deep learning for quality control of subcortical brain 3D shape models

ENIGMA Consortium

Research output: Contribution to journalArticlepeer-review

Abstract

We present several deep learning models for assessing the morphometric fidelity of deep grey matter region models extracted from brain MRI. We test three different convolutional neural net architectures (VGGNet, ResNet and Inception) over 2D maps of geometric features. Further, we present a novel geometry feature augmentation technique based on parametric spherical mapping. Finally, we present an approach for model decision visualization, allowing human raters to see the areas of subcortical shapes most likely to be deemed of failing quality by the machine. Our training data is comprised of 5200 subjects from the ENIGMA Schizophrenia MRI cohorts, and our test dataset contains 1500 subjects from the ENIGMA Major Depressive Disorder cohorts. Our final models reduce human rater time by 46-70%. ResNet outperforms VGGNet and Inception for all of our predictive tasks.

Original languageEnglish (US)
JournalUnknown Journal
DOIs
StatePublished - Aug 28 2018
Externally publishedYes

Keywords

  • Deep learning
  • Quality checking
  • Subcortical shape analysis

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • Immunology and Microbiology(all)
  • Neuroscience(all)
  • Pharmacology, Toxicology and Pharmaceutics(all)

Fingerprint Dive into the research topics of 'Deep learning for quality control of subcortical brain 3D shape models'. Together they form a unique fingerprint.

Cite this