Prediction of progression to Alzheimer's disease with deep infomax

Alzheimer's Disease Neuroimaging Initiative

Research output: Contribution to journalArticlepeer-review

Abstract

Arguably, unsupervised learning plays a crucial role in the majority of algorithms for processing brain imaging. A recently introduced unsupervised approach Deep InfoMax (DIM) is a promising tool for exploring brain structure in a flexible non-linear way. In this paper, we investigate the use of variants of DIM in a setting of progression to Alzheimer's disease in comparison with supervised AlexNet and ResNet inspired convolutional neural networks. As a benchmark, we use a classification task between four groups: patients with stable, and progressive mild cognitive impairment (MCI), with Alzheimer's disease, and healthy controls. Our dataset is comprised of 828 subjects from the Alzheimers Disease Neuroimaging Initiative (ADNI) database. Our experiments highlight encouraging evidence of the high potential utility of DIM in future neuroimaging studies.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Apr 24 2019
Externally publishedYes

Keywords

  • Classification
  • CNN
  • Deep InfoMax
  • MRI
  • Unsupervised

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Prediction of progression to Alzheimer's disease with deep infomax'. Together they form a unique fingerprint.

Cite this