Affordable Access

deepdyve-link
Publisher Website

Decentralized distribution-sampled classification models with application to brain imaging.

Authors
  • Lewis, Noah1
  • Gazula, Harshvardhan2
  • Plis, Sergey M2
  • Calhoun, Vince D3
  • 1 Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, United States; Department of Computer Science, The University of New Mexico, Albuquerque, NM, United States. Electronic address: [email protected] , (Georgia)
  • 2 Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, United States. , (Georgia)
  • 3 Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, United States; Department of Computer Science, The University of New Mexico, Albuquerque, NM, United States; Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM, United States. , (Georgia)
Type
Published Article
Journal
Journal of neuroscience methods
Publication Date
Oct 17, 2019
Volume
329
Pages
108418–108418
Identifiers
DOI: 10.1016/j.jneumeth.2019.108418
PMID: 31630085
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

In this age of big data, certain models require very large data stores in order to be informative and accurate. In many cases however, the data are stored in separate locations requiring data transfer between local sites which can cause various practical hurdles, such as privacy concerns or heavy network load. This is especially true for medical imaging data, which can be constrained due to the health insurance portability and accountability act (HIPAA) which provides security protocols for medical data. Medical imaging datasets can also contain many thousands or millions of features, requiring heavy network load. Our research expands upon current decentralized classification research by implementing a new singleshot method for both neural networks and support vector machines. Our approach is to estimate the statistical distribution of the data at each local site and pass this information to the other local sites where each site resamples from the individual distributions and trains a model on both locally available data and the resampled data. The model for each local site produces its own accuracy value which are then averaged together to produce the global average accuracy. We show applications of our approach to handwritten digit classification as well as to multi-subject classification of brain imaging data collected from patients with schizophrenia and healthy controls. Overall, the results showed comparable classification accuracy to the centralized model with lower network load than multishot methods. Many decentralized classifiers are multishot, requiring heavy network traffic. Our model attempts to alleviate this load while preserving prediction accuracy. We show that our proposed approach performs comparably to a centralized approach while minimizing network traffic compared to multishot methods. Copyright © 2019. Published by Elsevier B.V.

Report this publication

Statistics

Seen <100 times