Generative models and abstractions for large-scale neuroanatomy datasets

• Type of Material: Article
• Authors: David Rolnick, University of Pennsylvania; Eva Dyer, Emory University
• Language: English
• Date: 2019-04-01
• Publisher: Elsevier Inc
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2019 Elsevier Ltd. All rights reserved.
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1016/j.conb.2019.02.005
• Title of Journal or Parent Work: Current Opinion in Neurobiology
• Volume: 55
• Start Page: 112
• End Page: 120
• Keywords: Neuroanatomy; Generative models

Abstract

Neural datasets are increasing rapidly in both resolution and volume. In neuroanatomy, this trend has been accelerated by innovations in imaging technology. As full datasets are impractical and unnecessary for many applications, it is important to identify abstractions that distill useful features of neural structure, organization, and anatomy. In this review article, we discuss several such abstractions and highlight recent algorithmic advances in working with these models. In particular, we discuss the use of generative models in neuroanatomy; such models may be considered ‘meta-abstractions’ that capture distributions over other abstractions.