Variational autoencoding tissue response to microenvironment perturbation

Geoffrey F. Schau, Guillaume Thibault, Mark A. Dane, Joe W. Gray, Laura M. Heiser, Young Hwan Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


This work applies deep variational autoencoder learning architecture to study multi-cellular growth characteristics of human mammary epithelial cells in response to diverse microenvironment perturbations. Our approach introduces a novel method of visualizing learned feature spaces of trained variational autoencoding models that enables visualization of principal features in two dimensions. We find that unsupervised learned features more closely associate with expert annotation of cell colony organization than biologically-inspired hand-crafted features, demonstrating the utility of deep learning systems to meaningfully characterize features of multi-cellular growth characteristics in a fully unsupervised and data-driven manner.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2019
Subtitle of host publicationImage Processing
EditorsElsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini, Bennett A. Landman
ISBN (Electronic)9781510625457
StatePublished - 2019
EventMedical Imaging 2019: Image Processing - San Diego, United States
Duration: Feb 19 2019Feb 21 2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceMedical Imaging 2019: Image Processing
Country/TerritoryUnited States
CitySan Diego

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Variational autoencoding tissue response to microenvironment perturbation'. Together they form a unique fingerprint.

Cite this