Skip to main content

End-to-end Training of Deep Probabilistic CCA on Paired Biomedical Observations

Author(s): Gundersen, Gregory; Dumitrascu, Bianca; Ash, Jordan T; Engelhardt, Barbara E

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr14z7m
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGundersen, Gregory-
dc.contributor.authorDumitrascu, Bianca-
dc.contributor.authorAsh, Jordan T-
dc.contributor.authorEngelhardt, Barbara E-
dc.date.accessioned2021-10-08T19:49:06Z-
dc.date.available2021-10-08T19:49:06Z-
dc.date.issued2020en_US
dc.identifier.citationGundersen, Gregory, Bianca Dumitrascu, Jordan T. Ash, and Barbara E. Engelhardt. "End-to-end Training of Deep Probabilistic CCA on Paired Biomedical Observations." In Proceedings of The 35th Uncertainty in Artificial Intelligence Conference (2020): pp. 945-955.en_US
dc.identifier.issn2640-3498-
dc.identifier.urihttp://proceedings.mlr.press/v115/gundersen20a/gundersen20a.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr14z7m-
dc.description.abstractMedical pathology images are visually evaluated by experts for disease diagnosis, but the connection between image features and the state of the cells in an image is typically unknown. To understand this relationship, we develop a multimodal modeling and inference framework that estimates shared latent structure of joint gene expression levels and medical image features. Our method is built around probabilistic canonical correlation analysis (PCCA), which is fit to image embeddings that are learned using convolutional neural networks and linear embeddings of paired gene expression data. Using a differentiable take on the EM algorithm, we train the model end-to-end so that the PCCA and neural network parameters are estimated simultaneously. We demonstrate the utility of this method in constructing image features that are predictive of gene expression levels on simulated data and the Genotype-Tissue Expression data. We demonstrate that the latent variables are interpretable by disentangling the latent subspace through shared and modality-specific views.en_US
dc.format.extent945 - 955en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of The 35th Uncertainty in Artificial Intelligence Conferenceen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleEnd-to-end Training of Deep Probabilistic CCA on Paired Biomedical Observationsen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
EndEndTrainingPaired.pdf9.3 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.