Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

64 Downloads (Pure)

Abstract

Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semantically meaningful directions corresponding to human-interpretable image transformations. However, until now, their exploration for medical images has been limited due to the requirement of supervised data. Several methods for unsupervised discovery of interpretable directions in GAN latent spaces have shown interesting results on natural images. This work explores the potential of applying these techniques on medical images by training a GAN and a VAE on thoracic CT scans and using an unsupervised method to discover interpretable directions in the resulting latent space. We find several directions corresponding to non-trivial image transformations, such as rotation or breast size. Furthermore, the directions show that the generative models capture 3D structure despite being presented only with 2D data. The results show that unsupervised methods to discover interpretable directions in GANs generalize to VAEs and can be applied to medical images. This opens a wide array of future work using these methods in medical image analysis.
OriginalsprogEngelsk
TitelDeep Generative Models : Second MICCAI Workshop, DGM4MICCAI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings
ForlagSpringer
Publikationsdato2022
Sider24-33
ISBN (Trykt)978-3-031-18575-5
ISBN (Elektronisk)978-3-031-18576-2
DOI
StatusUdgivet - 2022
BegivenhedSecond MICCAI Workshop, DGM4MICCAI 2022, - Singapore
Varighed: 22 sep. 2022 → …

Workshop

WorkshopSecond MICCAI Workshop, DGM4MICCAI 2022,
BySingapore
Periode22/09/2022 → …
NavnLecture Notes in Computer Science
Vol/bind13609
ISSN0302-9743

Emneord

  • eess.IV
  • cs.CV
  • cs.LG

Citationsformater