Implicit Embeddings via GAN Inversion for High Resolution Chest Radiographs

MCML Authors

Tobias Weber

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Michael Ingrisch

Prof. Dr.

Principal Investigator

Clinical Data Science in Radiology

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

David Rügamer

Prof. Dr.

Principal Investigator

Statistics, Data Science and Machine Learning

Abstract

Generative models allow for the creation of highly realistic artificial samples, opening up promising applications in medical imaging. In this work, we propose a multi-stage encoder-based approach to invert the generator of a generative adversarial network (GAN) for high resolution chest radiographs. This gives direct access to its implicitly formed latent space, makes generative models more accessible to researchers, and enables to apply generative techniques to actual patient’s images. We investigate various applications for this embedding, including image compression, disentanglement in the encoded dataset, guided image manipulation, and creation of stylized samples. We find that this type of GAN inversion is a promising research direction in the domain of chest radiograph modeling and opens up new ways to combine realistic X-ray sample synthesis with radiological image analysis.

inproceedings

---

MAD @MICCAI 2022

1st Workshop on Medical Applications with Disentanglements at the 25th International Conference on Medical Image Computing and Computer Assisted Intervention. Singapore, Sep 18-22, 2022.

---

Authors

T. Weber • M. Ingrisch • B. Bischl • D. Rügamer

---

Links

DOI

---

Research Areas

 A1 | Statistical Foundations & Explainability

 C1 | Medicine