Implicit Embeddings via GAN Inversion for High Resolution Chest Radiographs

Weber, Tobias ; Ingrisch, Michael ; Bischl, Bernd und Rügamer, David (2022): Implicit Embeddings via GAN Inversion for High Resolution Chest Radiographs. MICCAI Workshop on Medical Applications with Disentanglements, Singapore, 18. - 22. September 2022. Fragemann, Jana; Li, Jianning; Liu, Xiao und Tsaftar, Sotirios A. (Hrsg.): In: Medical Applications with Disentanglements, Cham: Springer. S. 22-32

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.

• Dokumententyp: Konferenzbeitrag (Vortrag)
• Keywords: Generative modeling; latent space disentanglement; representation learning
• Fakultät: Mathematik, Informatik und Statistik > Statistik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISSN: 0302-9743
• Ort: Cham
• Sprache: Englisch