Implicit Embeddings via GAN Inversion for High Resolution Chest Radiographs

Weber, Tobias ; Ingrisch, Michael ; Bischl, Bernd and 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 and Tsaftar, Sotirios A. (eds.) : In: Medical Applications with Disentanglements, Cham: Springer. pp. 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.

• Item Type: Conference or Workshop Item (Speech)
• Keywords: Generative modeling; latent space disentanglement; representation learning
• Faculties: Mathematics, Computer Science and Statistics > Statistics
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• ISSN: 0302-9743
• Place of Publication: Cham
• Language: English