Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN

Utz J, Weise T, Schlereth M, Wagner F, Thies M, Gu M, Uderhardt S, Breininger K (2023)

Publication Type: Conference contribution

Publication year: 2023

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 3858-3866

Conference Proceedings Title: Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

Event location: Paris

ISBN: 9798350307443

DOI: 10.1109/ICCVW60793.2023.00417

Abstract

Annotating nuclei in microscopy images for the training of neural networks is a laborious task that requires expert knowledge and suffers from inter- and intra-rater variability, especially in fluorescence microscopy. Generative networks such as CycleGAN can inverse the process and generate synthetic microscopy images for a given mask, thereby building a synthetic dataset. However, past works report content inconsistencies between the mask and generated image, partially due to CycleGAN minimizing its loss by hiding shortcut information for the image reconstruction in high frequencies rather than encoding the desired image content and learning the target task. In this work, we propose to remove the hidden shortcut information, called steganography, from generated images by employing a low pass filtering based on the discrete cosine transform (DCT). We show that this increases coherence between generated images and cycled masks and evaluate synthetic datasets on a downstream nuclei segmentation task. Here we achieve an improvement of 5.4 percentage points in the F1-score compared to a vanilla CycleGAN. Integrating advanced regularization techniques into the CycleGAN architecture may help mitigate steganography-related issues and produce more accurate synthetic datasets for nuclei segmentation.

Authors with CRIS profile

How to cite

APA:

Utz, J., Weise, T., Schlereth, M., Wagner, F., Thies, M., Gu, M.,... Breininger, K. (2023). Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN. In Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 (pp. 3858-3866). Paris, FR: Institute of Electrical and Electronics Engineers Inc..

MLA:

Utz, Jonas, et al. "Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN." Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023, Paris Institute of Electrical and Electronics Engineers Inc., 2023. 3858-3866.

BibTeX: Download