CNN stability training improves robustness to scanner and IHC-based image variability for epithelium segmentation in cervical histology
2023 | journal article. A publication with affiliation to the University of Göttingen.
Jump to: Cite & Linked | Documents & Media | Details | Version history
Cite this publication
CNN stability training improves robustness to scanner and IHC-based image variability for epithelium segmentation in cervical histology
Miranda Ruiz, F.; Lahrmann, B.; Bartels, L.; Krauthoff, A.; Keil, A.; Härtel, S. & Tao, A. S et al. (2023)
Frontiers in Medicine, 10 pp. 1173616. DOI: https://doi.org/10.3389/fmed.2023.1173616
Documents & Media
Details
- Authors
- Miranda Ruiz, Felipe; Lahrmann, Bernd; Bartels, Liam; Krauthoff, Alexandra; Keil, Andreas; Härtel, Steffen; Tao, Amy S; Ströbel, Philipp; Clarke, Megan A; Wentzensen, Nicolas; Grabe, Niels
- Abstract
- In digital pathology, image properties such as color, brightness, contrast and blurriness may vary based on the scanner and sample preparation. Convolutional Neural Networks (CNNs) are sensitive to these variations and may underperform on images from a different domain than the one used for training. Robustness to these image property variations is required to enable the use of deep learning in clinical practice and large scale clinical research.
- Issue Date
- 2023
- Journal
- Frontiers in Medicine
- ISSN
- 2296-858X
- Language
- English
- Sponsor
- Open-Access-Publikationsfonds 2023
