CNN stability training improves robustness to scanner and IHC-based image variability for epithelium segmentation in cervical histology

CNN stability training improves robustness to scanner and IHC-based image variability for epithelium segmentation in cervical histology

BackgroundIn 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 fo...

Full description

Bibliographic Details
Main Authors: Felipe Miranda Ruiz, Bernd Lahrmann, Liam Bartels, Alexandra Krauthoff, Andreas Keil, Steffen Härtel, Amy S. Tao, Philipp Ströbel, Megan A. Clarke, Nicolas Wentzensen, Niels Grabe
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-07-01
Series:Frontiers in Medicine
Subjects:
digital pathology
deep learning
robustness
image variability
stability training
cervical intraepithelial neoplasia
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2023.1173616/full

Internet

https://www.frontiersin.org/articles/10.3389/fmed.2023.1173616/full

Similar Items