Towards embedding stain-invariance in convolutional neural networks for H&E-stained histopathology

Khrystyna Faryna; Jeroen van der Laak; Geert Litjens

doi:10.1117/12.3006572

3 April 2024 Towards embedding stain-invariance in convolutional neural networks for H&E-stained histopathology

Khrystyna Faryna, Jeroen van der Laak, Geert Litjens

Proceedings Volume 12933, Medical Imaging 2024: Digital and Computational Pathology; 1293304 (2024) https://doi.org/10.1117/12.3006572
Event: SPIE Medical Imaging, 2024, San Diego, California, United States

Abstract

Convolutional neural networks (CNNs) are known to fail if a difference exists in the data they are trained and tested on, known as domain shifts. This sensitivity is particularly problematic in computational pathology, where various factors, such as different staining protocols and stain providers, introduce domain shifts. Many solutions have been proposed in the literature to address this issue, with data augmentation being one of the most popular approaches. While data augmentation can significantly enhance the performance of a CNN in the presence of domain shifts, it does not guarantee robustness. Therefore, it would be advantageous to integrate generalization to specific sources of domain shift directly into the network’s capabilities when known to be present in the real world. In this study, we draw inspiration from roto-translation equivariant CNNs and propose a customized layer to enhance domain generalization and the CNN’s ability to handle variations in staining. To evaluate our approach, we conduct experiments on two publicly available, multi-institutional datasets: CAMELYON17 and MIDOG.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Khrystyna Faryna, Jeroen van der Laak, and Geert Litjens "Towards embedding stain-invariance in convolutional neural networks for H&E-stained histopathology", Proc. SPIE 12933, Medical Imaging 2024: Digital and Computational Pathology, 1293304 (3 April 2024); https://doi.org/10.1117/12.3006572

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available