Impact Factor 3.113
2018 JCR, Web of Science Group 2019

Frontiers journals are at the top of citation and impact metrics

Methods ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Med. | doi: 10.3389/fmed.2019.00162

Learning Domain-Invariant Representations of Histological Images

 Maxime Lafarge1*, Josien Pluim1, Koen Eppenhof1 and  Mitko Veta1
  • 1Department of Biomedical Engineering, Eindhoven University of Technology, Netherlands

Histological images present high appearance variability due to inconsistent latent parameters related to the preparation and scanning procedure of histological slides, as well as the inherent biological variability of tissues.

Machine-learning models are trained with images from a limited set of domains, and are expected to generalize to images from unseen domains. Methodological design choices have to be made in order to yield domain invariance and proper generalization. In digital pathology, standard approaches focus either on ad-hoc normalization of the latent parameters based on prior knowledge, such as staining normalization, or aim at anticipating new variations of these parameters via data augmentation.

Since every histological image originates from a unique data distribution, we propose to consider every histological slide of the training data as a domain and investigated the alternative approach of domain-adversarial training to learn features that are invariant to this available domain information. We carried out a comparative analysis with staining normalization and data augmentation on two different tasks: generalization to images acquired in unseen pathology labs for mitosis detection and generalization to unseen organs for nuclei segmentation.

We report that the utility of each method depends on the type of task and type of data variability present at training and test time. The proposed framework for domain-adversarial training is able to improve generalization performances on top of conventional methods.

Keywords: Histopathology image analysis, domain-invariant representation, domain-adversarial convolutional network, Mitosis detection, nuclei segmentation

Received: 01 Apr 2019; Accepted: 01 Jul 2019.

Edited by:

Anne Martel, Sunnybrook Research Institute (SRI), Canada

Reviewed by:

Thomas Menter, University Hospital of Basel, Switzerland
Andrea Ronchi, University of Campania Luigi Vanvitelli, Italy
Xin Qi, Rutgers University, The State University of New Jersey, United States  

Copyright: © 2019 Lafarge, Pluim, Eppenhof and Veta. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Mx. Maxime Lafarge, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands,