Learning Domain-Invariant Representations of Histological Images
Open Access
- 16 July 2019
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Medicine
- Vol. 6, 162
Abstract
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
Funding Information
- Technische Universiteit Eindhoven
This publication has 22 references indexed in Scilit:
- A Dataset and a Technique for Generalized Nuclear Segmentation for Computational PathologyIEEE Transactions on Medical Imaging, 2017
- Mitosis Counting in Breast Cancer: Object-Level Interobserver Agreement and Comparison to an Automatic MethodPLOS ONE, 2016
- Domain Adaptive Classification for Compensating Variability in Histopathological Whole Slide Images2016
- Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology ImagesIEEE Transactions on Medical Imaging, 2016
- Assessment of algorithms for mitosis detection in breast cancer histopathology imagesMedical Image Analysis, 2015
- Comprehensive molecular portraits of human breast tumoursNature, 2012
- Visualizing non-metric similarities in multiple mapsMachine Learning, 2011
- Comparison of Quantification of Histochemical Staining By Hue-Saturation-Intensity (HSI) Transformation and Color-DeconvolutionApplied Immunohistochemistry & Molecular Morphology, 2003
- Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long‐term follow‐up. C. W. Elston & I. O. Ellis. Histopathology 1991; 19; 403–410Histopathology, 2002
- Quantification of histochemical staining by color deconvolution.2001