English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generalization is one of the main challenges of computational pathology.Slide preparation heterogeneity and the diversity of scanners lead to poormodel performance when used on data from medical centers not seen duringtraining. In order to achieve stain invariance in breast invasive carcinomapatch classification, we implement a stain translation strategy using cycleGANsfor unsupervised image-to-image translation. We compare three cycleGAN-basedapproaches to a baseline classification model obtained without any staininvariance strategy. Two of the proposed approaches use cycleGAN's translationsat inference or training in order to build stain-specific classificationmodels. The last method uses them for stain data augmentation during training.This constrains the classification model to learn stain-invariant features.Baseline metrics are set by training and testing the baseline classificationmodel on a reference stain. We assessed performances using three medicalcenters with H&E and H&E&S staining. Every approach tested in this studyimproves baseline metrics without needing labels on target stains. The stainaugmentation-based approach produced the best results on every stain. Eachmethod's pros and cons are studied and discussed in this paper. However,training highly performing cycleGANs models in itself represents a challenge.In this work, we introduce a systematical method for optimizing cycleGANtraining by setting a novel stopping criterion. This method has the benefit ofnot requiring any visual inspection of cycleGAN results and proves superiorityto methods using a predefined number of training epochs. In addition, we alsostudy the minimal amount of data required for cycleGAN training.

Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology