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

Since data scarcity and data heterogeneity are prevailing for medical images,well-trained Convolutional Neural Networks (CNNs) using previous normalizationmethods may perform poorly when deployed to a new site. However, a reliablemodel for real-world clinical applications should be able to generalize wellboth on in-distribution (IND) and out-of-distribution (OOD) data (e.g., the newsite data). In this study, we present a novel normalization technique calledwindow normalization (WIN) to improve the model generalization on heterogeneousmedical images, which is a simple yet effective alternative to existingnormalization methods. Specifically, WIN perturbs the normalizing statisticswith the local statistics computed on the window of features. Thisfeature-level augmentation technique regularizes the models well and improvestheir OOD generalization significantly. Taking its advantage, we propose anovel self-distillation method called WIN-WIN for classification tasks. WIN-WINis easily implemented with twice forward passes and a consistency constraint,which can be a simple extension for existing methods. Extensive experimentalresults on various tasks (6 tasks) and datasets (24 datasets) demonstrate thegenerality and effectiveness of our methods.

A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images