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

Deep learning models can enable accurate and efficient disease diagnosis, buthave thus far been hampered by the data scarcity present in the medical world.Automated diagnosis studies have been constrained by underpowered single-centerdatasets, and although some results have shown promise, their generalizabilityto other institutions remains questionable as the data heterogeneity betweeninstitutions is not taken into account. By allowing models to be trained in adistributed manner that preserves patients' privacy, federated learningpromises to alleviate these issues, by enabling diligent multi-center studies.We present the first federated learning study on the modality of cardiovascularmagnetic resonance (CMR) and use four centers derived from subsets of the M\&Mand ACDC datasets, focusing on the diagnosis of hypertrophic cardiomyopathy(HCM). We adapt a 3D-CNN network pretrained on action recognition and exploretwo different ways of incorporating shape prior information to the model, andfour different data augmentation set-ups, systematically analyzing their impacton the different collaborative learning choices. We show that despite the smallsize of data (180 subjects derived from four centers), the privacy preservingfederated learning achieves promising results that are competitive withtraditional centralized learning. We further find that federatively trainedmodels exhibit increased robustness and are more sensitive to domain shifteffects.

Federated Learning for Multi-Center Imaging Diagnostics: A Study in Cardiovascular Disease