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

For machine learning applications in medical imaging, the availability oftraining data is often limited, which hampers the design of radiologicalclassifiers for subtle conditions such as autism spectrum disorder (ASD).Transfer learning is one method to counter this problem of low training dataregimes. Here we explore the use of meta-learning for very low data regimes inthe context of having prior data from multiple sites - an approach we termsite-agnostic meta-learning. Inspired by the effectiveness of meta-learning foroptimizing a model across multiple tasks, here we propose a framework to adaptit to learn across multiple sites. We tested our meta-learning model forclassifying ASD versus typically developing controls in 2,201 T1-weighted(T1-w) MRI scans collected from 38 imaging sites as part of Autism BrainImaging Data Exchange (ABIDE) [age: 5.2-64.0 years]. The method was trained tofind a good initialization state for our model that can quickly adapt to datafrom new unseen sites by fine-tuning on the limited data that is available. Theproposed method achieved an ROC-AUC=0.857 on 370 scans from 7 unseen sites inABIDE using a few-shot setting of 2-way 20-shot i.e., 20 training samples persite. Our results outperformed a transfer learning baseline by generalizingacross a wider range of sites as well as other related prior work. We alsotested our model in a zero-shot setting on an independent test site without anyadditional fine-tuning. Our experiments show the promise of the proposedsite-agnostic meta-learning framework for challenging neuroimaging tasksinvolving multi-site heterogeneity with limited availability of training data.

Few-Shot Classification of Autism Spectrum Disorder using Site-Agnostic Meta-Learning and Brain MRI