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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning methods have advanced quickly in brain imaging analysis overthe past few years, but they are usually restricted by the limited labeleddata. Pre-trained model on unlabeled data has presented promising improvementin feature learning in many domains, including natural language processing andcomputer vision. However, this technique is under-explored in brain networkanalysis. In this paper, we focused on pre-training methods with Transformernetworks to leverage existing unlabeled data for brain functional networkclassification. First, we proposed a Transformer-based neural network, named asBrainNPT, for brain functional network classification. The proposed methodleveraged <cls> token as a classification embedding vector for the Transformermodel to effectively capture the representation of brain network. Second, weproposed a pre-training framework for BrainNPT model to leverage unlabeledbrain network data to learn the structure information of brain networks. Theresults of classification experiments demonstrated the BrainNPT model withoutpre-training achieved the best performance with the state-of-the-art models,and the BrainNPT model with pre-training strongly outperformed thestate-of-the-art models. The pre-training BrainNPT model improved 8.75% ofaccuracy compared with the model without pre-training. We further compared thepre-training strategies, analyzed the influence of the parameters of the model,and interpreted the trained model.

BrainNPT: Pre-training of Transformer networks for brain network classification