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 approaches, together with neuroimaging techniques, play animportant role in psychiatric disorders classification. Previous studies onpsychiatric disorders diagnosis mainly focus on using functional connectivitymatrices of resting-state functional magnetic resonance imaging (rs-fMRI) asinput, which still needs to fully utilize the rich temporal information of thetime series of rs-fMRI data. In this work, we proposed amulti-dimension-embedding-aware modality fusion transformer (MFFormer) forschizophrenia and bipolar disorder classification using rs-fMRI and T1 weightedstructural MRI (T1w sMRI). Concretely, to fully utilize the temporalinformation of rs-fMRI and spatial information of sMRI, we constructed a deeplearning architecture that takes as input 2D time series of rs-fMRI and 3Dvolumes T1w. Furthermore, to promote intra-modality attention and informationfusion across different modalities, a fusion transformer module (FTM) isdesigned through extensive self-attention of hybrid feature maps ofmulti-modality. In addition, a dimension-up and dimension-down strategy issuggested to properly align feature maps of multi-dimensional from differentmodalities. Experimental results on our private and public OpenfMRI datasetsshow that our proposed MFFormer performs better than that using a singlemodality or multi-modality MRI on schizophrenia and bipolar disorder diagnosis.

Multi-Dimension-Embedding-Aware Modality Fusion Transformer for Psychiatric Disorder Clasification