Enhancing Autism Spectrum Disorder identification in multi-site MRI imaging: A multi-head cross-attention and multi-context approach for addressing variability in un-harmonized data DOI
Ranjeet Ranjan Jha,

Arvind Muralie,

Munish Daroch

и другие.

Artificial Intelligence in Medicine, Год журнала: 2024, Номер 157, С. 102998 - 102998

Опубликована: Окт. 16, 2024

Язык: Английский

The emergence of artificial intelligence in autism spectrum disorder research: A review of neuro imaging and behavioral applications DOI

i b,

P. M. Durai Raj Vincent

Computer Science Review, Год журнала: 2025, Номер 56, С. 100718 - 100718

Опубликована: Янв. 6, 2025

Язык: Английский

Процитировано

1

mGNN-bw: Multi-scale Graph Neural Network Based on Biased Random Walk Path Aggregation for ASD Diagnosis DOI Creative Commons
Wentao Pan, Guang Ling, Feng Liu

и другие.

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Год журнала: 2025, Номер 33, С. 900 - 910

Опубликована: Янв. 1, 2025

In recent years, computationally assisted diagnosis for classifying autism spectrum disorder (ASD) and typically developing (TD) individuals based on neuroimaging data, such as functional magnetic resonance imaging (fMRI), has garnered significant attention. Studies have shown that long-range connectivity patterns in ASD patients exhibit abnormalities, individual brain networks display considerable heterogeneity. However, current graph neural (GNNs) used research failed to adequately capture overlooked differences. To address these limitations, this study proposes a novel multi-scale network biased random walks (mGNN-bw). The model introduces co-optimization strategy between sub-models the main model, leveraging node pooling scores from guide walks, effectively capturing connectivity. By constructing high-order through path encoding aggregation, integrating them with low-order Pearson correlation, achieves robust feature representation. Experimental results publicly available ABIDE I dataset demonstrate superior performance of our approach, achieving accuracy rates 74.8% 73.2% using CC200 AAL atlases, respectively, outperforming existing methods. Additionally, identifies key ASD-associated regions, including frontal lobe, insula, cingulate, calcarine, supported by research. proposed method significantly contributes clinical ASD.

Язык: Английский

Процитировано

0

Hierarchical feature extraction on functional brain networks for autism spectrum disorder identification with resting-state fMRI data DOI

Yiqian Luo,

Qiurong Chen,

Fali Li

и другие.

Neural Networks, Год журнала: 2025, Номер 188, С. 107450 - 107450

Опубликована: Апрель 12, 2025

Язык: Английский

Процитировано

0

Enhancing Autism Spectrum Disorder identification in multi-site MRI imaging: A multi-head cross-attention and multi-context approach for addressing variability in un-harmonized data DOI
Ranjeet Ranjan Jha,

Arvind Muralie,

Munish Daroch

и другие.

Artificial Intelligence in Medicine, Год журнала: 2024, Номер 157, С. 102998 - 102998

Опубликована: Окт. 16, 2024

Язык: Английский

Процитировано

0