Multi-site diagnostic classification of Autism spectrum disorder using adversarial deep learning on resting-state fMRI

Tang, Yan; Gan, Tao; Xiong, Xuejian; Zhang, Chengyuan; Zhang, Hao; Yang, Yuan

doi:10.1016/j.bspc.2023.104892

Cited by 6 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As biomarkers, these identified regions need to be consistent across multiple datasets and enable to guide the classification process effectively. Regarding the detection of feature consistency, some cross-dataset studies have been conducted for other mental disorders, such as autism spectrum disorder (ASD), using federated adaptation [30] and adversarial learning [31]. However, there is limited research reported on ADHD.…”

Section: Introductionmentioning

confidence: 99%

ADHD classification with cross-dataset feature selection for biomarker consistency detection

Meng,

Chen,

Gao

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Attention deficit hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder in children. While numerous intelligent methods are applied for its subjective diagnosis, they seldom consider the consistency problem of ADHD biomarkers. In practice, these data-driven approaches lead to varying learned features for ADHD classification across diverse ADHD datasets. This phenomenon significantly undermines the reliability of identified biomarkers and hampers the interpretability of these methods. Approach. In this study, we propose a cross-dataset feature selection (FS) module using a grouped SVM-based recursive feature elimination approach (G-SVM-RFE) to enhance biomarker consistency across multiple datasets. Additionally, we employ connectome gradient data for ADHD classification. Specifically, we introduce the G-SVM-RFE method to effectively concentrate gradient components within a limited number of brain regions, thereby increasing the likelihood of identifying these regions as ADHD biomarkers. The cross-dataset FS module is integrated into an existing binary hypothesis testing (BHT) framework. This module utilizes external datasets to identify global regions that yield stable biomarkers, while the local dataset learns its own specific regions to further enhance the performance of ADHD classification. Main results. By employing this module, our experiments achieve an average accuracy of 96.7% on diverse datasets. Importantly, the discriminative gradient components primarily originate from the global regions, providing evidence for the significance of these regions. We further identify regions with the high appearance frequencies as biomarkers. All the used global regions and one local region are recognized, primarily belonging to the limbic system. Significance. These biomarkers align with existing research on impaired working memory and abnormal emotional reactivity in children with ADHD. Thus, our method demonstrates its validity by providing enhanced biological explanations derived from ADHD mechanisms.

show abstract

Section: Introductionmentioning

confidence: 99%