HMGNet: Autism Spectrum Disorder Diagnosis Based on Hierarchical Multi-dimensional Feature Map Convolutional Networks

Corresponding author: Yang XiaoLin, yangxl@pumc.edu.cn

DOI: 10.12201/bmr.202509.00005

•  

  Abstract: Purpose/Significance Starting from the challenges in the clinical diagnosis of Autism Spectrum Disorder (ASD), this study explores the potential application of functional connectivity (FC) based on resting-state functional magnetic resonance imaging (rs-fMRI) in predicting ASD. The aim is to address the difficulty of identifying reliable biomarkers in the diagnosis of neuropsychiatric disorders. Methods/Process We propose a novel model called HMGNet, a hierarchical multi-dimensional feature graph network. This model employs a TE time-series encoder to extract temporal correlation features with long-term dependencies and enhances FC matrix feature modeling. Additionally, a graph attention mechanism is introduced to dynamically adjust weights for identifying key inter-regional brain interactions, while residual learning is utilized to deepen the GCN architecture, enabling the learning of higher-level information hierarchies. Results/Conclusion Empirical results demonstrate that HMGNet achieves an accuracy of 74.4% on two types of ABIDE datasets, surpassing the performance of most competitors, which typically achieve 72.6%. Moreover, the identified biomarkers are highly consistent with authoritative medical knowledge, providing a feasible new pathway for the clinical diagnosis of ASD. By improving deep network construction and enhancing model interpretability, HMGNet not only increases diagnostic accuracy but also lays a solid foundation for the development of future strategies for early detection and intervention in ASD.

  Key words: fMRI; Hierarchical multi-dimensional feature graph network; Autism spectrum disorder; attention model

  Submit time: 1 September 2025

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• shaojie. Research progress on environmental factors of autism spectrum disorders in children. 2024. doi: 10.12201/bmr.202410.00005

  Data analysis of drug reviews based on public concerns and emotional perspectives: A case study of paroxetine treatment for autism. 2024. doi: 10.12201/bmr.202408.00060

  Xu Xiaolian, Ji Meng, Han Xiancheng. Application of Multi-dimensional Process Assessment in Residency Training Teaching. 2024. doi: 10.12201/bmr.202412.00010

  HU Haiyang, ZHAO Congpu, Ma Lian, JIANG Huizhen, ZHANG Jing, ZHU Weiguo. Attention Mechanism And Dilated Convolution Neural Networks for Named Entity Recognition. 2021. doi: 10.12201/bmr.202102.00004

  Lvyanhua, wangkanglong, zhongxiaoyun, Chen Jun Ye. Construction of user portrait model of Internet medical platform based on text mining: A case study of autism diagnosis data. 2023. doi: 10.12201/bmr.202312.00012

  HUANG Jin-quan, ZHANG Chu, LIU Ling-tao, PAN Wei, ZHAI Ju-ye, LIU Yu-wen. Research on online hospital feature mining based on HSM_LDA model. 2023. doi: 10.12201/bmr.202305.00012

  YU Feng, ZOU Xiao-jie, XU Zhen. The relationship between hyperactivity behavior in children with attention deficit hyperactivity disorder and serum levels of thyroid-stimulating hormone. 2024. doi: 10.12201/bmr.202411.00024

  fengli. A Comparative Study on the Accuracy of Nine Combined Machine Learning Algorithms in Early Diagnosis of Tumors Based on High-dimensional dataFeng Li 1,*, Yue Xiaofei 2. 2021. doi: 10.12201/bmr.202108.00016

  Chen Yifei, Tang Xiaoli. Study on Dynamic Technology Opportunity Detection Method Based on Graph Neural Network -- A Case Study of Diagnosis and Treatment of Atherosclerosis. 2025. doi: 10.12201/bmr.202503.00040

  huzhijian. Research on Hierarchical Diagnosis and Treatment System Based on Blockchain. 2021. doi: 10.12201/bmr.202111.00004

• ID	Submit time	Number	Download
  1	2025-06-26	bmr.202509.00005V1	Download

• Public  Anonymous  To author only Submit Comments