A Comparative Study of Population-Graph Construction Methods and Graph Neural Networks for Brain Age Regression

被引:0
|
作者
Bintsi, Kyriaki-Margarita [1 ]
Mueller, Tamara T. [2 ]
Starck, Sophie [2 ]
Baltatzis, Vasileios [1 ,3 ]
Hammers, Alexander [3 ]
Rueckert, Daniel [1 ,2 ]
机构
[1] Imperial Coll London, Dept Comp, BioMedIA, London, England
[2] Tech Univ Munich, Fac Informat, Lab AI Med & Healthcare, Munich, Germany
[3] Kings Coll London, Biomed Engn & Imaging Sci, London, England
基金
英国工程与自然科学研究理事会;
关键词
Brain age regression; Population graphs; Graph Neural Networks;
D O I
10.1007/978-3-031-55088-1_6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The difference between the chronological and biological brain age of a subject can be an important biomarker for neurodegenerative diseases, thus brain age estimation can be crucial in clinical settings. One way to incorporate multimodal information into this estimation is through population graphs, which combine various types of imaging data and capture the associations among individuals within a population. In medical imaging, population graphs have demonstrated promising results, mostly for classification tasks. In most cases, the graph structure is pre-defined and remains static during training. However, extracting population graphs is a non-trivial task and can significantly impact the performance of Graph Neural Networks (GNNs), which are sensitive to the graph structure. In this work, we highlight the importance of a meaningful graph construction and experiment with different population-graph construction methods and their effect on GNN performance on brain age estimation. We use the homophily metric and graph visualizations to gain valuable quantitative and qualitative insights on the extracted graph structures. For the experimental evaluation, we leverage the UK Biobank dataset, which offers many imaging and non-imaging phenotypes. Our results indicate that architectures highly sensitive to the graph structure, such as Graph Convolutional Network (GCN) and Graph Attention Network (GAT), struggle with low homophily graphs, while other architectures, such as GraphSage and Chebyshev, are more robust across different homophily ratios. We conclude that static graph construction approaches are potentially insufficient for the task of brain age estimation and make recommendations for alternative research directions.
引用
收藏
页码:64 / 73
页数:10
相关论文
共 50 条
  • [31] Review of Text Classification Methods Based on Graph Neural Networks
    Su, Yilei
    Li, Weijun
    Liu, Xueyang
    Ding, Jianping
    Liu, Shixia
    Li, Haonan
    Li, Guanfeng
    Computer Engineering and Applications, 2024, 60 (19) : 1 - 17
  • [32] DEEP NEURAL NETWORKS ON GRAPH SIGNALS FOR BRAIN IMAGING ANALYSIS
    Guo, Yiluan
    Nejati, Hossein
    Cheung, Ngai-Man
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3295 - 3299
  • [33] A graph neural network framework for causal inference in brain networks
    Wein, S.
    Malloni, W. M.
    Tome, A. M.
    Frank, S. M.
    Henze, G-, I
    Wuest, S.
    Greenlee, M. W.
    Lang, E. W.
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [34] Anti-Money Laundering in Cryptocurrencies Through Graph Neural Networks: A Comparative Study
    Marasi, Simone
    Ferretti, Stefano
    2024 IEEE 21ST CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE, CCNC, 2024, : 272 - 277
  • [35] Graph neural networks-based spatiotemporal prediction of photovoltaic power: a comparative study
    Dairi Abdelkader
    Harrou Fouzi
    Khaldi Belkacem
    Sun Ying
    Neural Computing and Applications, 2025, 37 (6) : 4769 - 4795
  • [36] A Comparative Study of Shock Graph Methods for shape Recognition
    Hingway, S. P.
    Bhurchandi, K. M.
    2009 SECOND INTERNATIONAL CONFERENCE ON EMERGING TRENDS IN ENGINEERING AND TECHNOLOGY (ICETET 2009), 2009, : 1178 - +
  • [37] Signed Curvature Graph Representation Learning of Brain Networks for Brain Age Estimation
    Li, Jingming
    Lyu, Zhengyuan
    Yu, Hu
    Fu, Si
    Li, Ke
    Yao, Li
    Guo, Xiaojuan
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (12) : 7491 - 7502
  • [38] Graph neural networks for multivariate time series regression with application to seismic data
    Bloemheuvel, Stefan
    van den Hoogen, Jurgen
    Jozinovic, Dario
    Michelini, Alberto
    Atzmueller, Martin
    INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS, 2023, 16 (03) : 317 - 332
  • [39] Graph neural networks for multivariate time series regression with application to seismic data
    Stefan Bloemheuvel
    Jurgen van den Hoogen
    Dario Jozinović
    Alberto Michelini
    Martin Atzmueller
    International Journal of Data Science and Analytics, 2023, 16 : 317 - 332
  • [40] A Robust Comparative Analysis of Graph Neural Networks on Dynamic Link Prediction
    Skarding, Joakim
    Hellmich, Matthew
    Gabrys, Bogdan
    Musial, Katarzyna
    IEEE ACCESS, 2022, 10 : 64146 - 64160