中国物理B ›› 2026, Vol. 35 ›› Issue (8): 88701-088701.doi: 10.1088/1674-1056/ae2670

• • 上一篇    

Early identification of subjective cognitive decline using 2D horizontal visibility graph analysis of structural MRI networks

Huang-Jing Ni(倪黄晶)1,†, Yu-Fei Dai(戴雨菲)1, Ye Wu(吴烨)2, Jiao-Long Qin(秦姣龙)2,‡, and for the Alzheimer's Disease Neuroimaging Initiative (ADNI)   

  1. 1 School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;
    2 Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
  • 收稿日期:2025-09-03 修回日期:2025-11-23 接受日期:2025-12-02 发布日期:2026-08-06
  • 通讯作者: Xiao-Ping Ou-Yang E-mail:nihuangjing@njupt.edu.cn;jiaolongq@njust.edu.cn
  • 基金资助:
    We acknowledge the OASIS-3 Principal Investigators (T. Benzinger, D. Marcus, and J. Morris) and OASIS-3 grants (NIH P30AG066444, P50AG00561, P30NS09857781, P01AG026276, P01AG003991, R01AG043434, UL1TR000448, and R01EB009352). AV-45 doses were provided by Avid Radiopharmaceuticals, a wholly owned subsidiary of Eli Lilly. We also gratefully acknowledge the contributions from the ADNI project. The ADNI was launched in 2003 as ADNI-1, with subsequent phases including ADNI-GO (2009), ADNI-2 (2010), and ADNI-3 (2016). The ADNI study has observed individuals diagnosed as cognitively normal or with varying degrees of cognitive impairment since 2005. Project updates and more detailed study information can be found at http://www.adni-info.org.
    Project supported by the National Key R&D Program of China (Grant No. 2023YFF1204803), the Natural Science Foundation of Jiangsu Province (Grant No. BK20190736), and the Natural Science Foundation of China (Grant No. 81701346).

Early identification of subjective cognitive decline using 2D horizontal visibility graph analysis of structural MRI networks

Huang-Jing Ni(倪黄晶)1,†, Yu-Fei Dai(戴雨菲)1, Ye Wu(吴烨)2, Jiao-Long Qin(秦姣龙)2,‡, and for the Alzheimer's Disease Neuroimaging Initiative (ADNI)   

  1. 1 School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;
    2 Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
  • Received:2025-09-03 Revised:2025-11-23 Accepted:2025-12-02 Published:2026-08-06
  • Contact: Xiao-Ping Ou-Yang E-mail:nihuangjing@njupt.edu.cn;jiaolongq@njust.edu.cn
  • Supported by:
    We acknowledge the OASIS-3 Principal Investigators (T. Benzinger, D. Marcus, and J. Morris) and OASIS-3 grants (NIH P30AG066444, P50AG00561, P30NS09857781, P01AG026276, P01AG003991, R01AG043434, UL1TR000448, and R01EB009352). AV-45 doses were provided by Avid Radiopharmaceuticals, a wholly owned subsidiary of Eli Lilly. We also gratefully acknowledge the contributions from the ADNI project. The ADNI was launched in 2003 as ADNI-1, with subsequent phases including ADNI-GO (2009), ADNI-2 (2010), and ADNI-3 (2016). The ADNI study has observed individuals diagnosed as cognitively normal or with varying degrees of cognitive impairment since 2005. Project updates and more detailed study information can be found at http://www.adni-info.org.
    Project supported by the National Key R&D Program of China (Grant No. 2023YFF1204803), the Natural Science Foundation of Jiangsu Province (Grant No. BK20190736), and the Natural Science Foundation of China (Grant No. 81701346).

PDF (PC)

1

赞

摘要： Subjective cognitive decline (SCD) represents a preclinical stage of Alzheimer's disease, yet objective evaluation criteria for early diagnosis remain lacking. Traditional morphometric indicators, such as gray matter volume or density, overlook local voxel features and inter-voxel associations. To address this limitation, this study introduces a two-dimensional horizontal visibility graph (2DHVG) analysis method to identify brain structural abnormalities in SCD patients. Each axial slice of gray matter images was converted into a 2DHVG, and complex network features, including clustering coefficient and betweenness centrality, were extracted to characterize local connectivity and global information transmission capacity. Principal component analysis and light gradient boosting machine were employed for feature selection and classification. The 2DHVG-based method achieved excellent performance in SCD identification, with a mean classification AUC of 0.958, mean accuracy of 89.0 %, mean sensitivity of 86.1 %, mean specificity of 90.3 %, and mean F1-score of 82.9 %. Furthermore, significant positive correlations were observed between the mean clustering coefficient and both ADNI working memory (ADNI_MEM, $R=0.3339$, $P=0.0014$) and learning ability indicators (RAVLT.learning, $R=0.3531$, $P=0.0007$). The mean betweenness centrality similarly correlated with ADNI_MEM ($R=0.3018$, $P=0.0041$) and RAVLT.learning ($R=0.3149$, $P=0.0027$). The 2DHVG-based structural imaging analysis method demonstrates significant advantages in feature extraction and classification modeling, providing novel insights for graph-theoretic modeling of structural MRI data in early SCD identification.

关键词: subjective cognitive decline, horizontal visibility graph, complex network, structural magnetic resonance imaging

Abstract: Subjective cognitive decline (SCD) represents a preclinical stage of Alzheimer's disease, yet objective evaluation criteria for early diagnosis remain lacking. Traditional morphometric indicators, such as gray matter volume or density, overlook local voxel features and inter-voxel associations. To address this limitation, this study introduces a two-dimensional horizontal visibility graph (2DHVG) analysis method to identify brain structural abnormalities in SCD patients. Each axial slice of gray matter images was converted into a 2DHVG, and complex network features, including clustering coefficient and betweenness centrality, were extracted to characterize local connectivity and global information transmission capacity. Principal component analysis and light gradient boosting machine were employed for feature selection and classification. The 2DHVG-based method achieved excellent performance in SCD identification, with a mean classification AUC of 0.958, mean accuracy of 89.0 %, mean sensitivity of 86.1 %, mean specificity of 90.3 %, and mean F1-score of 82.9 %. Furthermore, significant positive correlations were observed between the mean clustering coefficient and both ADNI working memory (ADNI_MEM, $R=0.3339$, $P=0.0014$) and learning ability indicators (RAVLT.learning, $R=0.3531$, $P=0.0007$). The mean betweenness centrality similarly correlated with ADNI_MEM ($R=0.3018$, $P=0.0041$) and RAVLT.learning ($R=0.3149$, $P=0.0027$). The 2DHVG-based structural imaging analysis method demonstrates significant advantages in feature extraction and classification modeling, providing novel insights for graph-theoretic modeling of structural MRI data in early SCD identification.

Key words: subjective cognitive decline, horizontal visibility graph, complex network, structural magnetic resonance imaging

中图分类号:  (Medical imaging)

  • 87.57.-s
05.10.-a (Computational methods in statistical physics and nonlinear dynamics) 87.19.lf (MRI: anatomic, functional, spectral, diffusion) 98.52.Cf (Classification and classification systems)