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

doi:10.1088/1674-1056/ae2670

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.

Keywords: subjective cognitive decline horizontal visibility graph complex network structural magnetic resonance imaging

Received: 03 September 2025
Revised: 23 November 2025
Accepted manuscript online: 02 December 2025

PACS:	87.57.-s	(Medical imaging)
	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)

Fund: 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).

Corresponding Authors: Xiao-Ping Ou-Yang
E-mail: nihuangjing@njupt.edu.cn;jiaolongq@njust.edu.cn

Cite this article:

Huang-Jing Ni(倪黄晶), Yu-Fei Dai(戴雨菲), Ye Wu(吴烨), Jiao-Long Qin(秦姣龙), and for the Alzheimer's Disease Neuroimaging Initiative (ADNI) Early identification of subjective cognitive decline using 2D horizontal visibility graph analysis of structural MRI networks 2026 Chin. Phys. B 35 088701

[1] Jessen F, Amariglio R E, et al. 2014 Alzheimers Dement. 10 844
[2] Jack C R, Bennett D A, Blennow K, Carrillo M C, Dunn B, Haeberlein S B, Holtzman D M, Jagust W, Jessen F, Karlawish J, Liu E, Molinuevo J L, Montine T, Phelps C, Rankin K P, Rowe C C, Scheltens P, Siemers E, Snyder H M, Sperling R, Elliott C, Masliah E, Ryan L and Silverberg N 2018 Alzheimers Dement. 14 535
[3] Vemuri P and Jack C R 2010 Alzheimers Res. Ther. 2 23
[4] Peter J, Scheef L, Abdulkadir A, Boecker H, Heneka M, Wagner M, Koppara A, Klöppel S, Jessen F and Alzheimer’s Disease Neuroimaging Initiative 2014 Alzheimers Dement. 10 99
[5] Arrondo P, Elía-Zudaire Ó,Martí-Andrés G, Fernańdez-SearaMA and Riverol M 2022 Alzheimers Res. Ther. 14 98
[6] Striepens N, Scheef L,Wind A, Popp J, Spottke A, Cooper-Mahkorn D, Suliman H,Wagner M, Schild H H and Jessen F 2010 Dement. Geriatr. Cogn. Disord. 29 75
[7] Doherty B M, Schultz S A, Oh J M, Koscik R L, Dowling N M, Gallagher C L, Carlsson C M, Bendlin B B, LaRue A, Hermann B P, Rowley H A, Asthana S, Sager M A, Johnson S C and Okonkwo O C 2015 Alzheimers Dement. 1 160
[8] Kim M J, Seo S W, Kim G H, Kim S T, Lee J M, Qiu A and Na D L 2013 Arch. Gerontol. Geriatr. 57 110
[9] Perrotin A, De Flores R, Lamberton F, Poisnel G, La Joie R, De La Sayette V, Mézenge F, Tomadesso C, Landeau B, Desgranges B and Chételat G 2015 J. Alzheimers Dis. 48 S141
[10] Liang L, Zhao L, Wei Y, Mai W, Duan G, Su J, Nong X, Yu B, Li C, Mo X, Wilson G, Deng D and Kong J 2020 Front. Aging Neurosci. 12 64
[11] Jessen F, Feyen L, Freymann K, Tepest R, Maier W, Heun R, Schild H H and Scheef L 2006 Neurobiol. Aging 27 1751
[12] Ryu S Y, Lim E Y, Na S, Shim Y S, Cho J H, Yoon B, Hong Y J and Yang D W 2017 Int. Psychogeriatr. 29 785
[13] Li W, Yue L and Xiao S 2022 Front. Psychiatry 13 950270
[14] Song J, Yang H, Yan H, Lu Q, Guo L, Zheng H, Zhang T, Lin B, Zhao Z, He C and Shen Y 2024 Brain Imaging Behav. 18 1536
[15] Zhang M and Huang P 2021 Int. J. Med. Radiol. 44 373
[16] Han S, Zheng R, Li S, Liu L, Wang C, Jiang Y, Wen M, Zhou B, Wei Y, Pang J, Li H, Zhang Y, Chen Y and Cheng J 2023 Psychol. Med. 53 2146
[17] Liu J, Tao W, Guo X, Kwapong W R, Ye C, Wang A, Wu X, Wang Z and Liu M 2023 Investig. Ophthalmol. Vis. Sci. 64 40
[18] De Flores R, Berron D, Ding S, Ittyerah R, Pluta J B, Xie L, Adler D H, Robinson J L, Schuck T, Trojanowski J Q, Grossman M, Liu W, Pickup S, Das S R, Wolk D A, Yushkevich P A and Wisse L E M 2020 Hippocampus 30 545
[19] Vermunt L, Dicks E, Wang G, et al. 2020 Brain Commun. 2 fcaa102
[20] Iacovacci J and Lacasa L 2018 IEEE Trans. Pattern Anal. Mach. Intell. 42 974
[21] Lacasa L, Luque J, Luque B, Ballesteros F and Nuño J C 2008 Proc. Natl. Acad. Sci. USA 105 4972
[22] Wen T, Chen H and Cheong K H 2022 Nonlinear Dyn. 110 2979
[23] Pei L, Li Z and Liu J 2021 Chaos 31 013128
[24] Ni H J, Du R Y, Liang L, Hua L L, Zhu L H and Qin J L 2023 Chin. Phys. B 32 078501
[25] Ma L, Ren Y L, He A J, Cheng D Q and Yang X D 2023 Chin. Phys. B 32 110506
[26] Derbie A Y, Altaye M, Wang J, Allahverdy A, He L, Tamm L and Parikh N A 2025 Commun. Biol. 8 345
[27] Sharma R and Joshi S D 2025 Ann. Neurosci. 32 21
[28] LaMontagne P J, Benzinger T L, Morris J C, Keefe S, Hornbeck R, Xiong C, Grant E, Hassenstab J, Moulder K, Vlassenko A G, Raichle M E, Cruchaga C and Marcus D 2019 Ann. Neurosci. 32 21
[29] Ni H, Xue J, Qin J and Zhang Y 2024 Comput. Methods Programs Biomed. 254 108281
[30] Yan C G and Zang Y F 2010 Front. Syst. Neurosci. 4 13
[31] Ashburner J 2007 NeuroImage 38 95
[32] Hocking M C, Schultz R T, Yerys B E, Minturn J E, Fantozzi P and Herrington J D 2024 J. Neurooncol. 169 247
[33] Dupré N, Drieu A and Joutel A 2024 J. Clin. Invest. 134 e172841
[34] Shu N, Wang X, Bi Q, Zhao T and Han Y 2018 Radiology 286 229
[35] Wang J,Wang X, Xia M, Liao X, Evans A and He Y 2015 Front. Hum. Neurosci. 9 386
[36] He Y, Chen Z J and Evans A C 2007 Cereb. Cortex 17 2407
[37] Deng S, Tan S, Song X, Lin X, Yang K and Li X 2024 CNS Neurosci. Ther. 30 e14859
[38] Xu X, Chen P, Xiang Y, Xie Z, Yu Q, Zhou X and Wang P 2022 Front. Aging Neurosci. 14 965923
[39] Dhavamani L, Joshi S V, Kothapalli P K V, Elangovan M, Putchanuthala R B and Senthamil Selvan R 2025 Microsc. Res. Tech. 88 1115
[40] Jin J, Ma J, Wu J J, Lu J J, Lu H Y, Zheng M X, Hua X Y and Xu J G 2025 CNS Neurosci. Ther. 31 e70205
[41] Verfaillie S C J, Slot R E R, Dicks E, Prins N D, Overbeek J M, Teunissen C E, Scheltens P, Barkhof F, van der Flier W M and Tijms B M 2018 Hum. Brain Mapp. 39 3143
[42] He Y, Chen Z and Evans A 2008 J. Neurosci. 28 4756
[43] Tijms B M, Möller C, Vrenken H, Wink A M, De Haan W, Van Der Flier W M, Stam C J, Scheltens P and Barkhof F 2013 PLoS ONE 8 e58921
[44] Rubinov M and Sporns O 2010 NeuroImage 52 1059
[45] Van Den Heuvel M P and Sporns O 2013 Trends Cogn. Sci. 17 683
[46] Dai Z and He Y 2014 Neurosci. Bull. 30 217
[47] Wang J, Zuo X, Dai Z, Xia M, Zhao Z, Zhao X, Jia J, Han Y and He Y 2013 Biol. Psychiatry 73 472
[48] Crane P K, Carle A, Gibbons L E, Insel P, Mackin R S, Gross A, Jones R N, Mukherjee S, Curtis S M, Harvey D, Weiner M and Mungas D 2012 Brain Imaging Behav. 6 502
[49] Estévez-González A, Kulisevsky J, Boltes A, Otermín P and García- Sánchez C 2003 Int. J. Geriatr. Psychiatry 18 1021
[50] Li X, Zhou Y, Dvornek N, Zhang M, Gao S, Zhuang J, Scheinost D, Staib L H, Ventola P and Duncan J S 2021 Med. Image Anal. 74 102233

[1]	A routing strategy for non-uniform spatial network Yicong Ye(叶毅聪), Yongxiang Xia(夏永祥), and Haicheng Tu(涂海程). Chin. Phys. B, 2026, 35(7): 078901.
[2]	Fixed points as regulatory hubs in discrete memristive neural networks: An analysis of the FitzHugh-Nagumo model Shaobo He(贺少波), Jiawei Xiao(肖佳伟), Qilai Chen(陈祺来), and Huihai Wang(王会海). Chin. Phys. B, 2026, 35(6): 060502.
[3]	Optimal synchronization of higher-order Kuramoto model on hypergraphs Chong-Yang Wang(王重阳), Bi-Yun Ji(季碧芸), and Linyuan Lü(吕琳媛). Chin. Phys. B, 2025, 34(7): 070502.
[4]	Global dynamics and optimal control of SEIQR epidemic model on heterogeneous complex networks Xiongding Liu(柳雄顶), Xiaodan Zhao(赵晓丹), Xiaojing Zhong(钟晓静), and Wu Wei(魏武). Chin. Phys. B, 2025, 34(6): 060203.
[5]	SFFSlib: A Python library for optimizing attribute layouts from micro to macro scales in network visualization Ke-Chao Zhang(张可超), Sheng-Yue Jiang(蒋升跃), and Jing Xiao(肖婧). Chin. Phys. B, 2025, 34(5): 058903.
[6]	Associated network family of the unified piecewise linear chaotic family and their relevance Haoying Niu(牛浩瀛) and Jie Liu(刘杰). Chin. Phys. B, 2025, 34(4): 040503.
[7]	Finite time hybrid synchronization of heterogeneous duplex complex networks via time-varying intermittent control Cheng-Jun Xie(解成俊) and Xiang-Qing Lu(卢向清). Chin. Phys. B, 2025, 34(4): 040601.
[8]	Explosive information spreading in higher-order networks: Effect of social reinforcement Yu Zhou(周宇), Yingpeng Liu(刘英鹏), Liang Yuan(袁亮), Youhao Zhuo(卓友濠), Kesheng Xu(徐克生), Jiao Wu(吴娇), and Muhua Zheng(郑木华). Chin. Phys. B, 2025, 34(3): 038704.
[9]	GPIC: A GPU-based parallel independent cascade algorithm in complex networks Chang Su(苏畅), Xu Na(那旭), Fang Zhou(周方), and Linyuan Lü(吕琳媛). Chin. Phys. B, 2025, 34(3): 030204.
[10]	Characteristics of complex network of heatwaves over China Xuemin Shen(沈雪敏), Xiaodong Hu(胡晓东), Aixia Feng(冯爱霞), Qiguang Wang(王启光), and Changgui Gu(顾长贵). Chin. Phys. B, 2025, 34(3): 038903.
[11]	Node ranking based on graph curvature and PageRank Hongbo Qu(曲鸿博), Yu-Rong Song(宋玉蓉), Ruqi Li(李汝琦), Min Li(李敏), and Guo-Ping Jiang(蒋国平). Chin. Phys. B, 2025, 34(2): 028901.
[12]	Detecting the core of a network by the centralities of the nodes Peijie Ma(马佩杰), Xuezao Ren(任学藻), Junfang Zhu(朱军芳), and Yanqun Jiang(蒋艳群). Chin. Phys. B, 2024, 33(8): 088903.
[13]	Dynamic analysis of major public health emergency transmission considering the dual-layer coupling of community-resident complex networks Peng Yang(杨鹏), Ruguo Fan(范如国), Yibo Wang(王奕博), and Yingqing Zhang(张应青). Chin. Phys. B, 2024, 33(7): 070206.
[14]	Prediction of collapse process and tipping points for mutualistic and competitive networks with k-core method Dongli Duan(段东立), Feifei Bi(毕菲菲), Sifan Li(李思凡), Chengxing Wu(吴成星), Changchun Lv(吕长春), and Zhiqiang Cai(蔡志强). Chin. Phys. B, 2024, 33(5): 050201.
[15]	Effects of individual heterogeneity on social contagions Fu-Zhong Nian(年福忠) and Yu Yang(杨宇). Chin. Phys. B, 2024, 33(5): 058705.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

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

Cite this article:

Online attention