Multi-scale metabolic brain connectivity construction: application to Alzheimer’s disease computer-aided diagnosis

Abstract

This study introduces a novel method for constructing multi-scale individual brain networks from static Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) images, with a primary focus on diagnosing Alzheimer’s Disease (AD). Using Schaefer atlases, we partition the brain image into distinct regions, treating them as nodes in the graph. Subsequently, the Kernel Density Estimation (KDE) and Wasserstein Distance (WD) algorithms are used to estimate similarities between brain regions, forming graph connections. Addressing limitations inherent in fixed KDE settings, we propose employing several methods: the interquartile range, Sturges’, and Freedman-Diaconis rules, to optimize KDE settings. WD, renowned for its ability to capture both probability and spatial differences, is used to enhance the comparison of similarities among graph nodes. The effectiveness of our method is validated using the ADNI dataset. Connectivity analysis across diagnostic groups–Cognitive Normal (CN), Mild Cognitive Impairment (MCI), and AD–reveals disruptions in information transmission within the FDG-PET based brain network of MCI and AD subjects, compared to CN. Our findings support the effectiveness of KDE and WD in constructing multi-scale individual brain networks from FDGPET images. This method shows promise for applications in other brain disorders, enabling personalized diagnosis.

Keywords

• Fluorodeoxyglucose Positron Emission Tomography
• Individual brain network
• Kernel Density Estimation
• Wasserstein Distance
• Alzheimer’s Disease
• Mild Cognitive Impairment

References

1. C. Patterson, C, (2018). World Alzheimer Report 2018: The State of the Art of Dementia Research. Alzheimer’s Disease International, London
2. Alberdi, A, Aztiria, A, Basarab, A, (2016). On the early diagnosis of Alzheimers Disease from multimodal signals: A survey. Artificial Intelligence in Medicine, vol. 71, pp. 1-29, 7.
3. Guedj, E et al, (2022). EANM procedure guidelines for brain PET imaging using [18 F] FDG, version 3. European Journal of Nuclear Medicine and Molecular Imaging, pp. 1-20, 2022.
4. Huang SY, Hsu JL, Lin KJ, Liu HL, Wey SP, Hsiao IT, (2018). Characteristic patterns of inter- and intra-hemispheric metabolic connectivity in patients with stable and progressive mild cognitive impairment and Alzheimer’s disease. Scientific Reports, vol. 8, 9.
5. Yao, Z, Hu, B, Chen, X, Xie, Y, Gutknecht, J, D. Majoe, D, (2017). Learning Metabolic Brain Networks in MCI and AD by Robustness and Leave-One-Out Analysis: An FDG-PET Study. American Journal of Alzheimer’s Disease & Other Dementias, vol. 33, p. 42–54, 9.
6. Wang, M, Jiang, J, Yan, Z, Alberts, I, Ge, J, Zhang, H, Zuo, C, Yu, J, Rominger, A, Shi, F, (2020). Individual brain metabolic connectome indicator based on Kullback-Leibler Divergence Similarity Estimation predicts progression from mild cognitive impairment to Alzheimer’s dementia. European Journal of Nuclear Medicine and Molecular Imaging, vol. 47, p. 2753–2764, 4.
7. Huang, SY, Hsu, JL, Lin, KJ, Hsiao, IT, (2020). A Novel Individual Metabolic Brain Network for 18F-FDG PET Imaging. Frontiers in Neuroscience, vol. 14, 5.
8. Li, W, Tang, Y, Peng, L, Wang, Z, Hu, S, Gao, X, (2023). The reconfiguration pattern of individual brain metabolic connectome for Parkinson’s disease identification. MedComm, vol.4, no.4, p.e305, 2023, doi: 10.1002/mco2.305.

9. Tuan, PM, Trung, NL, Adel, M, Guedj, E, (2023). Auto Encoder-based Feature Ranking for Predicting Mild Cognitive Impairment Conversion using FDG-PET Images. 2023 IEEE Statistical Signal Processing Workshop (SSP), Hanoi, Vietnam: IEEE, pp. 720–724. doi: 10.1109/SSP53291.2023.10208072.
10. Mitchell, AJ, (2009). A meta-analysis of the accuracy of the mini-mental state examination in the detection of dementia and mild cognitive impairment. Journal of Psychiatric Research, vol. 43, no. 4, pp. 411431.
11. Schaefer A et al. (2018). Local-Global Parcellation of the Human Cerebral Cortex from Intrinsic Functional Connectivity MRI. Cerebral Cortex, vol. 28, no. 9, pp. 3095–3114, doi: 10.1093/cercor/bhx179.
12. Weglarczyk, S, (2018). Kernel density estimation and its application," ITM Web of Conferences, vol. 23, p. 00037.
13. Hubert M, Vandervieren, E, (2008). An adjusted boxplot for skewed distributions. Computational Statistics & Data Analysis, vol. 52, no. 12, pp. 5186–5201, doi: 10.1016/j.csda.2007.11.008.
14. Scott, DW, (2009). Sturges’ rule. WIREs Computational Stats, vol. 1, no. 3, pp. 303–306, doi: 10.1002/wics.35.
15. Birgé, L, Rozenholc, Y, (2006). How many bins should be put in a regular histogram. ESAIM: PS, vol. 10, pp. 24–45, doi: 10.1051/ps:2006001.
16. Panaretos VM, Zemel, Y, (2019). Statistical spects of Wasserstein Distances. Annu. Rev. Stat. Appl., vol. 6, no. 1, pp. 405–431, doi: 10.1146/annurev-statistics- 30718-104938.
17. Ramdas, A, N. Trillos, N, M. Cutu M, (2017). On Wasserstein Two-Sample Testing and Related Families of Nonparametric Tests. Entropy, vol. 19, no. 2, p. 47, doi: 10.3390/e19020047.
18. Farahani, FV, Karwowski, W, Ligthall, NR, (2019). Application of Graph Theory for Identifying Connectivity Patterns in Human Brain Networks: A Systematic Review. Front. Neurosci., vol. 13, p. 585, doi: 0.3389/fnins.2019.00585.
19. Zhong Y et al., (2014). Altered effective connectivity patterns of the default mode network in Alzheimer’s disease: An fMRI study. Neuroscience Letters, vol. 578, pp. 171–175, Aug. 2014, doi: 10.1016/j.neulet.2014.06.043.
20. Sporns, O, (2018). Graph theory methods: applications in brain networks. Dialogues in Clinical Neuroscience, vol. 20, no. 2, pp. 111-121.
21. Wu Z et al., (2020). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 1, pp. 4-24.