Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations
- PMID: 31491832
- PMCID: PMC6627731
- DOI: 10.1016/j.nicl.2019.101929
Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations
Abstract
Combining machine learning with neuroimaging data has a great potential for early diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, it remains unclear how well the classifiers built on one population can predict MCI/AD diagnosis of other populations. This study aimed to employ a spectral graph convolutional neural network (graph-CNN), that incorporated cortical thickness and geometry, to identify MCI and AD based on 3089 T1-weighted MRI data of the ADNI-2 cohort, and to evaluate its feasibility to predict AD in the ADNI-1 cohort (n = 3602) and an Asian cohort (n = 347). For the ADNI-2 cohort, the graph-CNN showed classification accuracy of controls (CN) vs. AD at 85.8% and early MCI (EMCI) vs. AD at 79.2%, followed by CN vs. late MCI (LMCI) (69.3%), LMCI vs. AD (65.2%), EMCI vs. LMCI (60.9%), and CN vs. EMCI (51.8%). We demonstrated the robustness of the graph-CNN among the existing deep learning approaches, such as Euclidean-domain-based multilayer network and 1D CNN on cortical thickness, and 2D and 3D CNNs on T1-weighted MR images of the ADNI-2 cohort. The graph-CNN also achieved the prediction on the conversion of EMCI to AD at 75% and that of LMCI to AD at 92%. The find-tuned graph-CNN further provided a promising CN vs. AD classification accuracy of 89.4% on the ADNI-1 cohort and >90% on the Asian cohort. Our study demonstrated the feasibility to transfer AD/MCI classifiers learned from one population to the other. Notably, incorporating cortical geometry in CNN has the potential to improve classification performance.
Keywords: Convolutional neural networks; Cortical thickness; Dementia classification; Graph; Transfer learning.
Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.
Figures






Similar articles
-
Automated classification of Alzheimer's disease, mild cognitive impairment, and cognitively normal patients using 3D convolutional neural network and radiomic features from T1-weighted brain MRI: A comparative study on detection accuracy.Clin Imaging. 2024 Nov;115:110301. doi: 10.1016/j.clinimag.2024.110301. Epub 2024 Sep 16. Clin Imaging. 2024. PMID: 39303405
-
Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks.Neuroimage Clin. 2019;21:101645. doi: 10.1016/j.nicl.2018.101645. Epub 2018 Dec 18. Neuroimage Clin. 2019. PMID: 30584016 Free PMC article.
-
A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease.Neuroimage. 2019 Apr 1;189:276-287. doi: 10.1016/j.neuroimage.2019.01.031. Epub 2019 Jan 14. Neuroimage. 2019. PMID: 30654174
-
[Research on the application of convolution neural network in the diagnosis of Alzheimer's disease].Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2021 Feb 25;38(1):169-177. doi: 10.7507/1001-5515.202007019. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2021. PMID: 33899442 Free PMC article. Chinese.
-
Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer's Disease Not Using Neuroimaging Biomarkers: A Systematic Review.J Alzheimers Dis. 2024;98(3):793-823. doi: 10.3233/JAD-231271. J Alzheimers Dis. 2024. PMID: 38489188 Free PMC article.
Cited by
-
Subtyping of mild cognitive impairment using a deep learning model based on brain atrophy patterns.Cell Rep Med. 2021 Dec 21;2(12):100467. doi: 10.1016/j.xcrm.2021.100467. eCollection 2021 Dec 21. Cell Rep Med. 2021. PMID: 35028609 Free PMC article.
-
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future.Sensors (Basel). 2021 Jul 12;21(14):4758. doi: 10.3390/s21144758. Sensors (Basel). 2021. PMID: 34300498 Free PMC article. Review.
-
MRI-based mild cognitive impairment and Alzheimer's disease classification using an algorithm of combination of variational autoencoder and other machine learning classifiers.J Alzheimers Dis Rep. 2024 Oct 18;8(1):1434-1452. doi: 10.1177/25424823241290694. eCollection 2024. J Alzheimers Dis Rep. 2024. PMID: 40034356 Free PMC article.
-
Cohort-Specific Optimization of Models Predicting Preclinical Alzheimer's Disease, to Enhance Screening Performance in the Middle of Preclinical Alzheimer's Disease Clinical Studies.J Prev Alzheimers Dis. 2021;8(4):503-512. doi: 10.14283/jpad.2021.39. J Prev Alzheimers Dis. 2021. PMID: 34585226 Free PMC article.
-
Graph representation learning in biomedicine and healthcare.Nat Biomed Eng. 2022 Dec;6(12):1353-1369. doi: 10.1038/s41551-022-00942-x. Epub 2022 Oct 31. Nat Biomed Eng. 2022. PMID: 36316368 Free PMC article. Review.
References
-
- Aderghal K., Benois-Pineau J., Afdel K. Approach and Fusion on ADNI. Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. ACM; Bucharest, Romania: 2017. Classification of sMRI for Alzheimer’s disease diagnosis with CNN: single siamese networks with 2D+? pp. 494–498.
-
- Alzheimer’s Association 2015 Alzheimer’s disease facts and figures. Alzheimers Dement. 2015;11:332–384. - PubMed
-
- Barandela R., Sánchez J.S., Garcia V., Rangel E. Strategies for learning in class imbalance problems. Pattern Recogn. 2003;36:849–851.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Medical