Zoom-In Neural Network Deep-Learning Model for Alzheimer’s Disease Assessments
Abstract
:1. Introduction
2. Zoom-In Neural Network with Subpattern and Refined Learning
2.1. Structure of Zoom-In Neural Network
2.2. Zoom-In Learning Unit Processes
2.3. Zoom-In Neural Network Algorithm
Algorithm 1: Train Algorithm of ZNN |
1 Input Layer 1.1 Split train input data with n features into the k subsets with n/k features such that {I0,1}, {I0,2}, …, {I0,k} 2 i-th ZLU layer (initially i = 1) 2.1 Let ZLUi,j be j-th ZLU in i-th ZLU layer 2.2 For each {Ii−1,j}, where j = 1 to k 2.2.1 Assign {Ii−1,j} to ZLUi,j as input 2.3 For each ZLUi,j, where j = 1 to k 2.3.1 Standard training 2.3.1.1 Standard training using NEWFMi,j from {Ii−1,j} 2.3.1.2 Instance grouping: divide {Ii−1,j} instances into misclassified instances (MI) {Mi,j} and correctly classified instances (CCI) {Ci,j} 2.3.2 Zoom-in training 2.3.2.1 Subpattern training from {Mi,j} using NEWFMi,j,M 2.3.2.2 Refine training from {Ci,j} using NEWFMi,j,C 2.3.3 Zoom-in output 2.3.3.1 Output TSD {Ti,j,M} using NEWFMi,j,M from {Ii−1,j} 2.3.3.2 Output TSD {Ti,j,C} using NEWFMi,j,C from {Ii−1,j} 2.4 Split the TSDs {Ti,1,M, Ti,1,C, Ti,2,M, Ti,2,C, …, Ti,n,M, Ti,n,C} into {Ii,1}, {Ii,2}, …, {Ii,n}, where n is the number of ZLUs in the (i + 1)-th ZLU layer 2.5 i = i + 1, k = n, and go to 2 until predefined i is reached 3 Output Layer 3.1 Train by the NEWFMi using {Ii−1,1}, {Ii−1,2}, …, {Ii−1,k} |
Algorithm 2: Test Algorithm of ZNN |
1 Input Layer 1.1 Split test input data with n features into the k subsets with n/k features such that: {I0,1}, {I0,2}, …, {I0,k} as in 1.1 of Train Algorithm of ZNN 2 i-th ZLU Layer (initially i = 1) 2.1 For each {Ii−1,j}, where j = 1 to k 2.1.1 Assign {Ii−1,j} to ZLUi,j as input 2.1.2 Zoom-in test: 2.2.2.1 Output TSD {Ti,j,M} using NEWFMi,j,M from {Ii−1,j} 2.2.2.2 Output TSD {Ti,j,C} using NEWFMi,j,C from {Ii−1,j} 2.2 Split the TSDs {Ti,1,M, Ti,1,C, Ti,2,M, Ti,2,C, …, Ti,n,M, Ti,n,C} into {Ii,1}, {Ii,2}, …, {Ii,n}, where n is the number of ZLUs in the (i + 1)-th ZLU layer 2.3 i = i + 1, k = n, and go to 2 until the output layer is reached 3 Output Layer 3.1 Output TSD {Ti} by the NEWFMi using {Ii−1,1}, {Ii−1,2}, …, {Ii−1,k} |
3. Experimental Results
3.1. Dataset
3.2. Experimental Structure for Alzheimer’s Disease Assessments Using ZNN
3.3. AD, MCI, and NC Classifications
4. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Sutskever, I.; Martens, J. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th International Conference on Machine Learning, JMLR Atlanta, GA, USA, June 2013; pp. 16–21. [Google Scholar]
- Crick, F. The recent excitement about neural networks. Nature 1989, 337, 129–132. [Google Scholar] [CrossRef] [PubMed]
- Rumelhart, D.E.; Hinton, G.E.; Williams, R.J. Learning representations by back-propagating errors. Nature 1986, 323, 533–536. [Google Scholar] [CrossRef]
- Schiess, M.; Urbanczik, R.; Senn, W. Somato-dendritic Synaptic Plasticity and Error-backpropagation in Active Dendrites. PLoS Comput. Biol. 2016, 12, e1004638. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Bengio, Y. Learning deep architectures for AI. Found. Trends Mach. Learn. 2009, 2, 1–127. [Google Scholar] [CrossRef]
- Hinton, G.E.; Salakhutdinov, R. Reducing the dimensionality of data with neural networks. Science 2006, 313, 504–507. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Hinton, G.E.; Osindero, S.; The, Y.-W. A fast learning algorithm for deep belief nets. Neural Comput. 2006, 18, 1527–1554. [Google Scholar] [CrossRef]
- Sutskever, I.; Martens, J.; Hinton, G. Generating text with recurrent neural networks. In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, WA, USA, 28 June–2 July 2011. [Google Scholar]
- LeCun, Y.; Boser, B.; Denker, J.S.; Henderson, D.; Howard, R.E.; Hubbard, W.; Jackel, L.D. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1989, 1, 541–551. [Google Scholar] [CrossRef]
- Mnih, V.; Kavukcuoglu, K.; Silver, D.; Rusu, A.A.; Veness, J.; Bellemare, M.G.; Graves, A.; Riedmiller, M.; Fidjeland, A.K.; Ostrovski, G.; et al. Human-level control through deep reinforcement learning. Nature 2015, 518, 529–533. [Google Scholar] [CrossRef]
- Lu, J.; Yuan, X.; Yahagi, T. A method of face recognition based on fuzzy clustering and parallel neural networks. Signal Process. 2006, 86, 2026–2039. [Google Scholar] [CrossRef]
- Hochreiter, S. The Vanishing Gradient Problem during Learning Recurrent Neural Nets and Problem Solutions. Int. J. Unc. Fuzz. Knowl. Based Syst. 1998, 6, 107. [Google Scholar] [CrossRef]
- Lillicrap, T.P.; Cownden, D.; Tweed, D.B.; Akerman, C.J. Random synaptic feedback weights support error backpropagation for deep learning. Nat. Commun. 2016, 7, 13276. [Google Scholar] [CrossRef] [PubMed]
- Qu, L.; Lim Joon, S. Alzheimer’s Disease and Mild Cognitive Impairment Detection Using Zoom-in Neural Network. Basic Clin. Pharmacol. Toxicol. 2019, 124, S3. [Google Scholar]
- Lim, J.S. Finding Features for Real-Time Premature Ventricular Contraction Detection Using a Fuzzy Neural Network System. IEEE Trans. Neural Netw. 2009, 20, 522–527. [Google Scholar] [CrossRef] [PubMed]
- Takagi, T.; Sugeno, M. Fuzzy Identification of Systems and Its Applications to Modeling and Control. IEEE Trans. Syst. Man. Cybern. 1985, 15, 116–132. [Google Scholar] [CrossRef]
- Son, S.-Y.; Lee, S.-H.; Chung, K.; Lim, J.S. Feature selection for daily peak load forecasting using a neuro-fuzzy system. Multimed. Tools Appl. 2015, 74, 2321–2336. [Google Scholar] [CrossRef]
- Cao, Y.; Summerfield, C.; Park, H.; Giordano, B.L.; Kayser, C. Causal Inference in the Multisensory Brain. Neuron 2019, 102, 1076–1087.e8. [Google Scholar] [CrossRef] [Green Version]
- DiCarlo, J.J.; Zoccolan, D.; Rust, N.C. How does the brain solve visual object recognition? Neuron 2012, 73, 415–434. [Google Scholar] [CrossRef] [Green Version]
- Qiu, L.; Su, J.; Ni, Y.; Bai, Y.; Zhang, X.; Li, X.; Wan, X. The neural system of metacognition accompanying decision-making in the prefrontal cortex. PLoS Biol. 2018, 16, e2004037. [Google Scholar] [CrossRef]
- Jack, C.R., Jr.; Bernstein, M.A.; Fox, N.C.; Thompson, P.; Alexander, G.; Harvey, D.; Borowski, B.; Britson, P.J.; Whitwell, J.L.; Ward, C.; et al. The Alzheimer’s Disease Neuroimaging Initiative (ADNI): MRI Methods. J. Magn. Reson. Imaging 2008, 27, 685–691. [Google Scholar] [CrossRef] [Green Version]
- Tzourio-Mazoyer, N.; Landeau, B.; Papathanassiou, D.; Crivello, F.; Etard, O.; Delcroix, N.; Mazoyer, B.; Joliot, M. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRIsingle-subject brain. Neuroimage 2002, 15, 273–289. [Google Scholar] [CrossRef]
- Khazaee, A.; Ebrahimzadeh, A.; Babajani-Feremi, A. Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer’s disease. Brain Imaging Behav. 2016, 10, 799–817. [Google Scholar] [CrossRef] [PubMed]
- Guimera, R.; Sales-Pardo, M.; Amaral, L.A. Classes of complex networks defined by role-to-role connectivity profiles. Nat. Phys. 2007, 3, 63–69. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Rubinov, M.; Sporns, O. Weight-conserving characterization of complex functional brain networks. NeuroImage 2011, 56, 2068–2079. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Brandes, U. A faster algorithm for betweenness centrality*. J. Math. Sociol. 2001, 25, 163–177. [Google Scholar] [CrossRef]
- Hagmann, P.; Cammoun, L.; Gigandet, X.; Meuli, R.; Honey, C.J.; Wedeen, V.J.; Sporns, O. Mapping the structural core of human cerebral cortex. PLoS Biol. 2008, 6, e159. [Google Scholar] [CrossRef]
- Estrada, E.; Higham, D.J. Network properties revealed through matrix functions. SIAM Rev. 2010, 52, 696–714. [Google Scholar] [CrossRef]
- Newman, M.E.J. Mathematics of networks. In The New Palgrave Dictionary of Economics; Durlauf, S.N., Blume, L.E., Eds.; Palgrave Macmillan: London, UK, 2008. [Google Scholar]
- Boldi, P.; Santini, M.; Vigna, S. PageRank: Functional dependencies. ACM Trans. Inf. Syst. 2009, 27, 19. [Google Scholar] [CrossRef]
- Foster, J.G.; Foster, D.V.; Grassberger, P.; Paczuski, M. Edge direction and the structure of networks. Proc. Natl. Acad. Sci. USA 2010, 107, 10815–10820. [Google Scholar] [CrossRef] [Green Version]
- Humphries, M.D.; Gurney, K. Network ‘small-world-ness’: A quantitative method for determining canonical network equivalence. PLoS ONE 2008, 3, e0002051. [Google Scholar] [CrossRef]
- Saleem, T.J.; Zahra, S.R.; Wu, F.; Alwakeel, A.; Alwakeel, M.; Jeribi, F.; Hijji, M. Deep Learning-Based Diagnosis of Alzheimer’s Disease. J. Pers. Med. 2022, 12, 815. [Google Scholar] [CrossRef]
- Bozzali, M.; Giulietti, G.; Basile, B.; Serra, L.; Spano, B.; Perri, R.; Giubilei, F.; Marra, C.; Caltagirone, C.; Cercignani, M. Damage to the cingulum contributes to Alzheimer’s disease pathophysiology by deafferentation mechanism. Hum. Brain. Mapp. 2012, 33, 1295–1308. [Google Scholar] [CrossRef] [PubMed]
- Bubb, E.J.; Metzler-Baddeley, C.; Aggleton, J.P. The cingulum bundle: Anatomy, function, and dysfunction. Neurosci. Biobehav. Rev. 2018, 92, 104–127. [Google Scholar] [CrossRef] [PubMed]
- Son, S.-J.; Kim, J.; Park, H. Structural and functional connectional fingerprints in mild cognitive impairment and Alzheimer’s disease patients. PLoS ONE 2017, 12, e0173426. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Zhao, H.; Li, X.; Wu, W.; Li, Z.; Qian, L.; Li, S.; Zhang, B.; Xu, Y. Atrophic patterns of the frontal-subcortical circuits in patients with mild cognitive impairment and Alzheimer’s disease. PLoS ONE 2015, 10, 1–14. [Google Scholar] [CrossRef] [Green Version]
- Neufang, S.; Akhrif, A.; Riedl, V.; Förstl, H.; Kurz, A.; Zimmer, C.; Sorg, C.; Wohlschläger, A.M. Disconnection of Frontal and Parietal Areas Contributes to Impaired Attention in Very Early Alzheimer’s Disease. J. Alzheimer’S Dis. 2011, 25, 309–321. [Google Scholar] [CrossRef] [PubMed]
- Bakkour, A.; Morris, J.C.; Wolk, D.A.; Dickerson, B.C. The effects of aging and Alzheimer’s disease on cerebral cortical anatomy: Specificity and differential relationships with cognition. Neuroimage 2013, 76, 332–344. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Adriaanse, S.M.; Binnewijzend, M.A.; Ossenkoppele, R.; Tijms, B.M.; van der Flier, W.M.; Koene, T.; Smits, L.L.; Wink, A.M.; Scheltens, P.; van Berckel, B.N.; et al. Widespread Disruption of Functional Brain Organization in Early-Onset Alzheimer’s Disease. PLoS ONE 2014, 9, e102995. [Google Scholar] [CrossRef]
- Jitsuishi, T.; Yamaguch, A. Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data. Sci. Rep. 2022, 12, 4284. [Google Scholar] [CrossRef]
Feature Name | Reference | Meaning |
---|---|---|
Degree | [24] | The number of edges incident to the vertex |
Node strength | [24] | Strength of node |
Diversity coefficient | [25] | Coefficient to measure the diversity of vertex |
Betweenness centrality | [26] | The number of times a node acts as a bridge along the shortest path between two other nodes |
K-coreness centrality | [27] | Used to identify the most important vertices within a graph use idea of K-core |
Subgraph centrality | [28] | Used to identify the most important vertices within subgraph |
Eigenvector centrality | [29] | A measure of the influence of a node in a network |
PageRank centrality | [30] | Used to identify the most important vertices within a graph use idea of PageRank |
Assortativity | [31] | Correlations between nodes of similar degree |
One measure of network small-worldness | [32] | A measure of a small-world network |
Classifier | ZNN (Train/Test) | NEWFM (Train/Test) | SVM (Train/Test) |
---|---|---|---|
A-NM | 98.9/97.7 | 88.6/87.3 | 86.9/83.8 |
N-AM | 93.4/84.8 | 77.1/72.7 | 83.6/81.8 |
M-AN | 82.6/72.7 | 67.6/63.8 | 76.1/71.7 |
Layer | 1st ZLU Layer (Train/Test) | 2nd ZLU Layer (Train/Test) | Output Layer (Train/Test) |
---|---|---|---|
A-NM | 82.9/79.7 | 93.7/82.8 | 98.9/97.7 |
N-AM | 75.0/64.8 | 84.7/72.45 | 93.4/84.8 |
M-AN | 64.1/59.5 | 73.8/64.1 | 82.6/72.7 |
Accuracy Rank of ROI | A-NM | N-AM | M-AN |
---|---|---|---|
1 | cingulum_mid_r | cingulum_mid_r | cingulum_mid_r |
2 | caudate_r | caudate_r | postcentral_l |
3 | caudate_l | amygdala_l | caudate_l |
4 | parietal_sup_l | frontal_sup_orb_l | parietal_sup_l |
5 | frontal_mid_r | caudate_l | frontal_mid_r |
6 | parietal_inf_l | parietal_sup_l | parietal_inf_l |
7 | frontal_mid_l | lingual_l | frontal_mid_l |
8 | cuneus_r | parahippocampal_l | lingual_l |
9 | postcentral_r | frontal_mid_r | postcentral_r |
10 | cuneus_l | parietal_inf_l | cuneus_l |
11 | frontal_inf_oper_r | thalamus_l | frontal_inf_oper_r |
12 | frontal_inf_tri_r | frontal_inf_oper_l | frontal_inf_tri_r |
13 | temporal_inf_r | frontal_mid_l | temporal_inf_r |
14 | parietal_sup_r | cuneus_r | parietal_sup_r |
15 | cingulum_mid_l | insula_l | cingulum_mid_l |
16 | frontal_sup_medial_r | postcentral_r | thalamus_l |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, B.; Lim, J.S. Zoom-In Neural Network Deep-Learning Model for Alzheimer’s Disease Assessments. Sensors 2022, 22, 8887. https://doi.org/10.3390/s22228887
Wang B, Lim JS. Zoom-In Neural Network Deep-Learning Model for Alzheimer’s Disease Assessments. Sensors. 2022; 22(22):8887. https://doi.org/10.3390/s22228887
Chicago/Turabian StyleWang, Bohyun, and Joon S. Lim. 2022. "Zoom-In Neural Network Deep-Learning Model for Alzheimer’s Disease Assessments" Sensors 22, no. 22: 8887. https://doi.org/10.3390/s22228887
APA StyleWang, B., & Lim, J. S. (2022). Zoom-In Neural Network Deep-Learning Model for Alzheimer’s Disease Assessments. Sensors, 22(22), 8887. https://doi.org/10.3390/s22228887