1
|
Mehmood A, Shahid F, Khan R, Ibrahim MM, Zheng Z. Utilizing Siamese 4D-AlzNet and Transfer Learning to Identify Stages of Alzheimer's Disease. Neuroscience 2024; 545:69-85. [PMID: 38492797 DOI: 10.1016/j.neuroscience.2024.03.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Revised: 03/05/2024] [Accepted: 03/10/2024] [Indexed: 03/18/2024]
Abstract
Alzheimer's disease (AD) is the general form of dementia, leading to a progressive neurological disorder characterized by memory loss due to brain cell damage. Artificial Intelligence (AI) assists in the early identification and prediction of AD patients, determining future risks and benefits for radiologists and doctors to save time and cost. Since deep learning (DL) approaches work well with massive datasets and have recently become helpful for AD detection, there remains an area for improvement in automating detection performance. Present approaches somehow addressed the challenges of limited annotated data samples for binary classification. This contrasts with prior state-of-the-art techniques, which were constrained by their incapacity to capture abstract-level information. In this paper, we proposed a Siamese 4D-AlzNet model comprised of four parallel convolutional neural network (CNN) streams (Five CNN layer blocks) and customized transfer learning models (Frozen VGG-19, Frozen VGG-16, and customized AlexNet). Siamese 4D-AlzNet was vertically and horizontally stored, and the spatial features were passed to the final layer for classification. For experiments, T1-weighted MRI images comprised of four distinct subject classes, normal control (NC), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI), and AD, have been employed. Our proposed models achieved outstanding accuracy, with a remarkable 95.05% accuracy distinguishing between normal and AD subjects. The performance across remaining binary class pairs consistently exceeded 90%. We thoroughly compared our model with the latest methods using the same dataset as our reference. Our proposed model improved NC-AD and MCI-AD classification accuracy by 2% 7%.
Collapse
Affiliation(s)
- Atif Mehmood
- School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China; Zhejiang Institute of Photoelectronics & Zhejiang Institute for Advanced Light Source, Zhejiang Normal University, Jinhua, Zhejiang 321004, China
| | - Farah Shahid
- School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China; Zhejiang Institute of Photoelectronics & Zhejiang Institute for Advanced Light Source, Zhejiang Normal University, Jinhua, Zhejiang 321004, China.
| | - Rizwan Khan
- School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China
| | - Mostafa M Ibrahim
- Department of Electrical Engineering, Faculty of Engineering, Minia University, Minia 61519, Egypt
| | - Zhonglong Zheng
- School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China.
| |
Collapse
|
2
|
Kang DW, Wang SM, Um YH, Na HR, Kim NY, Lee CU, Lim HK. Distinctive Association of the Functional Connectivity of the Posterior Cingulate Cortex on Memory Performances in Early and Late Amnestic Mild Cognitive Impairment Patients. Front Aging Neurosci 2021; 13:696735. [PMID: 34276347 PMCID: PMC8281268 DOI: 10.3389/fnagi.2021.696735] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2021] [Accepted: 05/31/2021] [Indexed: 11/16/2022] Open
Abstract
Background Attempts have been made to explore the biological basis of neurodegeneration in the amnestic mild cognitive impairment (MCI) stage, subdivided by memory performance. However, few studies have evaluated the differential impact of functional connectivity (FC) on memory performances in early- and late-MCI patients. Objective This study aims to explore the difference in FC of the posterior cingulate cortex (PCC) among healthy controls (HC) (n = 37), early-MCI patients (n = 30), and late-MCI patients (n = 35) and to evaluate a group-memory performance interaction against the FC of PCC. Methods The subjects underwent resting-state functional MRI scanning and a battery of neuropsychological tests. Results A significant difference among the three groups was found in FC between the PCC (seed region) and bilateral crus cerebellum, right superior medial frontal gyrus, superior temporal gyrus, and left middle cingulate gyrus (Monte Carlo simulation-corrected p < 0.01; cluster p < 0.05). Additionally, the early-MCI patients displayed higher FC values than the HC and late-MCI patients in the right superior medial frontal gyrus, cerebellum crus 1, and left cerebellum crus 2 (Bonferroni-corrected p < 0.05). Furthermore, there was a significant group-memory performance interaction (HC vs. early MCI vs. late MCI) for the FC between PCC and bilateral crus cerebellum, right superior medial frontal gyrus, superior temporal gyrus, and left middle cingulate gyrus (Bonferroni-corrected p < 0.05). Conclusion These findings contribute to the biological implications of early- and late-MCI stages, categorized by evaluating the impairment of memory performance. Additionally, comprehensively analyzing the structural differences in the subdivided amnestic MCI (aMCI) stages could deepen our understanding of these biological meanings.
Collapse
Affiliation(s)
- Dong Woo Kang
- Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Sheng-Min Wang
- Department of Psychiatry, Yeouido St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Yoo Hyun Um
- Department of Psychiatry, St. Vincent's Hospital, College of Medicine, The Catholic University of Korea, Suwon, South Korea
| | - Hae-Ran Na
- Department of Psychiatry, Yeouido St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Nak-Young Kim
- Department of Psychiatry, Keyo Hospital, Uiwang, South Korea
| | - Chang Uk Lee
- Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Hyun Kook Lim
- Department of Psychiatry, Yeouido St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| |
Collapse
|
3
|
Xu W, Rao J, Song Y, Chen S, Xue C, Hu G, Lin X, Chen J. Altered Functional Connectivity of the Basal Nucleus of Meynert in Subjective Cognitive Impairment, Early Mild Cognitive Impairment, and Late Mild Cognitive Impairment. Front Aging Neurosci 2021; 13:671351. [PMID: 34248603 PMCID: PMC8267913 DOI: 10.3389/fnagi.2021.671351] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2021] [Accepted: 05/11/2021] [Indexed: 01/10/2023] Open
Abstract
Background: The spectrum of early Alzheimer's disease (AD) is thought to include subjective cognitive impairment, early mild cognitive impairment (eMCI), and late mild cognitive impairment (lMCI). Choline dysfunction affects the early progression of AD, in which the basal nucleus of Meynert (BNM) is primarily responsible for cortical cholinergic innervation. The aims of this study were to determine the abnormal patterns of BNM-functional connectivity (BNM-FC) in the preclinical AD spectrum (SCD, eMCI, and lMCI) and further explore the relationships between these alterations and neuropsychological measures. Methods: Resting-state functional magnetic resonance imaging (rs-fMRI) was used to investigate FC based on a seed mask (BNM mask) in 28 healthy controls (HC), 30 SCD, 24 eMCI, and 25 lMCI patients. Furthermore, the relationship between altered FC and neurocognitive performance was examined by a correlation analysis. The receiver operating characteristic (ROC) curve of abnormal BNM-FC was used to specifically determine the classification ability to differentiate the early AD disease spectrum relative to HC (SCD and HC, eMCI and HC, lMCI and HC) and pairs of groups in the AD disease spectrum (eMCI and SCD, lMCI and SCD, eMCI and lMCI). Results: Compared with HC, SCD patients showed increased FC in the bilateral SMA and decreased FC in the bilateral cerebellum and middle frontal gyrus (MFG), eMCI patients showed significantly decreased FC in the bilateral precuneus, and lMCI individuals showed decreased FC in the right lingual gyrus. Compared with the SCD group, the eMCI group showed decreased FC in the right superior frontal gyrus (SFG), while the lMCI group showed decreased FC in the left middle temporal gyrus (MTG). Compared with the eMCI group, the lMCI group showed decreased FC in the right hippocampus. Interestingly, abnormal FC was associated with certain cognitive domains and functions including episodic memory, executive function, information processing speed, and visuospatial function in the disease groups. BNM-FC of SFG in distinguishing eMCI from SCD; BNM-FC of MTG in distinguishing lMCI from SCD; BNM-FC of the MTG, hippocampus, and cerebellum in distinguishing SCD from HC; and BNM-FC of the hippocampus and MFG in distinguishing eMCI from lMCI have high sensitivity and specificity. Conclusions: The abnormal BNM-FC patterns can characterize the early disease spectrum of AD (SCD, eMCI, and lMCI) and are closely related to the cognitive domains. These new and reliable findings will provide a new perspective in identifying the early disease spectrum of AD and further strengthen the role of cholinergic theory in AD.
Collapse
Affiliation(s)
- Wenwen Xu
- Department of Neurology, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Jiang Rao
- Department of Rehabilitation, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Yu Song
- Department of Neurology, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Shanshan Chen
- Department of Neurology, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Chen Xue
- Department of Radiology, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Guanjie Hu
- Institute of Neuropsychiatry, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China.,Institute of Brain Functional Imaging, Nanjing Medical University, Nanjing, China
| | - Xingjian Lin
- Department of Neurology, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Jiu Chen
- Institute of Neuropsychiatry, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China.,Institute of Brain Functional Imaging, Nanjing Medical University, Nanjing, China
| |
Collapse
|
4
|
Kang DW, Lim HK, Joo SH, Lee NR, Lee CU. Differential Associations Between Volumes of Atrophic Cortical Brain Regions and Memory Performances in Early and Late Mild Cognitive Impairment. Front Aging Neurosci 2019; 11:245. [PMID: 31551759 PMCID: PMC6738351 DOI: 10.3389/fnagi.2019.00245] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2018] [Accepted: 08/20/2019] [Indexed: 11/13/2022] Open
Abstract
Background Early and late mild cognitive impairment (MCI) patients have been reported to have a distinctive prognosis of converting to Alzheimer’s disease. Objective To evaluate the difference in gray matter volume and assess the association between cognitive function evaluated by comprehensive cognitive function test, and cortical thickness across healthy controls (HCs) (n = 37), early (n = 30), and late MCI patients (n = 35). Methods Differences in gray matter volume were evaluated by whole brain voxel-based morphometry across the groups. Multiple regression analysis was used to analyze group by memory performance interactions for the normalized gray matter volume. Results The early MCI group showed reduced gray matter volume in the right middle temporal gyrus in comparison to the HC group. The late MCI group displayed atrophy in the left parahippocampal gyrus in comparison to the HC group. Late MCI patients exhibited a decreased gray matter volume in the left fusiform gyrus in comparison to patients in the early MCI group (Monte Carlo simulation corrected p < 0.01, Tukey post hoc tests). Furthermore, there was a significant group (HC vs. early MCI) by memory performance interaction for the normalized cortical volume of the right middle temporal gyrus. Additionally, a significant group (early MCI vs. late MCI) by memory performance interaction was found for the normalized gray matter volume of the left fusiform gyrus (p < 0.001). Conclusion Early and late MCI patients showed distinctive associations of gray matter volumes in compensatory brain regions with memory performances. The findings can contribute to a better understanding of the structural changes in compensatory brain regions to elucidate memory decline in the trajectory of the subdivided prodromal stages of the Alzheimer’s disease (AD).
Collapse
Affiliation(s)
- Dong Woo Kang
- Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Hyun Kook Lim
- Department of Psychiatry, Yeouido St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Soo-Hyun Joo
- Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Na Rae Lee
- Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Chang Uk Lee
- Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| |
Collapse
|
5
|
Motter JN, Pelton GH, D’Antonio K, Rushia SN, Pimontel MA, Petrella JR, Garcon E, Ciovacco MW, Sneed JR, Doraiswamy PM, Devanand DP. Clinical and radiological characteristics of early versus late mild cognitive impairment in patients with comorbid depressive disorder. Int J Geriatr Psychiatry 2018; 33:1604-1612. [PMID: 30035339 PMCID: PMC6246783 DOI: 10.1002/gps.4955] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/22/2017] [Accepted: 06/17/2018] [Indexed: 01/28/2023]
Abstract
OBJECTIVE The classification of mild cognitive impairment (MCI) continues to be debated though it has recently been subtyped into late (LMCI) versus early (EMCI) stages. Older adults presenting with both a depressive disorder (DEP) and cognitive impairment (CI) represent a unique, understudied population. Our aim was to examine baseline characteristics of DEP-CI patients in the DOTCODE trial, a randomized controlled trial of open antidepressant treatment for 16 weeks followed by add-on donepezil or placebo for 62 weeks. METHODS/DESIGN Key inclusion criteria were diagnosis of major depression or dysthymic disorder with Hamilton Depression Rating Scale (HAM-D) score >14, and cognitive impairment defined by MMSE score ≥21 and impaired performance on the WMS-R Logical Memory II test. Patients were classified as EMCI or LMCI based on the 1.5 SD cutoff on tests of verbal memory, and compared on baseline clinical, neuropsychological, and anatomical characteristics. RESULTS Seventy-nine DEP-CI patients were recruited of whom 39 met criteria for EMCI and 40 for LMCI. The mean age was 68.9, and mean HAM-D was 23.0. Late mild cognitive impairment patients had significantly worse ADAS-Cog (P < .001), MMSE (P = .004), Block Design (P = .024), Visual Rep II (P = .006), CFL Animal (P = .006), UPSIT (P = .051), as well as smaller right hippocampal volume (P = .037) compared to EMCI patients. MRI indices of cerebrovascular disease did not differ between EMCI and LMCI patients. CONCLUSIONS Cognitive and neuronal loss markers differed between EMCI and LMCI among patients with DEP-CI, with LMCI being more likely to have the clinical and neuronal loss markers known to be associated with Alzheimer's disease.
Collapse
Affiliation(s)
- Jeffrey N. Motter
- The Graduate Center, City University of New York,Queens College, City University of New York
| | | | | | - Sara N. Rushia
- The Graduate Center, City University of New York,Queens College, City University of New York
| | - Monique A. Pimontel
- The Graduate Center, City University of New York,Queens College, City University of New York
| | | | - Ernst Garcon
- Columbia University and the New York State Psychiatric Institute
| | | | - Joel R. Sneed
- The Graduate Center, City University of New York,Queens College, City University of New York,Columbia University and the New York State Psychiatric Institute
| | | | - Davangere P. Devanand
- Columbia University and the New York State Psychiatric Institute,Correspondence: D. P. Devanand, MD, Department of Psychiatry, Division of Geriatric Psychiatry, 1051 Riverside Drive, Unit 98, New York, NY 10032,
| |
Collapse
|
6
|
Abstract
BACKGROUND: Mild Cognitive Impairment (MCI) has been considered to have a high risk in converting into Alzheimer’s Disease (AD). Previous studies showed that AD was associated with changes in resting-state networks (RSNs). However, few studies have evaluated the altered functional connectivity in early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI). OBJECTIVE: The aim of this work was to evaluate the impaired network functional connectivity with the disease progression. METHODS: In this paper, we evaluated the impaired function connectivity with the progression of disease based on a priori defined 246 regions of interest based on Brainnetome Atlas. Connectivity analysis based on three levels (node integrity, intra-network, and inter-network) was conducted. RESULTS: Altered function connectivity was detected in several RSNs. These results provided insights into the dysfunction of more RSNs accompany the progression of AD. We also found that one brain region may belong to multiple RSNs and contribute to achieving different network function. CONCLUSIONS: The aberrant intra- and inter-network dysfunctions might be potential biomarkers or predictors of MCI and AD progression and provide new insight into the pathophysiology of these diseases.
Collapse
Affiliation(s)
- Yongxin Zhang
- Postdoctoral Programme of Management Science and Engineering, Shandong Normal University, Jinan, Shandong, China.,School of Mathematics and Statistics, Shandong Normal University, Jinan, Shandong, China
| | - Xiyu Liu
- School of Management Science and Engineering, Shandong Normal University, Jinan, Shandong, China
| | - Kun Zhao
- School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China
| | - Lin Li
- School of Mathematics and Statistics, Shandong Normal University, Jinan, Shandong, China
| | - Yanhui Ding
- School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China
| |
Collapse
|
7
|
Xiang J, Guo H, Cao R, Liang H, Chen J. An abnormal resting-state functional brain network indicates progression towards Alzheimer's disease. Neural Regen Res 2014; 8:2789-99. [PMID: 25206600 PMCID: PMC4146017 DOI: 10.3969/j.issn.1673-5374.2013.30.001] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2013] [Accepted: 08/28/2013] [Indexed: 11/18/2022] Open
Abstract
Brain structure and cognitive function change in the temporal lobe, hippocampus, and prefrontal cortex of patients with mild cognitive impairment and Alzheimer's disease, and brain network-connection strength, network efficiency, and nodal attributes are abnormal. However, existing research has only analyzed the differences between these patients and normal controls. In this study, we constructed brain networks using resting-state functional MRI data that was extracted from four populations (normal controls, patients with early mild cognitive impairment, patients with late mild cognitive impairment, and patients with Alzheimer's disease) using the Alzheimer's Disease Neuroimaging Initiative data set. The aim was to analyze the characteristics of resting-state functional neural networks, and to observe mild cognitive impairment at different stages before the transformation to Alzheimer's disease. Results showed that as cognitive deficits increased across the four groups, the shortest path in the resting-state functional network gradually increased, while clustering coefficients gradually decreased. This evidence indicates that dementia is associated with a decline of brain network efficiency. In addition, the changes in functional networks revealed the progressive deterioration of network function across brain regions from healthy elderly adults to those with mild cognitive impairment and Alzheimer's disease. The alterations of node attributes in brain regions may reflect the cognitive functions in brain regions, and we speculate that early impairments in memory, hearing, and language function can eventually lead to diffuse brain injury and other cognitive impairments.
Collapse
Affiliation(s)
- Jie Xiang
- College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, Shanxi Province, China ; International WIC Institute, Beijing University of Technology, Beijing 100022, China
| | - Hao Guo
- College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, Shanxi Province, China
| | - Rui Cao
- College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, Shanxi Province, China
| | - Hong Liang
- College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, Shanxi Province, China
| | - Junjie Chen
- College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, Shanxi Province, China
| |
Collapse
|