1
|
Kaplan E, Baygin M, Barua PD, Dogan S, Tuncer T, Altunisik E, Palmer EE, Acharya UR. ExHiF: Alzheimer's disease detection using exemplar histogram-based features with CT and MR images. Med Eng Phys 2023; 115:103971. [PMID: 37120169 DOI: 10.1016/j.medengphy.2023.103971] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Revised: 03/16/2023] [Accepted: 03/18/2023] [Indexed: 05/01/2023]
Abstract
PURPOSE The classification of medical images is an important priority for clinical research and helps to improve the diagnosis of various disorders. This work aims to classify the neuroradiological features of patients with Alzheimer's disease (AD) using an automatic hand-modeled method with high accuracy. MATERIALS AND METHOD This work uses two (private and public) datasets. The private dataset consists of 3807 magnetic resonance imaging (MRI) and computer tomography (CT) images belonging to two (normal and AD) classes. The second public (Kaggle AD) dataset contains 6400 MR images. The presented classification model comprises three fundamental phases: feature extraction using an exemplar hybrid feature extractor, neighborhood component analysis-based feature selection, and classification utilizing eight different classifiers. The novelty of this model is feature extraction. Vision transformers inspire this phase, and hence 16 exemplars are generated. Histogram-oriented gradients (HOG), local binary pattern (LBP) and local phase quantization (LPQ) feature extraction functions have been applied to each exemplar/patch and raw brain image. Finally, the created features are merged, and the best features are selected using neighborhood component analysis (NCA). These features are fed to eight classifiers to obtain highest classification performance using our proposed method. The presented image classification model uses exemplar histogram-based features; hence, it is called ExHiF. RESULTS We have developed the ExHiF model with a ten-fold cross-validation strategy using two (private and public) datasets with shallow classifiers. We have obtained 100% classification accuracy using cubic support vector machine (CSVM) and fine k nearest neighbor (FkNN) classifiers for both datasets. CONCLUSIONS Our developed model is ready to be validated with more datasets and has the potential to be employed in mental hospitals to assist neurologists in confirming their manual screening of AD using MRI/CT images.
Collapse
Affiliation(s)
- Ela Kaplan
- Department of Radiology, Adiyaman Training and Research Hospital, Adiyaman, Turkey
| | - Mehmet Baygin
- Department of Computer Engineering, College of Engineering, Ardahan University, Ardahan, Turkey
| | - Prabal D Barua
- Cogninet Australia, Sydney, NSW, 2010, Australia; School of Business (Information System), University of Southern Queensland, Australia; Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, 2007, Australia; Australian International Institute of Higher Education, Sydney, NSW, 2000, Australia; School of Science & Technology, University of New England, Australia; School of Biosciences, Taylor's University, Malaysia; School of Computing, SRM Institute of Science and Technology, India; School of Science and Technology, Kumamoto University, Japan; Sydney School of Education and Social work, University of Sydney, Australia
| | - Sengul Dogan
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey.
| | - Turker Tuncer
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey
| | - Erman Altunisik
- Department of Neurology, Adiyaman University Medicine Faculty, Adiyaman, Turkey
| | - Elizabeth Emma Palmer
- Department of Medical Genetics, Sydney Children's Hospital, High Street, Randwick, NSW, Australia
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia
| |
Collapse
|
2
|
Bagheri N, Mavoa S, Tabatabaei-Jafari H, Knibbs LD, Coffee NT, Salvador-Carulla L, Anstey KJ. The Impact of Built and Social Environmental Characteristics on Diagnosed and Estimated Future Risk of Dementia. J Alzheimers Dis 2021; 84:621-632. [PMID: 34569946 DOI: 10.3233/jad-210208] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022]
Abstract
BACKGROUND Dementia is a major global health challenge and the impact of built and social environments' characteristics on dementia risk have not yet been fully evaluated. OBJECTIVE To investigate associations between built and social environmental characteristics and diagnosed dementia cases and estimated dementia risk. METHODS We recruited 25,511 patients aged 65 and older from family physicians' practices. We calculated a dementia risk score based on risk and protective factors for patients not diagnosed with dementia. Our exposure variables were estimated for each statistical area level 1: social fragmentation, nitrogen dioxide, public open spaces, walkability, socio-economic status, and the length of main roads. We performed a multilevel mixed effect linear regression analysis to allow for the hierarchical nature of the data. RESULTS We found that a one standard deviation (1-SD) increase in NO2 and walkability score was associated with 10% higher odds of any versus no dementia (95% CI: 1%, 21% for NO2 and 0%, 22% for walkability score). For estimated future risk of dementia, a 1-SD increase in social fragmentation and NO2 was associated with a 1% increase in dementia risk (95% CI: 0, 1%). 1-SD increases in public open space and socioeconomic status were associated with 3% (95% CI: 0.95, 0.98) and 1% decreases (95% CI: 0.98, 0.99) in dementia risk, respectively. There was spatial heterogeneity in the pattern of diagnosed dementia and the estimated future risk of dementia. CONCLUSION Associations of neighborhood NO2 level, walkability, public open space, and social fragmentation with diagnosed dementia cases and estimated future risk of dementia were statistically significant, indicating the potential to reduce the risk through changes in built and social environments.
Collapse
Affiliation(s)
- Nasser Bagheri
- Centre for Mental Health Research, the Research School of Population Health, the Australian National University, Australia.,The Australian Geospatial Health Lab, Health Research Institute, The University of Canberra, Australia
| | - Suzanne Mavoa
- Melbourne School of Population and Global Health, the University of Melbourne, Australia
| | - Hossein Tabatabaei-Jafari
- Centre for Mental Health Research, the Research School of Population Health, the Australian National University, Australia
| | - Luke D Knibbs
- The School of Public Health, The University of Sydney, Australia
| | - Neil T Coffee
- The Australian Geospatial Health Lab, Health Research Institute, The University of Canberra, Australia
| | - Luis Salvador-Carulla
- Centre for Mental Health Research, the Research School of Population Health, the Australian National University, Australia.,Menzies Centre for Health Policy, Faculty of Medicine and Health, University of Sydney
| | - Kaarin J Anstey
- UNSW Ageing Futures Institute, the University of New South Wales, Australia.,Neuroscience Research Australia, Australia
| |
Collapse
|
3
|
Liu CC, Liu CH, Sun Y, Lee HJ, Tang LY, Chiu MJ. Rural-urban disparities in the prevalence of mild cognitive impairment and dementia in Taiwan: A door-to-door nationwide study. J Epidemiol 2021; 32:502-509. [PMID: 33840652 DOI: 10.2188/jea.je20200602] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND Screening or diagnosis for the elderly with dementia in rural regions might be delayed and underestimated due to limited utilization of healthcare resources. This study aimed to evaluate the disparities of prevalence and risk factors of mild cognitive impairment (MCI) and dementia between urban and rural residence. METHODS In this nationwide door-to-door survey, 10,432 participants aged 65 years and more were selected by computerized random sampling from all administrative districts in Taiwan and were assessed by an in-person interview. We calculated the prevalence of MCI and dementia with their risk factors examined by multivariable logistic regression. RESULTS The prevalence of dementia in rural, suburban, and urban areas among the elderly was 8.69% (95% CI, 8.68-8.69), 6.63% (95% CI, 6.62-6.63), and 4.46% (95% CI, 4.46-4.47), respectively. A similar rural-suburban-urban gradient relationship on the dementia prevalence was observed in any age and sex group. The rural/urban ratio was higher in women than in men for both MCI and dementia. Urbanization remained to be an independent factor for both MCI and dementia after adjustment for age, gender, education, lifestyle, and health status. The beneficial effects of exercise on dementia were more evident in rural areas than in urban ones. CONCLUSIONS Significantly higher prevalence of MCI and dementia were found in rural areas than in urban ones, especially for women. The odds of risk factors for MCI and dementia varied between urbanization statuses. Focus on the rural-urban inequality and the modification of associated factors specifically for different urbanization levels are needed.
Collapse
Affiliation(s)
- Chih-Ching Liu
- Department of Healthcare Administration, College of Medical and Health Science, Asia University
| | - Chien-Hui Liu
- School of Nursing, National Yang Ming Chiao Tung University
| | - Yu Sun
- Department of Neurology, En Chu Kong Hospital
| | | | | | - Ming-Jang Chiu
- Department of Neurology, National Taiwan University Hospital, College of Medicine, National Taiwan University.,Graduate Institute of Brain and Mind Sciences, College of Medicine, National Taiwan University.,Graduate Institute of Psychology, College of Science, National Taiwan University.,Graduate Institute of Biomedical Electronics and Bioinformatics; National Taiwan University
| |
Collapse
|
4
|
Automated Detection of Alzheimer's Disease Using Brain MRI Images- A Study with Various Feature Extraction Techniques. J Med Syst 2019; 43:302. [PMID: 31396722 DOI: 10.1007/s10916-019-1428-9] [Citation(s) in RCA: 82] [Impact Index Per Article: 16.4] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2019] [Accepted: 07/21/2019] [Indexed: 10/26/2022]
Abstract
The aim of this work is to develop a Computer-Aided-Brain-Diagnosis (CABD) system that can determine if a brain scan shows signs of Alzheimer's disease. The method utilizes Magnetic Resonance Imaging (MRI) for classification with several feature extraction techniques. MRI is a non-invasive procedure, widely adopted in hospitals to examine cognitive abnormalities. Images are acquired using the T2 imaging sequence. The paradigm consists of a series of quantitative techniques: filtering, feature extraction, Student's t-test based feature selection, and k-Nearest Neighbor (KNN) based classification. Additionally, a comparative analysis is done by implementing other feature extraction procedures that are described in the literature. Our findings suggest that the Shearlet Transform (ST) feature extraction technique offers improved results for Alzheimer's diagnosis as compared to alternative methods. The proposed CABD tool with the ST + KNN technique provided accuracy of 94.54%, precision of 88.33%, sensitivity of 96.30% and specificity of 93.64%. Furthermore, this tool also offered an accuracy, precision, sensitivity and specificity of 98.48%, 100%, 96.97% and 100%, respectively, with the benchmark MRI database.
Collapse
|
5
|
Elfaal W. Role of imaging in Alzheimer's disease. HAMDAN MEDICAL JOURNAL 2019. [DOI: 10.4103/hmj.hmj_44_18] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
|
6
|
Killin LOJ, Starr JM, Shiue IJ, Russ TC. Environmental risk factors for dementia: a systematic review. BMC Geriatr 2016; 16:175. [PMID: 27729011 PMCID: PMC5059894 DOI: 10.1186/s12877-016-0342-y] [Citation(s) in RCA: 218] [Impact Index Per Article: 27.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2016] [Accepted: 09/19/2016] [Indexed: 01/08/2023] Open
Abstract
BACKGROUND Dementia risk reduction is a major and growing public health priority. While certain modifiable risk factors for dementia have been identified, there remains a substantial proportion of unexplained risk. There is evidence that environmental risk factors may explain some of this risk. Thus, we present the first comprehensive systematic review of environmental risk factors for dementia. METHODS We searched the PubMed and Web of Science databases from their inception to January 2016, bibliographies of review articles, and articles related to publically available environmental data. Articles were included if they examined the association between an environmental risk factor and dementia. Studies with another outcome (for example, cognition), a physiological measure of the exposure, case studies, animal studies, and studies of nutrition were excluded. Data were extracted from individual studies which were, in turn, appraised for methodological quality. The strength and consistency of the overall evidence for each risk factor identified was assessed. RESULTS We screened 4784 studies and included 60 in the review. Risk factors were considered in six categories: air quality, toxic heavy metals, other metals, other trace elements, occupational-related exposures, and miscellaneous environmental factors. Few studies took a life course approach. There is at least moderate evidence implicating the following risk factors: air pollution; aluminium; silicon; selenium; pesticides; vitamin D deficiency; and electric and magnetic fields. CONCLUSIONS Studies varied widely in size and quality and therefore we must be circumspect in our conclusions. Nevertheless, this extensive review suggests that future research could focus on a short list of environmental risk factors for dementia. Furthermore, further robust, longitudinal studies with repeated measures of environmental exposures are required to confirm these associations.
Collapse
Affiliation(s)
- Lewis O. J. Killin
- Alzheimer Scotland Dementia Research Centre, University of Edinburgh, Edinburgh, UK
- Centre for Cognitive Ageing & Cognitive Epidemiology, University of Edinburgh, Edinburgh, UK
- Scottish Dementia Clinical Research Network, NHS Scotland, Perth, UK
| | - John M. Starr
- Alzheimer Scotland Dementia Research Centre, University of Edinburgh, Edinburgh, UK
- Centre for Cognitive Ageing & Cognitive Epidemiology, University of Edinburgh, Edinburgh, UK
| | - Ivy J. Shiue
- Alzheimer Scotland Dementia Research Centre, University of Edinburgh, Edinburgh, UK
- Faculty of Health and Life Sciences, Northumbria University, Newcastle-upon-Tyne, UK
| | - Tom C. Russ
- Alzheimer Scotland Dementia Research Centre, University of Edinburgh, Edinburgh, UK
- Centre for Cognitive Ageing & Cognitive Epidemiology, University of Edinburgh, Edinburgh, UK
- Centre for Dementia Prevention, University of Edinburgh, Edinburgh, UK
- Division of Psychiatry, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, UK
| |
Collapse
|
7
|
Winblad B, Amouyel P, Andrieu S, Ballard C, Brayne C, Brodaty H, Cedazo-Minguez A, Dubois B, Edvardsson D, Feldman H, Fratiglioni L, Frisoni GB, Gauthier S, Georges J, Graff C, Iqbal K, Jessen F, Johansson G, Jönsson L, Kivipelto M, Knapp M, Mangialasche F, Melis R, Nordberg A, Rikkert MO, Qiu C, Sakmar TP, Scheltens P, Schneider LS, Sperling R, Tjernberg LO, Waldemar G, Wimo A, Zetterberg H. Defeating Alzheimer's disease and other dementias: a priority for European science and society. Lancet Neurol 2016; 15:455-532. [DOI: 10.1016/s1474-4422(16)00062-4] [Citation(s) in RCA: 1001] [Impact Index Per Article: 125.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2015] [Revised: 10/06/2015] [Accepted: 02/09/2016] [Indexed: 12/15/2022]
|
8
|
Narayanan L, Murray AD. What is the role of neuroimaging in dementia? A review. IMAGING 2014. [DOI: 10.1259/img.20120015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
|
9
|
Russ TC, Batty GD, Hearnshaw GF, Fenton C, Starr JM. Geographical variation in dementia: systematic review with meta-analysis. Int J Epidemiol 2012; 41:1012-32. [PMID: 22798662 PMCID: PMC3429875 DOI: 10.1093/ije/dys103] [Citation(s) in RCA: 119] [Impact Index Per Article: 9.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/01/2012] [Indexed: 12/27/2022] Open
Abstract
BACKGROUND Geographical variation in dementia prevalence and incidence may indicate important socio-environmental contributions to dementia aetiology. However, previous comparisons have been hampered by combining studies with different methodologies. This review systematically collates and synthesizes studies examining geographical variation in the prevalence and incidence of dementia based on comparisons of studies using identical methodologies. METHODS Papers were identified by a comprehensive electronic search of relevant databases, scrutinising the reference sections of identified publications, contacting experts in the field and re-examining papers already known to us. Identified articles were independently reviewed against inclusion/exclusion criteria and considered according to geographical scale. Rural/urban comparisons were meta-analysed. RESULTS Twelve thousand five hundred and eighty records were reviewed and 51 articles were included. Dementia prevalence and incidence varies at a number of scales from the national down to small areas, including some evidence of an effect of rural living [prevalence odds ratio (OR) = 1.11, 90% confidence interval (CI) 0.79-1.57; incidence OR = 1.20, 90% CI 0.84-1.71]. However, this association of rurality was stronger for Alzheimer disease, particularly when early life rural living was captured (prevalence OR = 2.22, 90% CI 1.19-4.16; incidence OR = 1.64, 90% CI 1.08-2.50). CONCLUSIONS There is evidence of geographical variation in rates of dementia in affluent countries at a variety of geographical scales. Rural living is associated with an increased risk of Alzheimer disease, and there is a suggestion that early life rural living further increases this risk. However, the fact that few studies have been conducted in resource-poor countries limits conclusions.
Collapse
Affiliation(s)
- Tom C Russ
- Scottish Dementia Clinical Research Network, NHS Scotland, UK.
| | | | | | | | | |
Collapse
|