1
|
Kang S, Kim SW, Seong JK. Disentangling brain atrophy heterogeneity in Alzheimer's disease: A deep self-supervised approach with interpretable latent space. Neuroimage 2024; 297:120737. [PMID: 39004409 DOI: 10.1016/j.neuroimage.2024.120737] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Revised: 07/03/2024] [Accepted: 07/11/2024] [Indexed: 07/16/2024] Open
Abstract
Alzheimer's disease (AD) is heterogeneous, but existing methods for capturing this heterogeneity through dimensionality reduction and unsupervised clustering have limitations when it comes to extracting intricate atrophy patterns. In this study, we propose a deep learning based self-supervised framework that characterizes complex atrophy features using latent space representation. It integrates feature engineering, classification, and clustering to synergistically disentangle heterogeneity in Alzheimer's disease. Through this representation learning, we trained a clustered latent space with distinct atrophy patterns and clinical characteristics in AD, and replicated the findings in prodromal Alzheimer's disease. Moreover, we discovered that these clusters are not solely attributed to subtypes but also reflect disease progression in the latent space, representing the core dimensions of heterogeneity, namely progression and subtypes. Furthermore, longitudinal latent space analysis revealed two distinct disease progression pathways: medial temporal and parietotemporal pathways. The proposed approach enables effective latent representations that can be integrated with individual-level cognitive profiles, thereby facilitating a comprehensive understanding of AD heterogeneity.
Collapse
Affiliation(s)
- Sohyun Kang
- Department of Artificial Intelligence, College of Informatics, Korea University, Seoul, 02841, South Korea
| | - Sung-Woo Kim
- School of Biomedical Engineering, College of Health Science, Korea University, Seoul, 02841, South Korea; Department of Neurology, Wonju Severance Christian Hospital, Yonsei University Wonju College of Medicine, Wonju, 26426, South Korea; Research Institute of Metabolism and Inflammation, Yonsei University Wonju College of Medicine, Wonju, 26426, South Korea
| | - Joon-Kyung Seong
- Department of Artificial Intelligence, College of Informatics, Korea University, Seoul, 02841, South Korea; School of Biomedical Engineering, College of Health Science, Korea University, Seoul, 02841, South Korea; Interdisciplinary Program in Precision Public Health, College of Health Science, Korea University, Seoul, 02841, South Korea.
| |
Collapse
|
2
|
Vipin A, Lee BTK, Kumar D, Soo SA, Leow YJ, Ghildiyal S, Lee FPHE, Hilal S, Kandiah N. The role of perfusion, grey matter volume and behavioural phenotypes in the data-driven classification of cognitive syndromes. Alzheimers Res Ther 2024; 16:40. [PMID: 38368378 PMCID: PMC10874041 DOI: 10.1186/s13195-024-01410-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Accepted: 02/05/2024] [Indexed: 02/19/2024]
Abstract
BACKGROUND The use of structural and perfusion brain imaging in combination with behavioural information in the prediction of cognitive syndromes using a data-driven approach remains to be explored. Here, we thus examined the contribution of brain structural and perfusion imaging and behavioural features to the existing classification of cognitive syndromes using a data-driven approach. METHODS Study participants belonged to the community-based Biomarker and Cognition Cohort Study in Singapore who underwent neuropsychological assessments, structural-functional MRI and blood biomarkers. Participants had a diagnosis of cognitively normal (CN), subjective cognitive impairment (SCI), mild cognitive impairment (MCI) and dementia. Cross-sectional structural and cerebral perfusion imaging, behavioural scale data including mild behaviour impairment checklist, Pittsburgh Sleep Quality Index and Depression, Anxiety and Stress scale data were obtained. RESULTS Three hundred seventy-three participants (mean age 60.7 years; 56% female sex) with complete data were included. Principal component analyses demonstrated that no single modality was informative for the classification of cognitive syndromes. However, multivariate glmnet analyses revealed a specific combination of frontal perfusion and temporo-frontal grey matter volume were key protective factors while the severity of mild behaviour impairment interest sub-domain and poor sleep quality were key at-risk factors contributing to the classification of CN, SCI, MCI and dementia (p < 0.0001). Moreover, the glmnet model showed best classification accuracy in differentiating between CN and MCI cognitive syndromes (AUC = 0.704; sensitivity = 0.698; specificity = 0.637). CONCLUSIONS Brain structure, perfusion and behavioural features are important in the classification of cognitive syndromes and should be incorporated by clinicians and researchers. These findings illustrate the value of using multimodal data when examining syndrome severity and provide new insights into how cerebral perfusion and behavioural impairment influence classification of cognitive syndromes.
Collapse
Affiliation(s)
- Ashwati Vipin
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore
| | - Bernett Teck Kwong Lee
- Centre for Biomedical Informatics, 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, 308232, Singapore
| | - Dilip Kumar
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore
| | - See Ann Soo
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore
| | - Yi Jin Leow
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore
| | - Smriti Ghildiyal
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore
| | - Faith Phemie Hui En Lee
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore
| | - Saima Hilal
- Saw Swee Hock School of Public Health, Tahir Foundation Building, 12 Science Drive 2, National University of Singapore and National University Health System, Singapore, 117549, Singapore
- Duke-NUS Medical School, 8 College Road, Singapore, 169857, Singapore
| | - Nagaendran Kandiah
- Dementia Research Centre (Singapore), 11 Mandalay Road, Lee Kong Chian School of Medicine, Nanyang Technology University, Singapore, 308232, Singapore.
- Duke-NUS Medical School, 8 College Road, Singapore, 169857, Singapore.
| |
Collapse
|
3
|
Chen P, Zhang S, Zhao K, Kang X, Rittman T, Liu Y. Robustly uncovering the heterogeneity of neurodegenerative disease by using data-driven subtyping in neuroimaging: A review. Brain Res 2024; 1823:148675. [PMID: 37979603 DOI: 10.1016/j.brainres.2023.148675] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 10/19/2023] [Accepted: 11/07/2023] [Indexed: 11/20/2023]
Abstract
Neurodegenerative diseases are associated with heterogeneity in genetics, pathology, and clinical manifestation. Understanding this heterogeneity is particularly relevant for clinical prognosis and stratifying patients for disease modifying treatments. Recently, data-driven methods based on neuroimaging have been applied to investigate the subtyping of neurodegenerative disease, helping to disentangle this heterogeneity. We reviewed brain-based subtyping studies in aging and representative neurodegenerative diseases, including Alzheimer's disease, mild cognitive impairment, frontotemporal dementia, and Lewy body dementia, from January 2000 to November 2022. We summarized clustering methods, validation, robustness, reproducibility, and clinical relevance of 71 eligible studies in the present study. We found vast variations in approaches between studies, including ten neuroimaging modalities, 24 cluster algorithms, and 41 methods of cluster number determination. The clinical relevance of subtyping studies was evaluated by summarizing the analysis method of clinical measurements, showing a relatively low clinical utility in the current studies. Finally, we conclude that future studies of heterogeneity in neurodegenerative disease should focus on validation, comparison between subtyping approaches, and prioritise clinical utility.
Collapse
Affiliation(s)
- Pindong Chen
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China; Department of Clinical Neurosciences, University of Cambridge, Cambridge, Cambridgeshire, UK
| | - Shirui Zhang
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
| | - Kun Zhao
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
| | - Xiaopeng Kang
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Timothy Rittman
- Department of Clinical Neurosciences, University of Cambridge, Cambridge, Cambridgeshire, UK
| | - Yong Liu
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
| |
Collapse
|
4
|
Pacyna RR, Han SD, Wroblewski KE, McClintock MK, Pinto JM. Rapid olfactory decline during aging predicts dementia and GMV loss in AD brain regions. Alzheimers Dement 2022; 19:1479-1490. [PMID: 35899859 DOI: 10.1002/alz.12717] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Revised: 02/23/2022] [Accepted: 05/18/2022] [Indexed: 11/07/2022]
Abstract
INTRODUCTION Longitudinal multivariable analyses are needed to determine if the rate of olfactory decline during normal cognition predicts subsequent Alzheimer's disease (AD) diagnoses and brain dysmorphology. METHODS Older adults (n = 515) were assessed annually for odor identification, cognitive function and dementia clinical diagnosis (max follow-up 18 years). Regional gray matter volumes (GMV) were quantified (3T MRI) in a cross-sectional subsample (n = 121). Regression models were adjusted for APOE-ε4 genotype, dementia risk factors and demographics. RESULTS Faster olfactory decline during periods of normal cognition predicted higher incidence of subsequent MCI or dementia (OR 1.89, 95% CI: 1.26, 2.90, p < 0.01; comparable to carrying an APOE-ε4 allele) and smaller GMV in AD and olfactory regions (β = -0.11, 95% CI -0.21, -0.00). DISCUSSION Rapid olfactory decline during normal cognition, using repeated olfactory measurement, predicted subsequent cognitive impairment, dementia, and smaller GMVs, highlighting its potential as a simple biomarker for early AD detection. HIGHLIGHTS Rate of olfactory decline was calculated from olfactory testing over ≥3 time points. Rapid olfactory decline predicted impaired cognition and higher risk of dementia. Neurodegeneration on 3T magnetic resonance imaging was identical in those with olfactory decline and Alzheimer's disease.
Collapse
Affiliation(s)
- Rachel R Pacyna
- Pritzker, School of Medicine, The University of Chicago, Chicago, Illinois, USA
| | - S Duke Han
- Departments of Family Medicine, Neurology, Psychology, and Gerontology, University of Southern California, Alhambra, California, USA
| | - Kristen E Wroblewski
- Department of Public Health Sciences, The University of Chicago, Chicago, Illinois, USA
| | | | - Jayant M Pinto
- Department of Surgery, and Section of Otolaryngology-Head and Neck Surgery, The University of Chicago, Chicago, Illinois, USA
| |
Collapse
|
5
|
Chen P, Yao H, Tijms BM, Wang P, Wang D, Song C, Yang H, Zhang Z, Zhao K, Qu Y, Kang X, Du K, Fan L, Han T, Yu C, Zhang X, Jiang T, Zhou Y, Lu J, Han Y, Liu B, Zhou B, Liu Y. Four Distinct Subtypes of Alzheimer's Disease Based on Resting-State Connectivity Biomarkers. Biol Psychiatry 2022; 93:759-769. [PMID: 36137824 DOI: 10.1016/j.biopsych.2022.06.019] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Revised: 05/19/2022] [Accepted: 06/13/2022] [Indexed: 11/29/2022]
Abstract
BACKGROUND Alzheimer's disease (AD) is a neurodegenerative disorder with significant heterogeneity. Different AD phenotypes may be associated with specific brain network changes. Uncovering disease heterogeneity by using functional networks could provide insights into precise diagnoses. METHODS We investigated the subtypes of AD using nonnegative matrix factorization clustering on the previously identified 216 resting-state functional connectivities that differed between AD and normal control subjects. We conducted the analysis using a discovery dataset (n = 809) and a validated dataset (n = 291). Next, we grouped individuals with mild cognitive impairment according to the model obtained in the AD groups. Finally, the clinical measures and brain structural characteristics were compared among the subtypes to assess their relationship with differences in the functional network. RESULTS Individuals with AD were clustered into 4 subtypes reproducibly, which included those with 1) diffuse and mild functional connectivity disruption (subtype 1), 2) predominantly decreased connectivity in the default mode network accompanied by an increase in the prefrontal circuit (subtype 2), 3) predominantly decreased connectivity in the anterior cingulate cortex accompanied by an increase in prefrontal cortex connectivity (subtype 3), and 4) predominantly decreased connectivity in the basal ganglia accompanied by an increase in prefrontal cortex connectivity (subtype 4). In addition to these differences in functional connectivity, differences between the AD subtypes were found in cognition, structural measures, and cognitive decline patterns. CONCLUSIONS These comprehensive results offer new insights that may advance precision medicine for AD and facilitate strategies for future clinical trials.
Collapse
Affiliation(s)
- Pindong Chen
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Hongxiang Yao
- Department of Radiology, the Second Medical Centre, National Clinical Research Centre for Geriatric Diseases, Chinese PLA General Hospital, Beijing, China
| | - Betty M Tijms
- Alzheimer Center Amsterdam, Department of Neurology, Amsterdam Neuroscience, Vrije Universiteit Amsterdam, Amsterdam UMC - Location VUmc, The Netherlands
| | - Pan Wang
- Department of Neurology, Tianjin Huanhu Hospital, Tianjin University, Tianjin, China
| | - Dawei Wang
- Department of Radiology, Qilu Hospital of Shandong University, Ji'nan, China
| | - Chengyuan Song
- Department of Neurology, Qilu Hospital of Shandong University, Ji'nan, China
| | - Hongwei Yang
- Department of Radiology, Xuanwu Hospital of Capital Medical University, Beijing, China
| | | | - Kun Zhao
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science & Medical Engineering, Beihang University, Beijing, China
| | - Yida Qu
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Xiaopeng Kang
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Kai Du
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Lingzhong Fan
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Tong Han
- Department of Radiology, Tianjin Huanhu Hospital, Tianjin University, Tianjin, China
| | - Chunshui Yu
- Department of Radiology, Tianjin Medical University General Hospital, Tianjin, China
| | - Xi Zhang
- Department of Neurology, the Second Medical Centre, National Clinical Research Centre for Geriatric Diseases, Chinese PLA General Hospital, Beijing, China
| | - Tianzi Jiang
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Yuying Zhou
- Department of Neurology, Tianjin Huanhu Hospital, Tianjin University, Tianjin, China
| | - Jie Lu
- Department of Radiology, Xuanwu Hospital of Capital Medical University, Beijing, China
| | - Ying Han
- Department of Neurology, Xuanwu Hospital of Capital Medical University, Beijing, China; Beijing Institute of Geriatrics, Beijing, China; National Clinical Research Center for Geriatric Disorders, Beijing, China
| | - Bing Liu
- State Key Laboratory of Cognition Neuroscience & Learning, Beijing Normal University, Beijing, China
| | - Bo Zhou
- Department of Neurology, the Second Medical Centre, National Clinical Research Centre for Geriatric Diseases, Chinese PLA General Hospital, Beijing, China.
| | - Yong Liu
- Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
| | | |
Collapse
|
6
|
Imaging Clinical Subtypes and Associated Brain Networks in Alzheimer’s Disease. Brain Sci 2022; 12:brainsci12020146. [PMID: 35203910 PMCID: PMC8869882 DOI: 10.3390/brainsci12020146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2021] [Revised: 01/17/2022] [Accepted: 01/18/2022] [Indexed: 11/17/2022] Open
Abstract
Alzheimer’s disease (AD) does not present uniform symptoms or a uniform rate of progression in all cases. The classification of subtypes can be based on clinical symptoms or patterns of pathological brain alterations. Imaging techniques may allow for the identification of AD subtypes and their differentiation from other neurodegenerative diseases already at an early stage. In this review, the strengths and weaknesses of current clinical imaging methods are described. These include positron emission tomography (PET) to image cerebral glucose metabolism and pathological amyloid or tau deposits. Magnetic resonance imaging (MRI) is more widely available than PET. It provides information on structural or functional changes in brain networks and their relation to AD subtypes. Amyloid PET provides a very early marker of AD but does not distinguish between AD subtypes. Regional patterns of pathology related to AD subtypes are observed with tau and glucose PET, and eventually as atrophy patterns on MRI. Structural and functional network changes occur early in AD but have not yet provided diagnostic specificity.
Collapse
|
7
|
Planche V, Bouteloup V, Mangin JF, Dubois B, Delrieu J, Pasquier F, Blanc F, Paquet C, Hanon O, Gabelle A, Ceccaldi M, Annweiler C, Krolak-Salmon P, Habert MO, Fischer C, Chupin M, Béjot Y, Godefroy O, Wallon D, Sauvée M, Bourdel-Marchasson I, Jalenques I, Tison F, Chêne G, Dufouil C. Clinical relevance of brain atrophy subtypes categorization in memory clinics. Alzheimers Dement 2020; 17:641-652. [PMID: 33325121 DOI: 10.1002/alz.12231] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Revised: 10/14/2020] [Accepted: 10/19/2020] [Indexed: 12/14/2022]
Abstract
INTRODUCTION The clinical relevance of brain atrophy subtypes categorization in non-demented persons without a priori knowledge regarding their amyloid status or clinical presentation is unknown. METHODS A total of 2083 outpatients with either subjective cognitive complaint or mild cognitive impairment at study entry were followed during 4 years (MEMENTO cohort). Atrophy subtypes were defined using baseline magnetic resonance imaging (MRI) and previously described algorithms. RESULTS Typical/diffuse atrophy was associated with faster cognitive decline and the highest risk of developing dementia and Alzheimer's disease (AD) over time, both in the whole analytic sample and in amyloid-positive participants. Hippocampal-sparing and limbic-predominant atrophy were also associated with incident dementia, with faster cognitive decline in the limbic predominant atrophy group. Lewy body dementia was more frequent in the hippocampal-sparing and minimal/no atrophy groups. DISCUSSION Atrophy subtypes categorization predicted different subsequent patterns of cognitive decline and rates of conversion to distinct etiologies of dementia in persons attending memory clinics.
Collapse
Affiliation(s)
- Vincent Planche
- Univ. Bordeaux, CNRS UMR 5293, Institut des Maladies Neurodégénératives, Centre Mémoire de Ressources et de Recherches, Pôle de Neurosciences Cliniques, CHU de Bordeaux, Bordeaux, France
| | - Vincent Bouteloup
- Univ. Bordeaux, Inserm U1219, Institut de Santé Publique, d'Epidémiologie et de Développement (ISPED), Bordeaux, France
| | - Jean-François Mangin
- Univ. Paris-Saclay, CEA, CNRS, Baobab, Neurospin, CATI multicenter neuroimaging platform, Gif-sur-Yvette, France
| | - Bruno Dubois
- Sorbonne-Université, Service des maladies cognitives et comportementales et Institut de la mémoire et de la maladie d'Alzheimer (IM2A), Hôpital de la Salpêtrière, AP-PH, Paris, France
| | - Julien Delrieu
- Departement de Gériatrie, Univ. Toulouse, Inserm U1027, Gérontopôle, CHU Purpan, Toulouse, France
| | - Florence Pasquier
- Univ. Lille, Inserm U1171, Centre Mémoire de Ressources et de Recherches, CHU Lille, DISTAlz, Lille, France
| | - Frédéric Blanc
- ICube laboratory, Departement de Gériatrie, Univ. Strasbourg, CNRS, UMR 7357, Fédération de Médecine Translationnelle de Strasbourg, Centre Mémoire de Ressources et de Recherches, Strasbourg, France
| | - Claire Paquet
- Univ. Paris, Inserm U1144, Groupe Hospitalier Lariboisière Fernand-Widal, AP-HP, Paris, France
| | - Olivier Hanon
- Univ. Paris Descartes Sorbonne Paris Cité, EA 4468, Service de Gériatrie, AP-HP, Hôpital Broca, Paris, France
| | - Audrey Gabelle
- Département de Neurologie, Univ. Montpellier, i-site MUSE, Inserm U1061, Centre Mémoire de Ressources et de Recherches, Pôle de Neurosciences, CHU de Montpellier, Montpellier, France
| | - Matthieu Ceccaldi
- Département de Neurologie et de Neuropsychologie, Univ. Aix Marseille, Inserm UMR 1106, Institut de Neurosciences des Systèmes, Centre Mémoire de Ressources et de Recherches, AP-HM, Marseille, France
| | - Cédric Annweiler
- Département de Gériatrie, CHU d'Angers, Univ. Angers, UPRES EA 4638, Centre Mémoire de Ressources et de Recherches, Angers, France
| | - Pierre Krolak-Salmon
- Univ. Lyon, Inserm U1028, CNRS UMR5292, Centre de Recherche en Neurosciences de Lyon, Centre Mémoire Ressource et Recherche de Lyon (CMRR), Hôpital des Charpennes, Hospices Civils de Lyon, Lyon, France
| | - Marie-Odile Habert
- Laboratoire d'Imagerie Biomédicale, Sorbonne-Université, CNRS, Inserm, CATI multicenter neuroimaging platform, AP-HP, Hôpital Pitié-Salpêtrière, Médecine Nucléaire, Paris, France
| | - Clara Fischer
- Univ. Paris-Saclay, CEA, CNRS, Baobab, Neurospin, CATI multicenter neuroimaging platform, Gif-sur-Yvette, France
| | - Marie Chupin
- Sorbonne-Université, Inserm U1127, CNRS UMR 7225, CATI multicenter neuroimaging platform, Institut du Cerveau et de la Moelle épinière, Paris, France
| | - Yannick Béjot
- Univ. Bourgogne, EA7460, Centre Mémoire de Ressources et de Recherches, CHU Dijon Bourgogne, Dijon, France
| | - Olivier Godefroy
- Laboratoire de Neurosciences Fonctionnelles et Pathologies, Univ. Picardie, UR UPJV4559, Service de Neurologie, CHU Amiens, Amiens, France
| | - David Wallon
- Departement de Neurologie, Univ. Normandie, UNIROUEN, Inserm U1245, CNR-MAJ, CHU de Rouen, Rouen, France
| | - Mathilde Sauvée
- Centre Mémoire de Ressources et de Recherches Grenoble Arc Alpin, Pôle de Psychiatrie et Neurologie, CHU Grenoble, Grenoble, France
| | - Isabelle Bourdel-Marchasson
- Univ. Bordeaux, Inserm U1219, Institut de Santé Publique, d'Epidémiologie et de Développement (ISPED), Bordeaux, France
- Univ. Bordeaux, CNRS UMR 5536, Centre de Résonance Magnétique des Systèmes Biologiques, Pole de gérontologie clinique, CHU de Bordeaux, Bordeaux, France
| | - Isabelle Jalenques
- Univ. Clermont Auvergne, Centre Mémoire de Ressources et de Recherches, CHU de Clermont-Ferrand, Clermont-Ferrand, France
| | - François Tison
- Univ. Bordeaux, CNRS UMR 5293, Institut des Maladies Neurodégénératives, Centre Mémoire de Ressources et de Recherches, Pôle de Neurosciences Cliniques, CHU de Bordeaux, Bordeaux, France
| | - Geneviève Chêne
- Univ. Bordeaux, Inserm U1219, Institut de Santé Publique, d'Epidémiologie et de Développement (ISPED), Pôle de Sante Publique, CHU de Bordeaux, Bordeaux, France
| | - Carole Dufouil
- Univ. Bordeaux, Inserm U1219, Institut de Santé Publique, d'Epidémiologie et de Développement (ISPED), Pôle de Sante Publique, CHU de Bordeaux, Bordeaux, France
| |
Collapse
|
8
|
Lee JY, Oh SW, Chung MS, Park JE, Moon Y, Jeon HJ, Moon WJ. Clinically Available Software for Automatic Brain Volumetry: Comparisons of Volume Measurements and Validation of Intermethod Reliability. Korean J Radiol 2020; 22:405-414. [PMID: 33236539 PMCID: PMC7909859 DOI: 10.3348/kjr.2020.0518] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2020] [Revised: 06/08/2020] [Accepted: 06/17/2020] [Indexed: 01/18/2023] Open
Abstract
OBJECTIVE To compare two clinically available MR volumetry software, NeuroQuant® (NQ) and Inbrain® (IB), and examine the inter-method reliabilities and differences between them. MATERIALS AND METHODS This study included 172 subjects (age range, 55-88 years; mean age, 71.2 years), comprising 45 normal healthy subjects, 85 patients with mild cognitive impairment, and 42 patients with Alzheimer's disease. Magnetic resonance imaging scans were analyzed with IB and NQ. Mean differences were compared with the paired t test. Inter-method reliability was evaluated with Pearson's correlation coefficients and intraclass correlation coefficients (ICCs). Effect sizes were also obtained to document the standardized mean differences. RESULTS The paired t test showed significant volume differences in most regions except for the amygdala between the two methods. Nevertheless, inter-method measurements between IB and NQ showed good to excellent reliability (0.72 < r < 0.96, 0.83 < ICC < 0.98) except for the pallidum, which showed poor reliability (left: r = 0.03, ICC = 0.06; right: r = -0.05, ICC = -0.09). For the measurements of effect size, volume differences were large in most regions (0.05 < r < 6.15). The effect size was the largest in the pallidum and smallest in the cerebellum. CONCLUSION Comparisons between IB and NQ showed significantly different volume measurements with large effect sizes. However, they showed good to excellent inter-method reliability in volumetric measurements for all brain regions, with the exception of the pallidum. Clinicians using these commercial software should take into consideration that different volume measurements could be obtained depending on the software used.
Collapse
Affiliation(s)
- Ji Young Lee
- Department of Radiology, Hanyang University Medical Center, Seoul, Korea
| | - Se Won Oh
- Department of Radiology, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Mi Sun Chung
- Department of Radiology, Chung-Ang University Hospital, Seoul, Korea
| | - Ji Eun Park
- Department of Radiology, Asan Medical Center, Seoul, Korea
| | - Yeonsil Moon
- Department of Neurology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul, Korea
| | - Hong Jun Jeon
- Department of Psychiatry, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul, Korea
| | - Won Jin Moon
- Department of Radiology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul, Korea.
| |
Collapse
|
9
|
Habes M, Grothe MJ, Tunc B, McMillan C, Wolk DA, Davatzikos C. Disentangling Heterogeneity in Alzheimer's Disease and Related Dementias Using Data-Driven Methods. Biol Psychiatry 2020; 88:70-82. [PMID: 32201044 PMCID: PMC7305953 DOI: 10.1016/j.biopsych.2020.01.016] [Citation(s) in RCA: 88] [Impact Index Per Article: 22.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/07/2019] [Revised: 11/30/2019] [Accepted: 01/21/2020] [Indexed: 12/14/2022]
Abstract
Brain aging is a complex process that includes atrophy, vascular injury, and a variety of age-associated neurodegenerative pathologies, together determining an individual's course of cognitive decline. While Alzheimer's disease and related dementias contribute to the heterogeneity of brain aging, these conditions themselves are also heterogeneous in their clinical presentation, progression, and pattern of neural injury. We reviewed studies that leveraged data-driven approaches to examining heterogeneity in Alzheimer's disease and related dementias, with a principal focus on neuroimaging studies exploring subtypes of regional neurodegeneration patterns. Over the past decade, the steadily increasing wealth of clinical, neuroimaging, and molecular biomarker information collected within large-scale observational cohort studies has allowed for a richer understanding of the variability of disease expression within the aging and Alzheimer's disease and related dementias continuum. Moreover, the availability of these large-scale datasets has supported the development and increasing application of clustering techniques for studying disease heterogeneity in a data-driven manner. In particular, data-driven studies have led to new discoveries of previously unappreciated disease subtypes characterized by distinct neuroimaging patterns of regional neurodegeneration, which are paralleled by heterogeneous profiles of pathological, clinical, and molecular biomarker characteristics. Incorporating these findings into novel frameworks for more differentiated disease stratification holds great promise for improving individualized diagnosis and prognosis of expected clinical progression, and provides opportunities for development of precision medicine approaches for therapeutic intervention. We conclude with an account of the principal challenges associated with data-driven heterogeneity analyses and outline avenues for future developments in the field.
Collapse
Affiliation(s)
- Mohamad Habes
- Center for Biomedical Image Computing and Analytics, University of Pennsylvania, Philadelphia, Pennsylvania; Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania; Department of Neurology, University of Pennsylvania, Philadelphia, Pennsylvania; Penn Memory Center, Perelman Center for Advanced Medicine, University of Pennsylvania, Philadelphia, Pennsylvania; Biggs Institute Neuroimaging Core, Glenn Biggs Institute for Neurodegenerative Disorders, University of Texas Health Science Center at San Antonio, San Antonio, Texas.
| | - Michel J. Grothe
- German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany,Wallenberg Center for Molecular and Translational Medicine and the Department of Psychiatry and Neurochemistry, University of Gothenburg, Gothenburg, Sweden
| | - Birkan Tunc
- Department of Psychiatry, University of Pennsylvania, Philadelphia, USA
| | - Corey McMillan
- Department of Neurology and Penn FTD Center, University of Pennsylvania, Philadelphia, USA
| | - David A. Wolk
- Department of Neurology and Penn Memory Center, University of Pennsylvania, Philadelphia, USA
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics and Department of Radiology, University of Pennsylvania, Philadelphia, USA
| |
Collapse
|
10
|
Fu CHY, Fan Y, Davatzikos C. Widespread Morphometric Abnormalities in Major Depression: Neuroplasticity and Potential for Biomarker Development. Neuroimaging Clin N Am 2020; 30:85-95. [PMID: 31759575 PMCID: PMC7106506 DOI: 10.1016/j.nic.2019.09.008] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
Major depression is common and debilitating. Identifying neurobiological subtypes that comprise the disorder and predict clinical outcome are key challenges. Genetic and environmental factors leading to major depression are expressed in neural structure and function. Volumetric decreases in gray matter have been demonstrated in corticolimbic circuits involved in emotion regulation. MR imaging observable abnormalities reflect cytoarchitectonic alterations within a local neuroendocrine milieu with systemic effects. Multivariate pattern analysis offers the potential to identify the neurobiological subtypes and predictors of clinical outcome. It is essential to characterize disease heterogeneity by incorporating data-driven inductive and symptom-based deductive approaches in an iterative process.
Collapse
Affiliation(s)
- Cynthia H Y Fu
- School of Psychology, University of East London, Arthur Edwards Building, Water Lane, London E15 4LZ, UK; Centre for Affective Disorders, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
| | - Yong Fan
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
| |
Collapse
|
11
|
Application of an amyloid and tau classification system in subcortical vascular cognitive impairment patients. Eur J Nucl Med Mol Imaging 2019; 47:292-303. [DOI: 10.1007/s00259-019-04498-y] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2019] [Accepted: 08/21/2019] [Indexed: 10/26/2022]
|
12
|
Fu CHY, Fan Y, Davatzikos C. Addressing heterogeneity (and homogeneity) in treatment mechanisms in depression and the potential to develop diagnostic and predictive biomarkers. Neuroimage Clin 2019; 24:101997. [PMID: 31525565 PMCID: PMC6807387 DOI: 10.1016/j.nicl.2019.101997] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2019] [Revised: 08/09/2019] [Accepted: 08/27/2019] [Indexed: 01/26/2023]
Abstract
It has been 10 years since machine learning was first applied to neuroimaging data in psychiatric disorders to identify diagnostic and prognostic markers at the level of the individual. Proof of concept findings in major depression have since been extended in international samples and are beginning to include hundreds of samples from multisite data. Neuroimaging provides the unique capability to detect an acute depressive state in major depression, while we would not expect perfect classification with current diagnostic criteria which are based solely on clinical features. We review developments and the potential impact of heterogeneity, as well as homogeneity, on classification for diagnosis and prediction of clinical outcome. It is likely that there are distinct biotypes which comprise the disorder and which predict clinical outcome. Neuroimaging-based biotypes could aid in identifying the illness in individuals who are unable to recognise their illness and perhaps to identify the treatment resistant form early in the course of the illness. We propose that heterogeneous symptom profiles can arise from a limited number of neural biotypes and that apparently heterogeneous clinical outcomes include a common baseline predictor and common mechanism of treatment. Baseline predictors of clinical outcome reflect factors which indicate the general likelihood of response as well as those which are selective for a particular form of treatment. Irrespective of the mechanism, the capacity for response will moderate the outcome, which includes inherent models of interpersonal relationships that could be associated with genetic risk load and represented by patterns of functional and structural neural correlates as a predictive biomarker. We propose that methods which directly address heterogeneity are essential and that a synergistic combination could bring together data-driven inductive and symptom-based deductive approaches. Through this iterative process, major depression can develop from being syndrome characterized by a collection of symptoms to a disease with an identifiable pathophysiology.
Collapse
Affiliation(s)
- Cynthia H Y Fu
- School of Psychology, University of East London, London, UK; Centre for Affective Disorders, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
| | - Yong Fan
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, USA
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, USA
| |
Collapse
|
13
|
Planche V, Coupé P, Helmer C, Le Goff M, Amieva H, Tison F, Dartigues JF, Catheline G. Evolution of brain atrophy subtypes during aging predicts long-term cognitive decline and future Alzheimer's clinical syndrome. Neurobiol Aging 2019; 79:22-29. [DOI: 10.1016/j.neurobiolaging.2019.03.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2018] [Revised: 02/14/2019] [Accepted: 03/13/2019] [Indexed: 01/06/2023]
|