1
|
Yu Y, Cui H, Haas SS, New F, Sanford N, Yu K, Zhan D, Yang G, Gao J, Wei D, Qiu J, Banaj N, Boomsma DI, Breier A, Brodaty H, Buckner RL, Buitelaar JK, Cannon DM, Caseras X, Clark VP, Conrod PJ, Crivello F, Crone EA, Dannlowski U, Davey CG, de Haan L, de Zubicaray GI, Di Giorgio A, Fisch L, Fisher SE, Franke B, Glahn DC, Grotegerd D, Gruber O, Gur RE, Gur RC, Hahn T, Harrison BJ, Hatton S, Hickie IB, Hulshoff Pol HE, Jamieson AJ, Jernigan TL, Jiang J, Kalnin AJ, Kang S, Kochan NA, Kraus A, Lagopoulos J, Lazaro L, McDonald BC, McDonald C, McMahon KL, Mwangi B, Piras F, Rodriguez‐Cruces R, Royer J, Sachdev PS, Satterthwaite TD, Saykin AJ, Schumann G, Sevaggi P, Smoller JW, Soares JC, Spalletta G, Tamnes CK, Trollor JN, Van't Ent D, Vecchio D, Walter H, Wang Y, Weber B, Wen W, Wierenga LM, Williams SCR, Wu M, Zunta‐Soares GB, Bernhardt B, Thompson P, Frangou S, Ge R. Brain-age prediction: Systematic evaluation of site effects, and sample age range and size. Hum Brain Mapp 2024; 45:e26768. [PMID: 38949537 PMCID: PMC11215839 DOI: 10.1002/hbm.26768] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Revised: 05/15/2024] [Accepted: 06/10/2024] [Indexed: 07/02/2024] Open
Abstract
Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.
Collapse
Affiliation(s)
- Yuetong Yu
- Djavad Mowafaghian Centre for Brain Health, Department of PsychiatryUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | - Hao‐Qi Cui
- Djavad Mowafaghian Centre for Brain Health, Department of PsychiatryUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | - Shalaila S. Haas
- Department of PsychiatryIcahn School of Medicine at Mount SinaiNew YorkNew YorkUSA
| | - Faye New
- Department of PsychiatryIcahn School of Medicine at Mount SinaiNew YorkNew YorkUSA
| | - Nicole Sanford
- Djavad Mowafaghian Centre for Brain Health, Department of PsychiatryUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | - Kevin Yu
- Djavad Mowafaghian Centre for Brain Health, Department of PsychiatryUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | - Denghuang Zhan
- School of Population and Public HealthUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | - Guoyuan Yang
- Advanced Research Institute of Multidisciplinary Sciences, School of Medical Technology, School of Life ScienceBeijing Institute of TechnologyBeijingChina
| | - Jia‐Hong Gao
- Center for MRI ResearchPeking UniversityBeijingChina
| | - Dongtao Wei
- School of PsychologySouthwest UniversityChongqingChina
| | - Jiang Qiu
- School of PsychologySouthwest UniversityChongqingChina
| | - Nerisa Banaj
- Laboratory of Neuropsychiatry, Department of Clinical and Behavioral NeurologyIRCCS Santa Lucia FoundationRomeItaly
| | - Dorret I. Boomsma
- Department of Biological PsychologyVrije Universiteit AmsterdamAmsterdamThe Netherlands
| | - Alan Breier
- Department of PsychiatryIndiana University School of MedicineIndianapolisIndianaUSA
| | - Henry Brodaty
- Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
| | - Randy L. Buckner
- Department of Psychology, Center for Brain ScienceHarvard UniversityBostonMassachusettsUSA
- Department of Psychiatry, Massachusetts General HospitalHarvard Medical SchoolBostonMassachusettsUSA
| | - Jan K. Buitelaar
- Department of Cognitive NeuroscienceDonders Institute for Brain, Cognition and Behaviour, Radboud University Medical CenterNijmegenThe Netherlands
| | - Dara M. Cannon
- Centre for Neuroimaging & Cognitive Genomics (NICOG), Clinical Neuroimaging Laboratory, Galway Neuroscience CentreCollege of Medicine Nursing and Health Sciences, University of GalwayGalwayIreland
| | - Xavier Caseras
- Centre for Neuropsychiatric Genetics and Genomics, Division of Psychological Medicine and Clinical NeurosciencesCardiff UniversityCardiffUK
| | - Vincent P. Clark
- Psychology Clinical Neuroscience Center, Department of PsychologyUniversity of New MexicoAlbuquerqueNew MexicoUSA
| | - Patricia J. Conrod
- Department of Psychiatry and AddictionUniversité de Montréal, CHU Ste JustineMontrealQuebecCanada
| | - Fabrice Crivello
- Institut des Maladies NeurodégénérativesUniversité de BordeauxBordeauxFrance
| | - Eveline A. Crone
- Department of Psychology, Faculty of Social SciencesLeiden UniversityLeidenThe Netherlands
- Erasmus School of Social and Behavioral SciencesErasmus University RotterdamRotterdamThe Netherlands
| | - Udo Dannlowski
- Institute for Translational PsychiatryUniversity of MünsterMünsterGermany
| | | | - Lieuwe de Haan
- Department of PsychiatryAmsterdam UMCAmsterdamThe Netherlands
| | - Greig I. de Zubicaray
- Faculty of Health, School of Psychology & CounsellingQueensland University of TechnologyBrisbaneQueenslandAustralia
| | | | - Lukas Fisch
- Institute for Translational PsychiatryUniversity of MünsterMünsterGermany
| | - Simon E. Fisher
- Language and Genetics DepartmentMax Planck Institute for PsycholinguisticsNijmegenThe Netherlands
- Donders Institute for Brain, Cognition and BehaviourRadboud UniversityNijmegenThe Netherlands
| | - Barbara Franke
- Donders Institute for Brain, Cognition and BehaviourRadboud UniversityNijmegenThe Netherlands
- Department of Cognitive NeuroscienceRadboud University Medical CenterNijmegenThe Netherlands
- Department of Human GeneticsRadboud University Medical CenterNijmegenThe Netherlands
| | - David C. Glahn
- Department of Psychiatry, Tommy Fuss Center for Neuropsychiatric Disease Research, Boston Children's HospitalHarvard Medical SchoolBostonMassachusettsUSA
| | - Dominik Grotegerd
- Institute for Translational PsychiatryUniversity of MünsterMünsterGermany
| | - Oliver Gruber
- Section for Experimental Psychopathology and Neuroimaging, Department of General PsychiatryHeidelberg UniversityHeidelbergGermany
| | - Raquel E. Gur
- Department of PsychiatryUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Ruben C. Gur
- Department of PsychiatryUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Tim Hahn
- Institute for Translational PsychiatryUniversity of MünsterMünsterGermany
| | - Ben J. Harrison
- Department of PsychiatryThe University of MelbourneMelbourneVictoriaAustralia
| | - Sean Hatton
- Brain and Mind CentreThe University of SydneySydneyNew South WalesAustralia
| | - Ian B. Hickie
- Brain and Mind CentreThe University of SydneySydneyNew South WalesAustralia
| | - Hilleke E. Hulshoff Pol
- Department of PsychiatryIcahn School of Medicine at Mount SinaiNew YorkNew YorkUSA
- Department of PsychologyUtrecht UniversityUtrechtThe Netherlands
- Department of PsychiatryUniversity Medical Center UtrechtUtrechtThe Netherlands
| | - Alec J. Jamieson
- Department of PsychiatryThe University of MelbourneMelbourneVictoriaAustralia
| | - Terry L. Jernigan
- Center for Human Development, Departments of Cognitive Science, Psychiatry, and RadiologyUniversity of CaliforniaSan DiegoCaliforniaUSA
| | - Jiyang Jiang
- Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
| | - Andrew J. Kalnin
- Department of RadiologyThe Ohio State University College of MedicineColumbusOhioUSA
| | - Sim Kang
- West Region, Institute of Mental HealthSingaporeSingapore
| | - Nicole A. Kochan
- Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
| | - Anna Kraus
- Institute for Translational PsychiatryUniversity of MünsterMünsterGermany
| | - Jim Lagopoulos
- Brain and Mind CentreThe University of SydneySydneyNew South WalesAustralia
| | - Luisa Lazaro
- Department of Child and Adolescent Psychiatry and PsychologyHospital Clínic, IDIBAPS, CIBERSAM, University of BarcelonaBarcelonaSpain
| | - Brenna C. McDonald
- Department of Radiology and Imaging SciencesIndiana University School of MedicineIndianapolisIndianaUSA
| | - Colm McDonald
- Centre for Neuroimaging & Cognitive Genomics (NICOG), Clinical Neuroimaging Laboratory, Galway Neuroscience CentreCollege of Medicine Nursing and Health Sciences, University of GalwayGalwayIreland
| | - Katie L. McMahon
- School of Clinical Sciences, Centre for Biomedical TechnologiesQueensland University of TechnologyBrisbaneQueenslandAustralia
| | - Benson Mwangi
- Louis A. Faillace, MD, Department of Psychiatry and Behavioral SciencesThe University of Texas Health Science Center at HoustonHoustonTexasUSA
| | - Fabrizio Piras
- Laboratory of Neuropsychiatry, Department of Clinical and Behavioral NeurologyIRCCS Santa Lucia FoundationRomeItaly
| | | | - Jessica Royer
- McConnell Brain Imaging CentreMcGill UniversityMontrealQuebecCanada
| | - Perminder S. Sachdev
- Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
| | | | - Andrew J. Saykin
- Department of Radiology and Imaging SciencesIndiana University School of MedicineIndianapolisIndianaUSA
| | - Gunter Schumann
- Department of PsychiatryCCM, Charite Universitaetsmedizin BerlinBerlinGermany
- Centre for Population Neuroscience and Stratified Medicine (PONS), ISTBIFudan UniversityShanghaiChina
| | - Pierluigi Sevaggi
- Department of Translational Biomedicine and NeuroscienceUniversity of Bari Aldo MoroBariItaly
| | - Jordan W. Smoller
- Department of Psychiatry, Massachusetts General HospitalHarvard Medical SchoolBostonMassachusettsUSA
- Center for Genomic MedicineMassachusetts General HospitalBostonMassachusettsUSA
- Center for Precision PsychiatryMassachusetts General HospitalBostonMassachusettsUSA
| | - Jair C. Soares
- Louis A. Faillace, MD, Department of Psychiatry and Behavioral SciencesThe University of Texas Health Science Center at HoustonHoustonTexasUSA
| | - Gianfranco Spalletta
- Laboratory of Neuropsychiatry, Department of Clinical and Behavioral NeurologyIRCCS Santa Lucia FoundationRomeItaly
| | - Christian K. Tamnes
- PROMENTA Research Center, Department of PsychologyUniversity of OsloOsloNorway
| | - Julian N. Trollor
- Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
- Department of Developmental Disability Neuropsychiatry, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
| | - Dennis Van't Ent
- Department of Biological PsychologyVrije Universiteit AmsterdamAmsterdamThe Netherlands
| | - Daniela Vecchio
- Laboratory of Neuropsychiatry, Department of Clinical and Behavioral NeurologyIRCCS Santa Lucia FoundationRomeItaly
| | - Henrik Walter
- Department of Psychiatry and Psychotherapy, Charité Universitätsmedizin BerlinCorporate Member of FU Berlin and Humboldt Universität zu BerlinBerlinGermany
| | - Yang Wang
- Department of RadiologyMedical College of WisconsinMilwaukeeWisconsinUSA
| | - Bernd Weber
- Institute for Experimental Epileptology and Cognition ResearchUniversity of Bonn and University Hospital BonnBonnGermany
| | - Wei Wen
- Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical MedicineUniversity of New South WalesSydneyNew South WalesAustralia
| | - Lara M. Wierenga
- Department of Psychology, Faculty of Social SciencesLeiden UniversityLeidenThe Netherlands
| | - Steven C. R. Williams
- Department of NeuroimagingInstitute of Psychiatry, Psychology and Neuroscience, King's College LondonLondonUK
| | - Mon‐Ju Wu
- Louis A. Faillace, MD, Department of Psychiatry and Behavioral SciencesThe University of Texas Health Science Center at HoustonHoustonTexasUSA
| | - Giovana B. Zunta‐Soares
- Louis A. Faillace, MD, Department of Psychiatry and Behavioral SciencesThe University of Texas Health Science Center at HoustonHoustonTexasUSA
| | - Boris Bernhardt
- McConnell Brain Imaging CentreMcGill UniversityMontrealQuebecCanada
| | - Paul Thompson
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of MedicineUniversity of Southern CaliforniaMarina del ReyCaliforniaUSA
| | - Sophia Frangou
- Djavad Mowafaghian Centre for Brain Health, Department of PsychiatryUniversity of British ColumbiaVancouverBritish ColumbiaCanada
- Department of PsychiatryIcahn School of Medicine at Mount SinaiNew YorkNew YorkUSA
| | - Ruiyang Ge
- Djavad Mowafaghian Centre for Brain Health, Department of PsychiatryUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | | |
Collapse
|
2
|
Gregorich M, Simpson SL, Heinze G. Flexible parametrization of graph-theoretical features from individual-specific networks for prediction. Stat Med 2024; 43:2592-2606. [PMID: 38664934 DOI: 10.1002/sim.10091] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2023] [Revised: 03/15/2024] [Accepted: 04/15/2024] [Indexed: 05/24/2024]
Abstract
Statistical techniques are needed to analyze data structures with complex dependencies such that clinically useful information can be extracted. Individual-specific networks, which capture dependencies in complex biological systems, are often summarized by graph-theoretical features. These features, which lend themselves to outcome modeling, can be subject to high variability due to arbitrary decisions in network inference and noise. Correlation-based adjacency matrices often need to be sparsified before meaningful graph-theoretical features can be extracted, requiring the data analysts to determine an optimal threshold. To address this issue, we propose to incorporate a flexible weighting function over the full range of possible thresholds to capture the variability of graph-theoretical features over the threshold domain. The potential of this approach, which extends concepts from functional data analysis to a graph-theoretical setting, is explored in a plasmode simulation study using real functional magnetic resonance imaging (fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE) Preprocessed initiative. The simulations show that our modeling approach yields accurate estimates of the functional form of the weight function, improves inference efficiency, and achieves a comparable or reduced root mean square prediction error compared to competitor modeling approaches. This assertion holds true in settings where both complex functional forms underlie the outcome-generating process and a universal threshold value is employed. We demonstrate the practical utility of our approach by using resting-state fMRI data to predict biological age in children. Our study establishes the flexible modeling approach as a statistically principled, serious competitor to ad-hoc methods with superior performance.
Collapse
Affiliation(s)
- Mariella Gregorich
- Medical University of Vienna, Center for Medical Data Science, Institute of Clinical Biometrics, Vienna, Austria
| | - Sean L Simpson
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA
| | - Georg Heinze
- Medical University of Vienna, Center for Medical Data Science, Institute of Clinical Biometrics, Vienna, Austria
| |
Collapse
|
3
|
Huang C, Li A, Pang Y, Yang J, Zhang J, Wu X, Mei L. How the intrinsic functional connectivity patterns of the semantic network support semantic processing. Brain Imaging Behav 2024; 18:539-554. [PMID: 38261218 DOI: 10.1007/s11682-024-00849-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 01/05/2024] [Indexed: 01/24/2024]
Abstract
Semantic processing, a core of language comprehension, involves the activation of brain regions dispersed extensively across the frontal, temporal, and parietal cortices that compose the semantic network. To comprehend the functional structure of this semantic network and how it prepares for semantic processing, we investigated its intrinsic functional connectivity (FC) and the relation between this pattern and semantic processing ability in a large sample from the Human Connectome Project (HCP) dataset. We first defined a well-studied brain network for semantic processing, and then we characterized the within-network connectivity (WNC) and the between-network connectivity (BNC) within this network using a voxel-based global brain connectivity (GBC) method based on resting-state functional magnetic resonance imaging (fMRI). The results showed that 97.73% of the voxels in the semantic network displayed considerably greater WNC than BNC, demonstrating that the semantic network is a fairly encapsulated network. Moreover, multiple connector hubs in the semantic network were identified after applying the criterion of WNC > 1 SD above the mean WNC of the semantic network. More importantly, three of these connector hubs (i.e., the left anterior temporal lobe, angular gyrus, and orbital part of the inferior frontal gyrus) were reliably associated with semantic processing ability. Our findings suggest that the three identified regions use WNC as the central mechanism for supporting semantic processing and that task-independent spontaneous connectivity in the semantic network is essential for semantic processing.
Collapse
Affiliation(s)
- Chengmei Huang
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China
- School of Psychology, South China Normal University, Guangzhou, 510631, China
- Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, China
| | - Aqian Li
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China
- School of Psychology, South China Normal University, Guangzhou, 510631, China
- Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, China
| | - Yingdan Pang
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China
- School of Psychology, South China Normal University, Guangzhou, 510631, China
- Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, China
| | - Jiayi Yang
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China
- School of Psychology, South China Normal University, Guangzhou, 510631, China
- Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, China
| | - Jingxian Zhang
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China
- School of Psychology, South China Normal University, Guangzhou, 510631, China
- Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, China
| | - Xiaoyan Wu
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China
- School of Psychology, South China Normal University, Guangzhou, 510631, China
- Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, China
| | - Leilei Mei
- Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University), Ministry of Education, Guangzhou, 510631, China.
| |
Collapse
|
4
|
Iyer KK, Roberts JA, Waak M, Vogrin SJ, Kevat A, Chawla J, Haataja LM, Lauronen L, Vanhatalo S, Stevenson NJ. A growth chart of brain function from infancy to adolescence based on EEG. EBioMedicine 2024; 102:105061. [PMID: 38537603 PMCID: PMC11026939 DOI: 10.1016/j.ebiom.2024.105061] [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: 07/28/2023] [Revised: 02/29/2024] [Accepted: 03/01/2024] [Indexed: 04/14/2024] Open
Abstract
BACKGROUND In children, objective, quantitative tools that determine functional neurodevelopment are scarce and rarely scalable for clinical use. Direct recordings of cortical activity using routinely acquired electroencephalography (EEG) offer reliable measures of brain function. METHODS We developed and validated a measure of functional brain age (FBA) using a residual neural network-based interpretation of the paediatric EEG. In this cross-sectional study, we included 1056 children with typical development ranging in age from 1 month to 18 years. We analysed a 10- to 15-min segment of 18-channel EEG recorded during light sleep (N1 and N2 states). FINDINGS The FBA had a weighted mean absolute error (wMAE) of 0.85 years (95% CI: 0.69-1.02; n = 1056). A two-channel version of the FBA had a wMAE of 1.51 years (95% CI: 1.30-1.73; n = 1056) and was validated on an independent set of EEG recordings (wMAE = 2.27 years, 95% CI: 1.90-2.65; n = 723). Group-level maturational delays were also detected in a small cohort of children with Trisomy 21 (Cohen's d = 0.36, p = 0.028). INTERPRETATION A FBA, based on EEG, is an accurate, practical and scalable automated tool to track brain function maturation throughout childhood with accuracy comparable to widely used physical growth charts. FUNDING This research was supported by the National Health and Medical Research Council, Australia, Helsinki University Diagnostic Center Research Funds, Finnish Academy, Finnish Paediatric Foundation, and Sigrid Juselius Foundation.
Collapse
Affiliation(s)
- Kartik K Iyer
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, Australia; Faculty of Medicine, The University of Queensland, Brisbane, Australia.
| | - James A Roberts
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, Australia
| | - Michaela Waak
- Faculty of Medicine, The University of Queensland, Brisbane, Australia; Queensland Children's Hospital, Brisbane, Australia
| | | | - Ajay Kevat
- Faculty of Medicine, The University of Queensland, Brisbane, Australia; Queensland Children's Hospital, Brisbane, Australia
| | - Jasneek Chawla
- Faculty of Medicine, The University of Queensland, Brisbane, Australia; Queensland Children's Hospital, Brisbane, Australia
| | - Leena M Haataja
- Departments of Physiology and Clinical Neurophysiology, BABA Center, Paediatric Research Center, Children's Hospital, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Leena Lauronen
- Departments of Physiology and Clinical Neurophysiology, BABA Center, Paediatric Research Center, Children's Hospital, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Sampsa Vanhatalo
- Departments of Physiology and Clinical Neurophysiology, BABA Center, Paediatric Research Center, Children's Hospital, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Nathan J Stevenson
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, Australia.
| |
Collapse
|
5
|
Rosenblatt M, Tejavibulya L, Jiang R, Noble S, Scheinost D. Data leakage inflates prediction performance in connectome-based machine learning models. Nat Commun 2024; 15:1829. [PMID: 38418819 PMCID: PMC10901797 DOI: 10.1038/s41467-024-46150-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Accepted: 02/15/2024] [Indexed: 03/02/2024] Open
Abstract
Predictive modeling is a central technique in neuroimaging to identify brain-behavior relationships and test their generalizability to unseen data. However, data leakage undermines the validity of predictive models by breaching the separation between training and test data. Leakage is always an incorrect practice but still pervasive in machine learning. Understanding its effects on neuroimaging predictive models can inform how leakage affects existing literature. Here, we investigate the effects of five forms of leakage-involving feature selection, covariate correction, and dependence between subjects-on functional and structural connectome-based machine learning models across four datasets and three phenotypes. Leakage via feature selection and repeated subjects drastically inflates prediction performance, whereas other forms of leakage have minor effects. Furthermore, small datasets exacerbate the effects of leakage. Overall, our results illustrate the variable effects of leakage and underscore the importance of avoiding data leakage to improve the validity and reproducibility of predictive modeling.
Collapse
Affiliation(s)
- Matthew Rosenblatt
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
| | - Link Tejavibulya
- Interdepartmental Neuroscience Program, Yale University, New Haven, CT, USA
| | - Rongtao Jiang
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Stephanie Noble
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
- Department of Bioengineering, Northeastern University, Boston, MA, USA
- Department of Psychology, Northeastern University, Boston, MA, USA
| | - Dustin Scheinost
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
- Interdepartmental Neuroscience Program, Yale University, New Haven, CT, USA
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
- Child Study Center, Yale School of Medicine, New Haven, CT, USA
- Department of Statistics & Data Science, Yale University, New Haven, CT, USA
| |
Collapse
|
6
|
Finkelstein O, Levakov G, Kaplan A, Zelicha H, Meir AY, Rinott E, Tsaban G, Witte AV, Blüher M, Stumvoll M, Shelef I, Shai I, Riklin Raviv T, Avidan G. Deep learning-based BMI inference from structural brain MRI reflects brain alterations following lifestyle intervention. Hum Brain Mapp 2024; 45:e26595. [PMID: 38375968 PMCID: PMC10878010 DOI: 10.1002/hbm.26595] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 11/16/2023] [Accepted: 01/03/2024] [Indexed: 02/21/2024] Open
Abstract
Obesity is associated with negative effects on the brain. We exploit Artificial Intelligence (AI) tools to explore whether differences in clinical measurements following lifestyle interventions in overweight population could be reflected in brain morphology. In the DIRECT-PLUS clinical trial, participants with criterion for metabolic syndrome underwent an 18-month lifestyle intervention. Structural brain MRIs were acquired before and after the intervention. We utilized an ensemble learning framework to predict Body-Mass Index (BMI) scores, which correspond to adiposity-related clinical measurements from brain MRIs. We revealed that patient-specific reduction in BMI predictions was associated with actual weight loss and was significantly higher in active diet groups compared to a control group. Moreover, explainable AI (XAI) maps highlighted brain regions contributing to BMI predictions that were distinct from regions associated with age prediction. Our DIRECT-PLUS analysis results imply that predicted BMI and its reduction are unique neural biomarkers for obesity-related brain modifications and weight loss.
Collapse
Affiliation(s)
- Ofek Finkelstein
- Department of Cognitive and Brain SciencesBen‐Gurion University of the NegevBeer ShevaIsrael
| | - Gidon Levakov
- Department of Cognitive and Brain SciencesBen‐Gurion University of the NegevBeer ShevaIsrael
| | - Alon Kaplan
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
- The Chaim Sheba Medical Center, Tel HashomerRamat‐GanIsrael
| | - Hila Zelicha
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
| | - Anat Yaskolka Meir
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
| | - Ehud Rinott
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
| | - Gal Tsaban
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
- Soroka University Medical CenterBeer ShevaIsrael
| | - Anja Veronica Witte
- Department of Neurology, Max Planck‐Institute for Human Cognitive and Brain Sciences, and Cognitive NeurologyUniversity of Leipzig Medical CenterLeipzigGermany
| | | | | | - Ilan Shelef
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
- Soroka University Medical CenterBeer ShevaIsrael
| | - Iris Shai
- The Health & Nutrition Innovative International Research Center, Faculty of Health SciencesBen Gurion University of the NegevBeer ShevaIsrael
- Department of Nutrition, Harvard T.H. Chan School of Public HealthBostonMassachusettsUSA
| | - Tammy Riklin Raviv
- The School of Electrical and Computer EngineeringBen Gurion University of the NegevBeer ShevaIsrael
| | - Galia Avidan
- Department of PsychologyBen‐Gurion University of the NegevBeer ShevaIsrael
| |
Collapse
|
7
|
Cohen JW, Ramphal B, DeSerisy M, Zhao Y, Pagliaccio D, Colcombe S, Milham MP, Margolis AE. Relative brain age is associated with socioeconomic status and anxiety/depression problems in youth. Dev Psychol 2024; 60:199-209. [PMID: 37747510 PMCID: PMC10993304 DOI: 10.1037/dev0001593] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/26/2023]
Abstract
Brain age, a measure of biological aging in the brain, has been linked to psychiatric illness, principally in adult populations. Components of socioeconomic status (SES) associate with differences in brain structure and psychiatric risk across the lifespan. This study aimed to investigate the influence of SES on brain aging in childhood and adolescence, a period of rapid neurodevelopment and peak onset for many psychiatric disorders. We reanalyzed data from the Healthy Brain Network to examine the influence of SES components (occupational prestige, public assistance enrollment, parent education, and household income-to-needs ratio [INR]) on relative brain age (RBA). Analyses included 470 youth (5-17 years; 61.3% men), self-identifying as White (55%), African American (15%), Hispanic (9%), or multiracial (17.2%). Household income was 3.95 ± 2.33 (mean ± SD) times the federal poverty threshold. RBA quantified differences between chronological age and brain age using covariation patterns of morphological features and total volumes. We also examined associations between RBA and psychiatric symptoms (Child Behavior Checklist [CBCL]). Models covaried for sex, scan location, and parent psychiatric diagnoses. In a linear regression, lower RBA is associated with lower parent occupational prestige (p = .01), lower public assistance enrollment (p = .03), and more parent psychiatric diagnoses (p = .01), but not parent education or INR. Lower parent occupational prestige (p = .02) and lower RBA (p = .04) are associated with higher CBCL anxious/depressed scores. Our findings underscore the importance of including SES components in developmental brain research. Delayed brain aging may represent a potential biological pathway from SES to psychiatric risk. (PsycInfo Database Record (c) 2024 APA, all rights reserved).
Collapse
Affiliation(s)
- Jacob W. Cohen
- New York State Psychiatric Institute and Department of Psychiatry, Vagelos College of Physicians and Surgeons, Columbia University
| | - Bruce Ramphal
- New York State Psychiatric Institute and Department of Psychiatry, Vagelos College of Physicians and Surgeons, Columbia University
- T.H. Chan School of Public Health, Harvard Medical School
| | - Mariah DeSerisy
- Department of Epidemiology, Mailman School of Public Health, Columbia University
| | - Yihong Zhao
- Columbia University School of Nursing
- Center for Biological Imaging and Neuromodulation, Nathan S. Kline Institute, Orangeburg, New York, United States
| | - David Pagliaccio
- New York State Psychiatric Institute and Department of Psychiatry, Vagelos College of Physicians and Surgeons, Columbia University
| | - Stan Colcombe
- Center for Biological Imaging and Neuromodulation, Nathan S. Kline Institute, Orangeburg, New York, United States
| | - Michael P. Milham
- Child Mind Institute, New York, New York, United States
- Nathan S. Kline Institute, Orangeburg, New York, United States
| | - Amy E. Margolis
- New York State Psychiatric Institute and Department of Psychiatry, Vagelos College of Physicians and Surgeons, Columbia University
| |
Collapse
|
8
|
Rosenblatt M, Tejavibulya L, Jiang R, Noble S, Scheinost D. The effects of data leakage on connectome-based machine learning models. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.06.09.544383. [PMID: 38234740 PMCID: PMC10793416 DOI: 10.1101/2023.06.09.544383] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/19/2024]
Abstract
Predictive modeling has now become a central technique in neuroimaging to identify complex brain-behavior relationships and test their generalizability to unseen data. However, data leakage, which unintentionally breaches the separation between data used to train and test the model, undermines the validity of predictive models. Previous literature suggests that leakage is generally pervasive in machine learning, but few studies have empirically evaluated the effects of leakage in neuroimaging data. Although leakage is always an incorrect practice, understanding the effects of leakage on neuroimaging predictive models provides insight into the extent to which leakage may affect the literature. Here, we investigated the effects of leakage on machine learning models in two common neuroimaging modalities, functional and structural connectomes. Using over 400 different pipelines spanning four large datasets and three phenotypes, we evaluated five forms of leakage fitting into three broad categories: feature selection, covariate correction, and lack of independence between subjects. As expected, leakage via feature selection and repeated subjects drastically inflated prediction performance. Notably, other forms of leakage had only minor effects (e.g., leaky site correction) or even decreased prediction performance (e.g., leaky covariate regression). In some cases, leakage affected not only prediction performance, but also model coefficients, and thus neurobiological interpretations. Finally, we found that predictive models using small datasets were more sensitive to leakage. Overall, our results illustrate the variable effects of leakage on prediction pipelines and underscore the importance of avoiding data leakage to improve the validity and reproducibility of predictive modeling.
Collapse
Affiliation(s)
| | - Link Tejavibulya
- Interdepartmental Neuroscience Program, Yale University, New Haven, CT
| | - Rongtao Jiang
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT
| | - Stephanie Noble
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT
- Department of Bioengineering, Northeastern University, Boston, MA
- Department of Psychology, Northeastern University, Boston, MA
| | - Dustin Scheinost
- Department of Biomedical Engineering, Yale University, New Haven, CT
- Interdepartmental Neuroscience Program, Yale University, New Haven, CT
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT
- Child Study Center, Yale School of Medicine, New Haven, CT
- Department of Statistics & Data Science, Yale University, New Haven, CT
| |
Collapse
|
9
|
Marx GA, Kauffman J, McKenzie AT, Koenigsberg DG, McMillan CT, Morgello S, Karlovich E, Insausti R, Richardson TE, Walker JM, White CL, Babrowicz BM, Shen L, McKee AC, Stein TD, Farrell K, Crary JF. Histopathologic brain age estimation via multiple instance learning. Acta Neuropathol 2023; 146:785-802. [PMID: 37815677 PMCID: PMC10627911 DOI: 10.1007/s00401-023-02636-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 09/14/2023] [Accepted: 09/18/2023] [Indexed: 10/11/2023]
Abstract
Understanding age acceleration, the discordance between biological and chronological age, in the brain can reveal mechanistic insights into normal physiology as well as elucidate pathological determinants of age-related functional decline and identify early disease changes in the context of Alzheimer's and other disorders. Histopathological whole slide images provide a wealth of pathologic data on the cellular level that can be leveraged to build deep learning models to assess age acceleration. Here, we used a collection of digitized human post-mortem hippocampal sections to develop a histological brain age estimation model. Our model predicted brain age within a mean absolute error of 5.45 ± 0.22 years, with attention weights corresponding to neuroanatomical regions vulnerable to age-related changes. We found that histopathologic brain age acceleration had significant associations with clinical and pathologic outcomes that were not found with epigenetic based measures. Our results indicate that histopathologic brain age is a powerful, independent metric for understanding factors that contribute to brain aging.
Collapse
Affiliation(s)
- Gabriel A Marx
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
- Department of Artificial Intelligence and Human Health, Nash Family Department of Neuroscience, Ronald M. Loeb Center for Alzheimer's Disease, Friedman Brain Institute, Neuropathology Brain Bank and Research CoRE, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Justin Kauffman
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
- Department of Artificial Intelligence and Human Health, Nash Family Department of Neuroscience, Ronald M. Loeb Center for Alzheimer's Disease, Friedman Brain Institute, Neuropathology Brain Bank and Research CoRE, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Andrew T McKenzie
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
- Department of Artificial Intelligence and Human Health, Nash Family Department of Neuroscience, Ronald M. Loeb Center for Alzheimer's Disease, Friedman Brain Institute, Neuropathology Brain Bank and Research CoRE, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Daniel G Koenigsberg
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
- Department of Artificial Intelligence and Human Health, Nash Family Department of Neuroscience, Ronald M. Loeb Center for Alzheimer's Disease, Friedman Brain Institute, Neuropathology Brain Bank and Research CoRE, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Cory T McMillan
- Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Susan Morgello
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Nash Family Department of Neuroscience, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, New York, NY, USA
| | - Esma Karlovich
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Ricardo Insausti
- Human Neuroanatomy Laboratory, School of Medicine, University of Castilla-La Mancha, Albacete, Spain
| | - Timothy E Richardson
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Jamie M Walker
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Charles L White
- Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Bergan M Babrowicz
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA
| | - Li Shen
- Nash Family Department of Neuroscience, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, New York, NY, USA
| | - Ann C McKee
- Department of Pathology, Alzheimer's Disease and CTE Center, Boston University School of Medicine, Boston, MA, USA
- Department of Veterans Affairs Medical Center, Bedford, MA, USA
- VA Boston Healthcare System, Boston, MA, USA
| | - Thor D Stein
- Department of Pathology, Alzheimer's Disease and CTE Center, Boston University School of Medicine, Boston, MA, USA
- Department of Veterans Affairs Medical Center, Bedford, MA, USA
- VA Boston Healthcare System, Boston, MA, USA
| | - Kurt Farrell
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA.
- Department of Artificial Intelligence and Human Health, Nash Family Department of Neuroscience, Ronald M. Loeb Center for Alzheimer's Disease, Friedman Brain Institute, Neuropathology Brain Bank and Research CoRE, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA.
| | - John F Crary
- Department of Pathology, Icahn School of Medicine at Mount Sinai, Friedman Brain Institute, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA.
- Department of Artificial Intelligence and Human Health, Nash Family Department of Neuroscience, Ronald M. Loeb Center for Alzheimer's Disease, Friedman Brain Institute, Neuropathology Brain Bank and Research CoRE, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Place, Box 1194, New York, NY, 10029, USA.
| |
Collapse
|
10
|
Ray B, Chen J, Fu Z, Suresh P, Thapaliya B, Farahdel B, Calhoun VD, Liu J. Replication and Refinement of Brain Age Model for adolescent development. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.08.16.553472. [PMID: 37645839 PMCID: PMC10462059 DOI: 10.1101/2023.08.16.553472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/31/2023]
Abstract
The discrepancy between chronological age and estimated brain age, known as the brain age gap, may serve as a biomarker to reveal brain development and neuropsychiatric problems. This has motivated many studies focusing on the accurate estimation of brain age using different features and models, of which the generalizability is yet to be tested. Our recent study has demonstrated that conventional machine learning models can achieve high accuracy on brain age prediction during development using only a small set of selected features from multimodal brain imaging data. In the current study, we tested the replicability of various brain age models on the Adolescent Brain Cognitive Development (ABCD) cohort. We proposed a new refined model to improve the robustness of brain age prediction. The direct replication test for existing brain age models derived from the age range of 8-22 years onto the ABCD participants at baseline (9 to 10 years old) and year-two follow-up (11 to 12 years old) indicate that pre-trained models could capture the overall mean age failed precisely estimating brain age variation within a narrow range. The refined model, which combined broad prediction of the pre-trained model and granular information with the narrow age range, achieved the best performance with a mean absolute error of 0.49 and 0.48 years on the baseline and year-two data, respectively. The brain age gap yielded by the refined model showed significant associations with the participants' information processing speed and verbal comprehension ability on baseline data.
Collapse
Affiliation(s)
- Bhaskar Ray
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
- Department of Computer Science, Georgia State University, Atlanta, USA
| | - Jiayu Chen
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
| | - Zening Fu
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
| | - Pranav Suresh
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
- Department of Computer Science, Georgia State University, Atlanta, USA
| | - Bishal Thapaliya
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
- Department of Computer Science, Georgia State University, Atlanta, USA
| | - Britny Farahdel
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
- Department of Computer Science, Georgia State University, Atlanta, USA
| | - Vince D. Calhoun
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
- Department of Computer Science, Georgia State University, Atlanta, USA
| | - Jingyu Liu
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, USA
- Department of Computer Science, Georgia State University, Atlanta, USA
| |
Collapse
|
11
|
Fu J, Tzortzakakis A, Barroso J, Westman E, Ferreira D, Moreno R. Fast three-dimensional image generation for healthy brain aging using diffeomorphic registration. Hum Brain Mapp 2023; 44:1289-1308. [PMID: 36468536 PMCID: PMC9921328 DOI: 10.1002/hbm.26165] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2022] [Revised: 11/15/2022] [Accepted: 11/16/2022] [Indexed: 12/12/2022] Open
Abstract
Predicting brain aging can help in the early detection and prognosis of neurodegenerative diseases. Longitudinal cohorts of healthy subjects scanned through magnetic resonance imaging (MRI) have been essential to understand the structural brain changes due to aging. However, these cohorts suffer from missing data due to logistic issues in the recruitment of subjects. This paper proposes a methodology for filling up missing data in longitudinal cohorts with anatomically plausible images that capture the subject-specific aging process. The proposed methodology is developed within the framework of diffeomorphic registration. First, two novel modules are introduced within Synthmorph, a fast, state-of-the-art deep learning-based diffeomorphic registration method, to simulate the aging process between the first and last available MRI scan for each subject in three-dimensional (3D). The use of image registration also makes the generated images plausible by construction. Second, we used six image similarity measurements to rearrange the generated images to the specific age range. Finally, we estimated the age of every generated image by using the assumption of linear brain decay in healthy subjects. The methodology was evaluated on 2662 T1-weighted MRI scans from 796 healthy participants from 3 different longitudinal cohorts: Alzheimer's Disease Neuroimaging Initiative, Open Access Series of Imaging Studies-3, and Group of Neuropsychological Studies of the Canary Islands (GENIC). In total, we generated 7548 images to simulate the access of a scan per subject every 6 months in these cohorts. We evaluated the quality of the synthetic images using six quantitative measurements and a qualitative assessment by an experienced neuroradiologist with state-of-the-art results. The assumption of linear brain decay was accurate in these cohorts (R2 ∈ [.924, .940]). The experimental results show that the proposed methodology can produce anatomically plausible aging predictions that can be used to enhance longitudinal datasets. Compared to deep learning-based generative methods, diffeomorphic registration is more likely to preserve the anatomy of the different structures of the brain, which makes it more appropriate for its use in clinical applications. The proposed methodology is able to efficiently simulate anatomically plausible 3D MRI scans of brain aging of healthy subjects from two images scanned at two different time points.
Collapse
Affiliation(s)
- Jingru Fu
- Division of Biomedical ImagingDepartment of Biomedical Engineering and Health Systems, KTH Royal Institute of TechnologyStockholmSweden
| | - Antonios Tzortzakakis
- Division of RadiologyDepartment for Clinical Science, Intervention and Technology (CLINTEC), Karolinska InstitutetStockholmSweden
- Medical Radiation Physics and Nuclear MedicineFunctional Unit of Nuclear Medicine, Karolinska University HospitalHuddingeStockholmSweden
| | - José Barroso
- Department of PsychologyFaculty of Health Sciences, University Fernando Pessoa CanariasLas PalmasSpain
| | - Eric Westman
- Division of Clinical GeriatricsCentre for Alzheimer Research, Department of Neurobiology, Care Sciences, and Society (NVS), Karolinska InstitutetStockholmSweden
- Department of NeuroimagingCentre for Neuroimaging Sciences, Institute of Psychiatry, Psychology and Neuroscience, King's College LondonLondonUnited Kingdom
| | - Daniel Ferreira
- Division of Clinical GeriatricsCentre for Alzheimer Research, Department of Neurobiology, Care Sciences, and Society (NVS), Karolinska InstitutetStockholmSweden
| | - Rodrigo Moreno
- Division of Biomedical ImagingDepartment of Biomedical Engineering and Health Systems, KTH Royal Institute of TechnologyStockholmSweden
| | | |
Collapse
|
12
|
Clements RG, Claros-Olivares CC, McIlvain G, Brockmeier AJ, Johnson CL. Mechanical Property Based Brain Age Prediction using Convolutional Neural Networks. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.02.12.528186. [PMID: 36824781 PMCID: PMC9948973 DOI: 10.1101/2023.02.12.528186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/15/2023]
Abstract
Brain age is a quantitative estimate to explain an individual's structural and functional brain measurements relative to the overall population and is particularly valuable in describing differences related to developmental or neurodegenerative pathology. Accurately inferring brain age from brain imaging data requires sophisticated models that capture the underlying age-related brain changes. Magnetic resonance elastography (MRE) is a phase contrast MRI technology that uses external palpations to measure brain mechanical properties. Mechanical property measures of viscoelastic shear stiffness and damping ratio have been found to change across the entire life span and to reflect brain health due to neurodegenerative diseases and even individual differences in cognitive function. Here we develop and train a multi-modal 3D convolutional neural network (CNN) to model the relationship between age and whole brain mechanical properties. After training, the network maps the measurements and other inputs to a brain age prediction. We found high performance using the 3D maps of various mechanical properties to predict brain age. Stiffness maps alone were able to predict ages of the test group subjects with a mean absolute error (MAE) of 3.76 years, which is comparable to single inputs of damping ratio (MAE: 3.82) and outperforms single input of volume (MAE: 4.60). Combining stiffness and volume in a multimodal approach performed the best, with an MAE of 3.60 years, whereas including damping ratio worsened model performance. Our results reflect previous MRE literature that had demonstrated that stiffness is more strongly related to chronological age than damping ratio. This machine learning model provides the first prediction of brain age from brain biomechanical data-an advancement towards sensitively describing brain integrity differences in individuals with neuropathology.
Collapse
|