1
|
Zhou J, Chen Y, Jin X, Mao W, Xiao Z, Zhang S, Zhang T, Liu T, Kendrick K, Jiang X. Fusing multi-scale functional connectivity patterns via Multi-Branch Vision Transformer (MB-ViT) for macaque brain age prediction. Neural Netw 2024; 179:106592. [PMID: 39168070 DOI: 10.1016/j.neunet.2024.106592] [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: 08/07/2023] [Revised: 06/03/2024] [Accepted: 07/31/2024] [Indexed: 08/23/2024]
Abstract
Brain age (BA) is defined as a measure of brain maturity and could help characterize both the typical brain development and neuropsychiatric disorders in mammals. Various biological phenotypes have been successfully applied to predict BA of human using chronological age (CA) as label. However, whether the BA of macaque, one of the most important animal models, can also be reliably predicted is largely unknown. To address this question, we propose a novel deep learning model called Multi-Branch Vision Transformer (MB-ViT) to fuse multi-scale (i.e., from coarse-grained to fine-grained) brain functional connectivity (FC) patterns derived from resting state functional magnetic resonance imaging (rs-fMRI) data to predict BA of macaques. The discriminative functional connections and the related brain regions contributing to the prediction are further identified based on Gradient-weighted Class Activation Mapping (Grad-CAM) method. Our proposed model successfully predicts BA of 450 normal rhesus macaques from the publicly available PRIMatE Data Exchange (PRIME-DE) dataset with lower mean absolute error (MAE) and mean square error (MSE) as well as higher Pearson's correlation coefficient (PCC) and coefficient of determination (R2) compared to other baseline models. The correlation between the predicted BA and CA reaches as high as 0.82 of our proposed method. Furthermore, our analysis reveals that the functional connections predominantly contributing to the prediction results are situated in the primary motor cortex (M1), visual cortex, area v23 in the posterior cingulate cortex, and dysgranular temporal pole. In summary, our proposed deep learning model provides an effective tool to accurately predict BA of primates (macaque in this study), and lays a solid foundation for future studies of age-related brain diseases in those animal models.
Collapse
Affiliation(s)
- Jingchao Zhou
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Yuzhong Chen
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Xuewei Jin
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Wei Mao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Zhenxiang Xiao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Songyao Zhang
- School of Automation, Northwestern Polytechnical University, Xi'an, China
| | - Tuo Zhang
- School of Automation, Northwestern Polytechnical University, Xi'an, China
| | - Tianming Liu
- School of Computing, University of Georgia, Athens, USA
| | - Keith Kendrick
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Xi Jiang
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China.
| |
Collapse
|
2
|
Xue L, Fu Y, Gao X, Feng G, Qian S, Wei L, Li L, Zhuo C, Zhang H, Tian M. [ 18F]FDG PET integrated with structural MRI for accurate brain age prediction. Eur J Nucl Med Mol Imaging 2024; 51:3617-3629. [PMID: 38839623 DOI: 10.1007/s00259-024-06784-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: 01/29/2024] [Accepted: 05/30/2024] [Indexed: 06/07/2024]
Abstract
PURPOSE Brain aging is a complex and heterogeneous process characterized by both structural and functional decline. This study aimed to establish a novel deep learning (DL) method for predicting brain age by utilizing structural and metabolic imaging data. METHODS The dataset comprised participants from both the Universal Medical Imaging Diagnostic Center (UMIDC) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). The former recruited 395 normal control (NC) subjects, while the latter included 438 NC subjects, 51 mild cognitive impairment (MCI) subjects, and 56 Alzheimer's disease (AD) subjects. We developed a novel dual-pathway, 3D simple fully convolutional network (Dual-SFCNeXt) to estimate brain age using [18F]fluorodeoxyglucose positron emission tomography ([18F]FDG PET) and structural magnetic resonance imaging (sMRI) images of NC subjects as input. Several prevailing DL models were trained and tested using either MRI or PET data for comparison. Model accuracies were evaluated using mean absolute error (MAE) and Pearson's correlation coefficient (r). Brain age gap (BAG), deviations of brain age from chronologic age, was correlated with cognitive assessments in MCI and AD subjects. RESULTS Both PET- and MRI-based models achieved high prediction accuracy. The leading model was the SFCNeXt (the single-pathway version) for PET (MAE = 2.92, r = 0.96) and MRI (MAE = 3.23, r = 0.95) on all samples. By integrating both PET and MRI images, the Dual-SFCNeXt demonstrated significantly improved accuracy (MAE = 2.37, r = 0.97) compared to all single-modality models. Significantly higher BAG was observed in both the AD (P < 0.0001) and MCI (P < 0.0001) groups compared to the NC group. BAG correlated significantly with Mini-Mental State Examination (MMSE) scores (r=-0.390 for AD, r=-0.436 for MCI) and the Clinical Dementia Rating Scale Sum of Boxes (CDR-SB) scores (r = 0.333 for AD, r = 0.372 for MCI). CONCLUSION The integration of [18F]FDG PET with structural MRI enhances the accuracy of brain age prediction, potentially introducing a new avenue for related multimodal brain age prediction studies.
Collapse
Affiliation(s)
- Le Xue
- Department of Nuclear Medicine and PET Center, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China
- Institute of Nuclear Medicine and Molecular Imaging of Zhejiang University, Hangzhou, Zhejiang, China
- Key Laboratory of Medical Molecular Imaging of Zhejiang Province, Hangzhou, Zhejiang, China
| | - Yu Fu
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China
- School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China
| | - Xin Gao
- Shanghai Universal Medical Imaging Diagnostic Center, Shanghai, China
| | - Gang Feng
- Shanghai Universal Medical Imaging Diagnostic Center, Shanghai, China
| | - Shufang Qian
- Department of Nuclear Medicine and PET Center, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China
- Institute of Nuclear Medicine and Molecular Imaging of Zhejiang University, Hangzhou, Zhejiang, China
- Key Laboratory of Medical Molecular Imaging of Zhejiang Province, Hangzhou, Zhejiang, China
| | - Ling Wei
- Huashan Hospital & Human Phenome Institute, Fudan University, Shanghai, China
| | - Lanlan Li
- Huashan Hospital & Human Phenome Institute, Fudan University, Shanghai, China
| | - Cheng Zhuo
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China
| | - Hong Zhang
- Department of Nuclear Medicine and PET Center, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Institute of Nuclear Medicine and Molecular Imaging of Zhejiang University, Hangzhou, Zhejiang, China.
- Key Laboratory of Medical Molecular Imaging of Zhejiang Province, Hangzhou, Zhejiang, China.
- College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China.
- Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, Zhejiang, China.
| | - Mei Tian
- Department of Nuclear Medicine and PET Center, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Institute of Nuclear Medicine and Molecular Imaging of Zhejiang University, Hangzhou, Zhejiang, China.
- Key Laboratory of Medical Molecular Imaging of Zhejiang Province, Hangzhou, Zhejiang, China.
- Huashan Hospital & Human Phenome Institute, Fudan University, Shanghai, China.
| |
Collapse
|
3
|
Spitz G, Hicks AJ, McDonald SJ, Dore V, Krishnadas N, O'Brien TJ, O'Brien WT, Vivash L, Law M, Ponsford JL, Rowe C, Shultz SR. Plasma biomarkers in chronic single moderate-severe traumatic brain injury. Brain 2024:awae255. [PMID: 39315931 DOI: 10.1093/brain/awae255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2023] [Revised: 06/06/2024] [Accepted: 07/04/2024] [Indexed: 09/25/2024] Open
Abstract
Blood biomarkers are an emerging diagnostic and prognostic tool that reflect a range of neuropathological processes following traumatic brain injury (TBI). Their effectiveness in identifying long-term neuropathological processes after TBI is unclear. Studying biomarkers in the chronic phase is vital because elevated levels in TBI might result from distinct neuropathological mechanisms during acute and chronic phases. Here, we examine plasma biomarkers in the chronic period following TBI and their association with amyloid and tau PET, white matter microarchitecture, brain age and cognition. We recruited participants ≥40 years of age who had suffered a single moderate-severe TBI ≥10 years previously between January 2018 and March 2021. We measured plasma biomarkers using single molecule array technology [ubiquitin C-terminal hydrolase L1 (UCH-L1), neurofilament light (NfL), tau, glial fibrillary acidic protein (GFAP) and phosphorylated tau (P-tau181)]; PET tracers to measure amyloid-β (18F-NAV4694) and tau neurofibrillary tangles (18F-MK6240); MRI to assess white matter microstructure and brain age; and the Rey Auditory Verbal Learning Test to measure verbal-episodic memory. A total of 90 post-TBI participants (73% male; mean = 58.2 years) were recruited on average 22 years (range = 10-33 years) post-injury, and 32 non-TBI control participants (66% male; mean = 57.9 years) were recruited. Plasma UCH-L1 levels were 67% higher {exp(b) = 1.67, P = 0.018, adjusted P = 0.044, 95% confidence interval (CI) [10% to 155%], area under the curve = 0.616} and P-tau181 were 27% higher {exp(b) = 1.24, P = 0.011, adjusted P = 0.044, 95% CI [5% to 46%], area under the curve = 0.632} in TBI participants compared with controls. Amyloid and tau PET were not elevated in TBI participants. Higher concentrations of plasma P-tau181, UCH-L1, GFAP and NfL were significantly associated with worse white matter microstructure but not brain age in TBI participants. For TBI participants, poorer verbal-episodic memory was associated with higher concentration of P-tau181 {short delay: b = -2.17, SE = 1.06, P = 0.043, 95% CI [-4.28, -0.07]; long delay: bP-tau = -2.56, SE = 1.08, P = 0.020, 95% CI [-4.71, -0.41]}, tau {immediate memory: bTau = -6.22, SE = 2.47, P = 0.014, 95% CI [-11.14, -1.30]} and UCH-L1 {immediate memory: bUCH-L1 = -2.14, SE = 1.07, P = 0.048, 95% CI [-4.26, -0.01]}, but was not associated with functional outcome. Elevated plasma markers related to neuronal damage and accumulation of phosphorylated tau suggest the presence of ongoing neuropathology in the chronic phase following a single moderate-severe TBI. Plasma biomarkers were associated with measures of microstructural brain disruption on MRI and disordered cognition, further highlighting their utility as potential objective tools to monitor evolving neuropathology post-TBI.
Collapse
Affiliation(s)
- Gershon Spitz
- Monash-Epworth Rehabilitation Research Centre, School of Psychological Sciences, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3800, Australia
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
| | - Amelia J Hicks
- Monash-Epworth Rehabilitation Research Centre, School of Psychological Sciences, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3800, Australia
| | - Stuart J McDonald
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
- Department of Neurology, The Alfred, Melbourne, VIC 3004, Australia
| | - Vincent Dore
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Parkville, VIC 3010, Australia
- Department of Molecular Imaging and Therapy, Austin Health, Heidelberg, VIC 3084, Australia
| | - Natasha Krishnadas
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Parkville, VIC 3010, Australia
- Department of Molecular Imaging and Therapy, Austin Health, Heidelberg, VIC 3084, Australia
| | - Terence J O'Brien
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
- Department of Neurology, The Alfred, Melbourne, VIC 3004, Australia
- Department of Medicine, Royal Melbourne Hospital, The University of Melbourne, Parkville, VIC 3010, Australia
| | - William T O'Brien
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
| | - Lucy Vivash
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
- Department of Neurology, The Alfred, Melbourne, VIC 3004, Australia
- Department of Medicine, Royal Melbourne Hospital, The University of Melbourne, Parkville, VIC 3010, Australia
| | - Meng Law
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
- Department of Radiology, Alfred Health, Melbourne, VIC 3004, Australia
| | - Jennie L Ponsford
- Monash-Epworth Rehabilitation Research Centre, School of Psychological Sciences, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3800, Australia
| | - Christopher Rowe
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Parkville, VIC 3010, Australia
- Department of Molecular Imaging and Therapy, Austin Health, Heidelberg, VIC 3084, Australia
| | - Sandy R Shultz
- Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, VIC 3004, Australia
- Department of Neurology, The Alfred, Melbourne, VIC 3004, Australia
- The Centre for Trauma and Mental Health Research, Health Sciences and Human Services, Vancouver Island University, Nanaimo, BC V9R 5S5, Canada
| |
Collapse
|
4
|
Moody JN, Howard E, Nolan KE, Prieto S, Logue MW, Hayes JP. Traumatic Brain Injury and Genetic Risk for Alzheimer's Disease Impact Cerebrospinal Fluid β-Amyloid Levels in Vietnam War Veterans. Neurotrauma Rep 2024; 5:760-769. [PMID: 39184178 PMCID: PMC11342050 DOI: 10.1089/neur.2024.0048] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/27/2024] Open
Abstract
Traumatic brain injuries (TBIs) may increase the risk for Alzheimer's disease (AD) and its neuropathological correlates, although the mechanisms of this relationship are unclear. The current study examined the synergistic effects of TBI and genetic risk for AD on β-amyloid (Aβ) levels among Vietnam War Veterans. We hypothesized that the combination of TBI and higher polygenic risk score (PRS) for AD would be associated with lower cerebrospinal fluid (CSF) Aβ42/40. Data were obtained from the Department of Defense Alzheimer's Disease Neuroimaging Initiative. Participants included Vietnam War Veterans without dementia who identified as White non-Hispanic/Latino and had available demographic, clinical assessment, genetic, and CSF biomarker data. Lifetime TBI history was assessed using The Ohio State University TBI Identification Method. Participants were categorized into those with and without TBI. Among those with a prior TBI, injury severity was defined as either mild or moderate/severe. CSF Aβ42/40 ratios were calculated. Genetic propensity for AD was assessed using PRSs. Hierarchical linear regression models examined the interactive effects of TBI and PRS for AD on Aβ42/40. Exploratory analyses examined the interaction between TBI severity and PRS. The final sample included 88 male Vietnam War Veterans who identified as White non-Hispanic/Latino (M age = 68.3 years), 49 of whom reported a prior TBI. There was a significant interaction between TBI and PRS, such that individuals with TBI and higher PRS for AD had lower Aβ42/40 (B = -0.45, 95% CI: -0.86 to -0.05, p = 0.03). This relationship may be stronger with increasing TBI severity (p = 0.05). Overall, TBI was associated with lower Aβ42/40, indicating greater amyloid deposition in the brain, in the context of greater polygenic risk for AD. These findings highlight who may be at increased risk for AD neuropathology following TBI.
Collapse
Affiliation(s)
- Jena N. Moody
- Department of Psychology, The Ohio State University, Columbus, Ohio, USA
| | - Erica Howard
- Department of Psychology, The Ohio State University, Columbus, Ohio, USA
| | - Kate E. Nolan
- Department of Psychology, The Ohio State University, Columbus, Ohio, USA
| | - Sarah Prieto
- Department of Psychology, The Ohio State University, Columbus, Ohio, USA
| | - Mark W. Logue
- National Center for PTSD, VA Boston Healthcare System, Boston, Massachusetts, USA
- Psychiatry and Biomedical Genetics, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA
- Department of Biostatistics, Boston University School of Public Health, Boston, Massachusetts, USA
| | - Jasmeet P. Hayes
- Department of Psychology, The Ohio State University, Columbus, Ohio, USA
- Chronic Brain Injury Initiative, The Ohio State University, Columbus, Ohio, USA
| | | |
Collapse
|
5
|
Zhang X, Pan Y, Wu T, Zhao W, Zhang H, Ding J, Ji Q, Jia X, Li X, Lee Z, Zhang J, Bai L. Brain age prediction using interpretable multi-feature-based convolutional neural network in mild traumatic brain injury. Neuroimage 2024; 297:120751. [PMID: 39048043 DOI: 10.1016/j.neuroimage.2024.120751] [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: 04/20/2024] [Revised: 07/15/2024] [Accepted: 07/22/2024] [Indexed: 07/27/2024] Open
Abstract
BACKGROUND Convolutional neural network (CNN) can capture the structural features changes of brain aging based on MRI, thus predict brain age in healthy individuals accurately. However, most studies use single feature to predict brain age in healthy individuals, ignoring adding information from multiple sources and the changes in brain aging patterns after mild traumatic brain injury (mTBI) were still unclear. METHODS Here, we leveraged the structural data from a large, heterogeneous dataset (N = 1464) to implement an interpretable 3D combined CNN model for brain-age prediction. In addition, we also built an atlas-based occlusion analysis scheme with a fine-grained human Brainnetome Atlas to reveal the age-sstratified contributed brain regions for brain-age prediction in healthy controls (HCs) and mTBI patients. The correlations between brain predicted age gaps (brain-PAG) following mTBI and individual's cognitive impairment, as well as the level of plasma neurofilament light were also examined. RESULTS Our model utilized multiple 3D features derived from T1w data as inputs, and reduced the mean absolute error (MAE) of age prediction to 3.08 years and improved Pearson's r to 0.97 on 154 HCs. The strong generalizability of our model was also validated across different centers. Regions contributing the most significantly to brain age prediction were the caudate and thalamus for HCs and patients with mTBI, and the contributive regions were mostly located in the subcortical areas throughout the adult lifespan. The left hemisphere was confirmed to contribute more in brain age prediction throughout the adult lifespan. Our research showed that brain-PAG in mTBI patients was significantly higher than that in HCs in both acute and chronic phases. The increased brain-PAG in mTBI patients was also highly correlated with cognitive impairment and a higher level of plasma neurofilament light, a marker of neurodegeneration. The higher brain-PAG and its correlation with severe cognitive impairment showed a longitudinal and persistent nature in patients with follow-up examinations. CONCLUSION We proposed an interpretable deep learning framework on a relatively large dataset to accurately predict brain age in both healthy individuals and mTBI patients. The interpretable analysis revealed that the caudate and thalamus became the most contributive role across the adult lifespan in both HCs and patients with mTBI. The left hemisphere contributed significantly to brain age prediction may enlighten us to be concerned about the lateralization of brain abnormality in neurological diseases in the future. The proposed interpretable deep learning framework might also provide hope for testing the performance of related drugs and treatments in the future.
Collapse
Affiliation(s)
- Xiang Zhang
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Yizhen Pan
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Tingting Wu
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Wenpu Zhao
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Haonan Zhang
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Jierui Ding
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Qiuyu Ji
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Xiaoyan Jia
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Xuan Li
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Zhiqi Lee
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Jie Zhang
- Department of Radiation Medicine, School of Preventive Medicine, Air Force Medical University, Xi'an 710032, China.
| | - Lijun Bai
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China.
| |
Collapse
|
6
|
Stripelis D, Gupta U, Saleem H, Dhinagar N, Ghai T, Anastasiou C, Sánchez R, Steeg GV, Ravi S, Naveed M, Thompson PM, Ambite JL. A federated learning architecture for secure and private neuroimaging analysis. PATTERNS (NEW YORK, N.Y.) 2024; 5:101031. [PMID: 39233693 PMCID: PMC11368680 DOI: 10.1016/j.patter.2024.101031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/10/2023] [Revised: 04/04/2024] [Accepted: 06/06/2024] [Indexed: 09/06/2024]
Abstract
The amount of biomedical data continues to grow rapidly. However, collecting data from multiple sites for joint analysis remains challenging due to security, privacy, and regulatory concerns. To overcome this challenge, we use federated learning, which enables distributed training of neural network models over multiple data sources without sharing data. Each site trains the neural network over its private data for some time and then shares the neural network parameters (i.e., weights and/or gradients) with a federation controller, which in turn aggregates the local models and sends the resulting community model back to each site, and the process repeats. Our federated learning architecture, MetisFL, provides strong security and privacy. First, sample data never leave a site. Second, neural network parameters are encrypted before transmission and the global neural model is computed under fully homomorphic encryption. Finally, we use information-theoretic methods to limit information leakage from the neural model to prevent a "curious" site from performing model inversion or membership attacks. We present a thorough evaluation of the performance of secure, private federated learning in neuroimaging tasks, including for predicting Alzheimer's disease and for brain age gap estimation (BrainAGE) from magnetic resonance imaging (MRI) studies in challenging, heterogeneous federated environments where sites have different amounts of data and statistical distributions.
Collapse
Affiliation(s)
- Dimitris Stripelis
- University of Southern California, Information Sciences Institute, Marina del Rey, CA 90292, USA
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | - Umang Gupta
- University of Southern California, Information Sciences Institute, Marina del Rey, CA 90292, USA
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | - Hamza Saleem
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | - Nikhil Dhinagar
- University of Southern California, Imaging Genetics Center, Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, Marina del Rey, CA 90292, USA
| | - Tanmay Ghai
- University of Southern California, Information Sciences Institute, Marina del Rey, CA 90292, USA
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | | | - Rafael Sánchez
- University of Southern California, Information Sciences Institute, Marina del Rey, CA 90292, USA
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | - Greg Ver Steeg
- University of California, Riverside, Riverside, CA 92521, USA
| | - Srivatsan Ravi
- University of Southern California, Information Sciences Institute, Marina del Rey, CA 90292, USA
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | - Muhammad Naveed
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| | - Paul M. Thompson
- University of Southern California, Imaging Genetics Center, Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, Marina del Rey, CA 90292, USA
| | - José Luis Ambite
- University of Southern California, Information Sciences Institute, Marina del Rey, CA 90292, USA
- University of Southern California, Computer Science Department, Los Angeles, CA 90089, USA
| |
Collapse
|
7
|
Kalantari N, Daneault V, Blais H, André C, Sanchez E, Lina JM, Arbour C, Gilbert D, Carrier J, Gosselin N. Cerebral Gray Matter May Not Explain Sleep Slow-Wave Characteristics after Severe Brain Injury. J Neurosci 2024; 44:e1306232024. [PMID: 38844342 PMCID: PMC11308330 DOI: 10.1523/jneurosci.1306-23.2024] [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: 07/12/2023] [Revised: 04/24/2024] [Accepted: 04/26/2024] [Indexed: 08/09/2024] Open
Abstract
Sleep slow waves are the hallmark of deeper non-rapid eye movement sleep. It is generally assumed that gray matter properties predict slow-wave density, morphology, and spectral power in healthy adults. Here, we tested the association between gray matter volume (GMV) and slow-wave characteristics in 27 patients with moderate-to-severe traumatic brain injury (TBI, 32.0 ± 12.2 years old, eight women) and compared that with 32 healthy controls (29.2 ± 11.5 years old, nine women). Participants underwent overnight polysomnography and cerebral MRI with a 3 Tesla scanner. A whole-brain voxel-wise analysis was performed to compare GMV between groups. Slow-wave density, morphology, and spectral power (0.4-6 Hz) were computed, and GMV was extracted from the thalamus, cingulate, insula, precuneus, and orbitofrontal cortex to test the relationship between slow waves and gray matter in regions implicated in the generation and/or propagation of slow waves. Compared with controls, TBI patients had significantly lower frontal and temporal GMV and exhibited a subtle decrease in slow-wave frequency. Moreover, higher GMV in the orbitofrontal cortex, insula, cingulate cortex, and precuneus was associated with higher slow-wave frequency and slope, but only in healthy controls. Higher orbitofrontal GMV was also associated with higher slow-wave density in healthy participants. While we observed the expected associations between GMV and slow-wave characteristics in healthy controls, no such associations were observed in the TBI group despite lower GMV. This finding challenges the presumed role of GMV in slow-wave generation and morphology.
Collapse
Affiliation(s)
- Narges Kalantari
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Department of Psychology, Université de Montréal, Montreal, Quebec H2V 2S9, Canada
| | - Véronique Daneault
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Department of Psychology, Université de Montréal, Montreal, Quebec H2V 2S9, Canada
| | - Hélène Blais
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
| | - Claire André
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Department of Psychology, Université de Montréal, Montreal, Quebec H2V 2S9, Canada
| | - Erlan Sanchez
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Cognitive Neurology Research Unit, Sunnybrook Research Institute, Toronto, Ontario M4N 3M5, Canada
| | - Jean-Marc Lina
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Department of Electrical Engineering, École de Technologie Supérieure, Montreal, Quebec H3C 1K3, Canada
| | - Caroline Arbour
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Faculty of Nursing, Université de Montréal, Montreal, Quebec H3T 1A8, Canada
| | - Danielle Gilbert
- Department of Radiology, Radiation Oncology and Nuclear Medicine, Université de Montréal, Montreal, Quebec H3T 1A4, Canada
- Department of Radiology, Hôpital du Sacré-Coeur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
| | - Julie Carrier
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Department of Psychology, Université de Montréal, Montreal, Quebec H2V 2S9, Canada
| | - Nadia Gosselin
- Center for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de Montréal, Montreal, Quebec H4J 1C5, Canada
- Department of Psychology, Université de Montréal, Montreal, Quebec H2V 2S9, Canada
| |
Collapse
|
8
|
Casanova R, Walker KA, Justice JN, Anderson A, Duggan MR, Cordon J, Barnard RT, Lu L, Hsu FC, Sedaghat S, Prizment A, Kritchevsky SB, Wagenknecht LE, Hughes TM. Associations of plasma proteomics and age-related outcomes with brain age in a diverse cohort. GeroScience 2024; 46:3861-3873. [PMID: 38438772 PMCID: PMC11226584 DOI: 10.1007/s11357-024-01112-4] [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: 12/07/2023] [Accepted: 02/26/2024] [Indexed: 03/06/2024] Open
Abstract
Machine learning models are increasingly being used to estimate "brain age" from neuroimaging data. The gap between chronological age and the estimated brain age gap (BAG) is potentially a measure of accelerated and resilient brain aging. Brain age calculated in this fashion has been shown to be associated with mortality, measures of physical function, health, and disease. Here, we estimate the BAG using a voxel-based elastic net regression approach, and then, we investigate its associations with mortality, cognitive status, and measures of health and disease in participants from Atherosclerosis Risk in Communities (ARIC) study who had a brain MRI at visit 5 of the study. Finally, we used the SOMAscan assay containing 4877 proteins to examine the proteomic associations with the MRI-defined BAG. Among N = 1849 participants (age, 76.4 (SD 5.6)), we found that increased values of BAG were strongly associated with increased mortality and increased severity of the cognitive status. Strong associations with mortality persisted when the analyses were performed in cognitively normal participants. In addition, it was strongly associated with BMI, diabetes, measures of physical function, hypertension, prevalent heart disease, and stroke. Finally, we found 33 proteins associated with BAG after a correction for multiple comparisons. The top proteins with positive associations to brain age were growth/differentiation factor 15 (GDF-15), Sushi, von Willebrand factor type A, EGF, and pentraxin domain-containing protein 1 (SEVP 1), matrilysin (MMP7), ADAMTS-like protein 2 (ADAMTS), and heat shock 70 kDa protein 1B (HSPA1B) while EGF-receptor (EGFR), mast/stem-cell-growth-factor-receptor (KIT), coagulation-factor-VII, and cGMP-dependent-protein-kinase-1 (PRKG1) were negatively associated to brain age. Several of these proteins were previously associated with dementia in ARIC. These results suggest that circulating proteins implicated in biological aging, cellular senescence, angiogenesis, and coagulation are associated with a neuroimaging measure of brain aging.
Collapse
Affiliation(s)
- Ramon Casanova
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Medical Center Blvd., Winston-Salem, NC, USA.
| | | | - Jamie N Justice
- Department of Internal Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| | - Andrea Anderson
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Medical Center Blvd., Winston-Salem, NC, USA
| | | | | | - Ryan T Barnard
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Medical Center Blvd., Winston-Salem, NC, USA
| | - Lingyi Lu
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Medical Center Blvd., Winston-Salem, NC, USA
| | - Fang-Chi Hsu
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Medical Center Blvd., Winston-Salem, NC, USA
| | - Sanaz Sedaghat
- School of Public Health, Oncology and Transplantation, University of Minnesota, Minneapolis, MN, USA
| | - Anna Prizment
- Division of Epidemiology and Community Health, School of Public Health, University of Minnesota, Minneapolis, MN, USA
| | - Stephen B Kritchevsky
- Department of Internal Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| | - Lynne E Wagenknecht
- Division of Public Health Sciences, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| | - Timothy M Hughes
- Department of Internal Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| |
Collapse
|
9
|
Hacker BJ, Imms PE, Dharani AM, Zhu J, Chowdhury NF, Chaudhari NN, Irimia A. Identification and Connectomic Profiling of Concussion Using Bayesian Machine Learning. J Neurotrauma 2024; 41:1883-1900. [PMID: 38482793 DOI: 10.1089/neu.2023.0509] [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: 04/30/2024] Open
Abstract
Accurate early diagnosis of concussion is useful to prevent sequelae and improve neurocognitive outcomes. Early after head impact, concussion diagnosis may be doubtful in persons whose neurological, neuroradiological, and/or neurocognitive examinations are equivocal. Such individuals can benefit from novel accurate assessments that complement clinical diagnostics. We introduce a Bayesian machine learning classifier to identify concussion through cortico-cortical connectome mapping from magnetic resonance imaging in persons with quasi-normal cognition and without neuroradiological findings. Classifier features are generated from connectivity matrices specifying the mean fractional anisotropy of white matter connections linking brain structures. Each connection's saliency to classification was quantified by training individual classifier instantiations using a single feature type. The classifier was tested on a discovery sample of 92 healthy controls (HCs; 26 females, age μ ± σ: 39.8 ± 15.5 years) and 471 adult mTBI patients (158 females, age μ ± σ: 38.4 ± 5.9 years). Results were replicated in an independent validation sample of 256 HCs (149 females, age μ ± σ: 55.3 ± 12.1 years) and 126 patients with concussion (46 females, age μ ± σ: 39.0 ± 17.7 years). Classifier accuracy exceeds 99% in both samples, suggesting robust generalizability to new samples. Notably, 13 bilateral cortico-cortical connection pairs predict diagnostic status with accuracy exceeding 99% in both discovery and validation samples. Many such connection pairs are between prefrontal cortex structures, fronto-limbic and fronto-subcortical structures, and occipito-temporal structures in the ventral ("what") visual stream. This and related connectivity form a highly salient network of brain connections that is particularly vulnerable to concussion. Because these connections are important in mediating cognitive control, memory, and attention, our findings explain the high frequency of cognitive disturbances after concussion. Our classifier was trained and validated on concussed participants with cognitive profiles very similar to those of HCs. This suggests that the classifier can complement current diagnostics by providing independent information in clinical contexts where patients have quasi-normal cognition but where concussion diagnosis stands to benefit from additional evidence.
Collapse
Affiliation(s)
- Benjamin J Hacker
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
- Mork Family Department of Chemical Engineering and Materials Science, Viterbi School of Engineering, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| | - Phoebe E Imms
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| | - Ammar M Dharani
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| | - Jessica Zhu
- Corwin D. Denney Research Center, Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| | - Nahian F Chowdhury
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| | - Nikhil N Chaudhari
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
- Corwin D. Denney Research Center, Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| | - Andrei Irimia
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
- Corwin D. Denney Research Center, Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
- Department of Quantitative and Computational Biology, Dana and David Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, California, USA
| |
Collapse
|
10
|
Dennis EL, Vervoordt S, Adamson MM, Houshang A, Bigler ED, Caeyenberghs K, Cole JH, Dams-O'Connor K, Deutscher EM, Dobryakova E, Genova HM, Grafman JH, Håberg AK, Hellstrøm T, Irimia A, Koliatsos VE, Lindsey HM, Livny A, Menon DK, Merkley TL, Mohamed AZ, Mondello S, Monti MM, Newcombe VF, Newsome MR, Ponsford J, Rabinowitz A, Smevik H, Spitz G, Venkatesan UM, Westlye LT, Zafonte R, Thompson PM, Wilde EA, Olsen A, Hillary FG. Accelerated Aging after Traumatic Brain Injury: An ENIGMA Multi-Cohort Mega-Analysis. Ann Neurol 2024; 96:365-377. [PMID: 38845484 DOI: 10.1002/ana.26952] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2023] [Revised: 04/10/2024] [Accepted: 04/15/2024] [Indexed: 07/11/2024]
Abstract
OBJECTIVE The long-term consequences of traumatic brain injury (TBI) on brain structure remain uncertain. Given evidence that a single significant brain injury event increases the risk of dementia, brain-age estimation could provide a novel and efficient indexing of the long-term consequences of TBI. Brain-age procedures use predictive modeling to calculate brain-age scores for an individual using structural magnetic resonance imaging (MRI) data. Complicated mild, moderate, and severe TBI (cmsTBI) is associated with a higher predicted age difference (PAD), but the progression of PAD over time remains unclear. We sought to examine whether PAD increases as a function of time since injury (TSI) and if injury severity and sex interacted to influence this progression. METHODS Through the ENIGMA Adult Moderate and Severe (AMS)-TBI working group, we examine the largest TBI sample to date (n = 343), along with controls, for a total sample size of n = 540, to replicate and extend prior findings in the study of TBI brain age. Cross-sectional T1w-MRI data were aggregated across 7 cohorts, and brain age was established using a similar brain age algorithm to prior work in TBI. RESULTS Findings show that PAD widens with longer TSI, and there was evidence for differences between sexes in PAD, with men showing more advanced brain age. We did not find strong evidence supporting a link between PAD and cognitive performance. INTERPRETATION This work provides evidence that changes in brain structure after cmsTBI are dynamic, with an initial period of change, followed by relative stability in brain morphometry, eventually leading to further changes in the decades after a single cmsTBI. ANN NEUROL 2024;96:365-377.
Collapse
Affiliation(s)
- Emily L Dennis
- Department of Neurology, University of Utah, Salt Lake City, UT, USA
- George E. Whalen Veterans Affairs Medical Center, Salt Lake City, UT, USA
| | | | - Maheen M Adamson
- Women's Operational Military Exposure Network (WOMEN) & Rehabilitation, VA Palo Alto Healthcare System, Palo Alto, CA, USA
- Neurosurgery, Stanford University School of Medicine, Stanford, CA, USA
| | - Amiri Houshang
- Neuroscience Research Center, Institute of Neuropharmacology, Kerman University of Medical Sciences, Kerman, Iran
- Department of Radiology & Nuclear Medicine, Amsterdam UMC, Amsterdam, The Netherlands
| | - Erin D Bigler
- Department of Neurology, University of Utah, Salt Lake City, UT, USA
- Department of Psychology and Neuroscience Center, Brigham Young University, Provo, UT, USA
| | - Karen Caeyenberghs
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia
| | - James H Cole
- Centre for Medical Image Computing, Computer Science, University College London, London, UK
- Dementia Research Centre, Queen Square Institute of Neurology, University College London, London, UK
| | - Kristen Dams-O'Connor
- Department of Rehabilitation and Human Performance, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Evelyn M Deutscher
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia
| | - Ekaterina Dobryakova
- Center for Traumatic Brain Injury, Kessler Foundation, East Hanover, NJ, USA
- Rutgers New Jersey Medical School, Newark, NJ, USA
| | - Helen M Genova
- Rutgers New Jersey Medical School, Newark, NJ, USA
- Center for Neuropsychology and Neuroscience Research, Kessler Foundation, East Hanover, NJ, USA
| | | | - Asta K Håberg
- Department of Neuromedicine and Movement Science, Faculty of Medicine and Health Sciences, NTNU, Trondheim, Norway
- Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway
| | - Torgeir Hellstrøm
- Department of Physical Medicine and Rehabilitation, Oslo University Hospital, Oslo, Norway
| | - Andrei Irimia
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA, USA
- Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA
- Department of Quantitative and Computational Biology, Dornsife College of Arts and Sciences, University of Southern California, Los Angeles, CA, USA
| | - Vassilis E Koliatsos
- Departments of Pathology (Neuropathology), Neurology, and Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Neuropsychiatry Program, Sheppard and Enoch Pratt Hospital, Baltimore, MD, USA
| | - Hannah M Lindsey
- Department of Neurology, University of Utah, Salt Lake City, UT, USA
| | - Abigail Livny
- Division of Diagnostic Imaging, Sheba Medical Center, Tel-Aviv, Israel
- Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
- Sagol Neuroscience School, Tel-Aviv University, Tel-Aviv, Israel
| | - David K Menon
- Department of Medicine, University of Cambridge, Cambridge, UK
| | - Tricia L Merkley
- Department of Neurology, University of Utah, Salt Lake City, UT, USA
- Department of Psychology and Neuroscience Center, Brigham Young University, Provo, UT, USA
| | - Abdalla Z Mohamed
- Thompson Institute, University of the Sunshine Coast, Birtinya, Australia
| | - Stefania Mondello
- Department of Biomedical and Dental Sciences and Morphofunctional Imaging, University of Messina, Messina, Italy
| | - Martin M Monti
- Department of Psychology, UCLA, Los Angeles, CA, USA
- Brain Injury Research Center (BIRC), Department of Neurosurgery, UCLA, Los Angeles, CA, USA
| | | | - Mary R Newsome
- Department of Neurology, University of Utah, Salt Lake City, UT, USA
- George E. Whalen Veterans Affairs Medical Center, Salt Lake City, UT, USA
| | - Jennie Ponsford
- Monash-Epworth Rehabilitation Research Centre, School of Psychological Sciences, Monash University, Melbourne, Australia
- School of Psychological Sciences, Monash University, Melbourne, Australia
| | - Amanda Rabinowitz
- Moss Rehabilitation Research Institute, Elkins Park, PA, USA
- Department of Rehabilitation Medicine, Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, PA, USA
| | - Hanne Smevik
- Department of Psychology, NTNU, Trondheim, Norway
- NorHEAD - Norwegian Centre for Headache Research, NTNU, Trondheim, Norway
| | - Gershon Spitz
- Monash-Epworth Rehabilitation Research Centre, School of Psychological Sciences, Monash University, Melbourne, Australia
- School of Psychological Sciences, Monash University, Melbourne, Australia
- Department of Neuroscience, Central Clinical School, Monash University, Melbourne, Australia
| | - Umesh M Venkatesan
- Moss Rehabilitation Research Institute, Elkins Park, PA, USA
- Department of Rehabilitation Medicine, Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, PA, USA
| | - Lars T Westlye
- Department of Psychology, University of Oslo, Oslo, Norway
- NORMENT, Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway
| | - Ross Zafonte
- Department of Physical Medicine and Rehabilitation, Massachusetts General Hospital/Brigham & Women's Hospital, Boston, MA, USA
- Spaulding Rehabilitation Hospital, Boston, MA, USA
| | - Paul M Thompson
- Imaging Genetics Center, Stevens Neuroimaging & Informatics Institute, Keck School of Medicine of USC, Marina del Rey, CA, USA
- Departments of Neurology, Pediatrics, Psychiatry, Radiology, Engineering, and Ophthalmology, USC, Los Angeles, CA, USA
| | - Elisabeth A Wilde
- Department of Neurology, University of Utah, Salt Lake City, UT, USA
- George E. Whalen Veterans Affairs Medical Center, Salt Lake City, UT, USA
| | - Alexander Olsen
- Department of Psychology, NTNU, Trondheim, Norway
- NorHEAD - Norwegian Centre for Headache Research, NTNU, Trondheim, Norway
- Clinic of Rehabilitation, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway
| | - Frank G Hillary
- Department of Psychology, Penn State University, State College, PA, USA
| |
Collapse
|
11
|
Uparela-Reyes MJ, Villegas-Trujillo LM, Cespedes J, Velásquez-Vera M, Rubiano AM. Usefulness of Artificial Intelligence in Traumatic Brain Injury: A Bibliometric Analysis and Mini-review. World Neurosurg 2024; 188:83-92. [PMID: 38759786 DOI: 10.1016/j.wneu.2024.05.065] [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: 03/08/2024] [Accepted: 05/10/2024] [Indexed: 05/19/2024]
Abstract
BACKGROUND Traumatic brain injury (TBI) has become a major source of disability worldwide, increasing the interest in algorithms that use artificial intelligence (AI) to optimize the interpretation of imaging studies, prognosis estimation, and critical care issues. In this study we present a bibliometric analysis and mini-review on the main uses that have been developed for TBI in AI. METHODS The results informing this review come from a Scopus database search as of April 15, 2023. The bibliometric analysis was carried out via the mapping bibliographic metrics method. Knowledge mapping was made in the VOSviewer software (V1.6.18), analyzing the "link strength" of networks based on co-occurrence of key words, countries co-authorship, and co-cited authors. In the mini-review section, we highlight the main findings and contributions of the studies. RESULTS A total of 495 scientific publications were identified from 2000 to 2023, with 9262 citations published since 2013. Among the 160 journals identified, The Journal of Neurotrauma, Frontiers in Neurology, and PLOS ONE were those with the greatest number of publications. The most frequently co-occurring key words were: "machine learning", "deep learning", "magnetic resonance imaging", and "intracranial pressure". The United States accounted for more collaborations than any other country, followed by United Kingdom and China. Four co-citation author clusters were found, and the top 20 papers were divided into reviews and original articles. CONCLUSIONS AI has become a relevant research field in TBI during the last 20 years, demonstrating great potential in imaging, but a more modest performance for prognostic estimation and neuromonitoring.
Collapse
Affiliation(s)
- Maria José Uparela-Reyes
- Neurosurgery Section, School of Medicine, Universidad del Valle, Cali, Colombia; Neurosurgery Section, Hospital Universitario del Valle, Cali, Colombia.
| | - Lina María Villegas-Trujillo
- Neurosurgery Section, School of Medicine, Universidad del Valle, Cali, Colombia; School of Biomedical Sciences, Universidad del Valle, Cali, Colombia
| | - Jorge Cespedes
- Comprehensive Epilepsy Center, Yale University, New Haven, Connecticut, USA
| | - Miguel Velásquez-Vera
- Neurosurgery Section, School of Medicine, Universidad del Valle, Cali, Colombia; Neurosurgery Section, Hospital Universitario del Valle, Cali, Colombia
| | - Andrés M Rubiano
- Neurosurgery Section, School of Medicine, Universidad del Valle, Cali, Colombia; Neurosurgery Section, Hospital Universitario del Valle, Cali, Colombia; INUB-Meditech Research Group, Neurosciences Institute, Universidad El Bosque, Bogotá, Colombia
| |
Collapse
|
12
|
Gaser C, Kalc P, Cole JH. A perspective on brain-age estimation and its clinical promise. NATURE COMPUTATIONAL SCIENCE 2024:10.1038/s43588-024-00659-8. [PMID: 39048692 DOI: 10.1038/s43588-024-00659-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 06/12/2024] [Indexed: 07/27/2024]
Abstract
Brain-age estimation has gained increased attention in the neuroscientific community owing to its potential use as a biomarker of brain health. The difference between estimated and chronological age based on neuroimaging data enables a unique perspective on brain development and aging, with multiple open questions still remaining in the brain-age research field. This Perspective presents an overview of current advancements in the field and envisions the future evolution of the brain-age framework before its potential deployment in hospital settings.
Collapse
Affiliation(s)
- Christian Gaser
- Structural Brain Mapping Group, Department of Neurology, Jena University Hospital, Jena, Germany.
- Department of Psychiatry and Psychotherapy, Jena University Hospital, Jena, Germany.
- German Centre for Mental Health (DZPG), Jena-Halle-Magdeburg, Jena, Germany.
| | - Polona Kalc
- Structural Brain Mapping Group, Department of Neurology, Jena University Hospital, Jena, Germany
| | - James H Cole
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Dementia Research Centre, Queen Square Institute of Neurology, University College London, London, UK
| |
Collapse
|
13
|
Zhu R, Qu J, Xu G, Wu Y, Xin J, Wang D. Clinical and multimodal imaging features of adult-onset neuronal intranuclear inclusion disease. Neurol Sci 2024:10.1007/s10072-024-07699-y. [PMID: 39023713 DOI: 10.1007/s10072-024-07699-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Accepted: 07/09/2024] [Indexed: 07/20/2024]
Abstract
OBJECTIVES This study aimed to analyze the clinical and multimodal imaging manifestations of adult-onset neuronal intranuclear inclusion disease (NIID) patients and to investigate NIID-specific neuroimaging biomarkers. METHODS Forty patients were retrospectively enrolled from the Qilu Hospital of Shandong University. We analyzed the clinical and imaging characteristics of 40 adult-onset NIID patients and investigated the correlation between these characteristics and genetic markers and neuropsychological scores. We further explored NIID-specific alterations using multimodal imaging indices, including diffusion tensor imaging (DTI), magnetic resonance spectroscopy (MRS), and brain age estimation. In addition, we summarized the dynamic evolution pattern of NIID by examining the changes in diffusion weighted imaging (DWI) signals over time. RESULTS The NIID patients' ages ranged from 31 to 77 years. Cognitive impairment was the most common symptom (30/40, 75.0%), while some patients (18/40, 45.0%) initially presented with episodic symptoms such as headache (10/40, 25.0%). Patients with cognitive impairment symptoms had more cerebral white matter damage (χ2 = 11.475, P = 0.009). The most prevalent imaging manifestation was a high signal on DWI in the corticomedullary junction area, which was observed in 80.0% (32/40) of patients. In addition, the DWI dynamic evolution patterns could be classified into four main patterns. Diffusion tensor imaging (DTI) revealed extensive thinning of cerebral white matter fibers. The estimated brain age surpassed the patient's chronological age, signifying advanced brain aging in NIID patients. CONCLUSIONS The clinical manifestations of NIID exhibit significant variability, usually leading to misdiagnosis. Our results provided new imaging perspectives for accurately diagnosing and exploring this disease's neuropathological mechanisms.
Collapse
Affiliation(s)
- Rui Zhu
- Department of Radiology, Qilu Hospital of Shandong University, Jinan, 250012, China
| | - Junyu Qu
- Department of Radiology, Qilu Hospital of Shandong University, Jinan, 250012, China
| | - Guihua Xu
- Department of Radiology, Qilu Hospital of Shandong University, Jinan, 250012, China
| | - Yongsheng Wu
- Department of Radiology, Qilu Hospital of Shandong University, Jinan, 250012, China
| | - Jiaxiang Xin
- MR Research Collaboration, Siemens Healthineers Ltd, Shanghai, China
| | - Dawei Wang
- Department of Radiology, Qilu Hospital of Shandong University, Jinan, 250012, China.
- Qilu Medical Imaging Institute of Shandong University, Jinan, 250012, China.
- Shandong Key Laboratory: Magnetic Field-free Medicine & Functional Imaging (MF), Jinan, 250012, China.
| |
Collapse
|
14
|
Chen SJ, Li SJ, Hong HM, Hwang HF, Lin MR. Effects of Age, Sex, and Postconcussive Symptoms on Domain-Specific Quality of Life a Year After Mild Traumatic Brain Injury. J Head Trauma Rehabil 2024; 39:E225-E236. [PMID: 38032833 DOI: 10.1097/htr.0000000000000916] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/02/2023]
Abstract
OBJECTIVE To identify the factors influencing longitudinal changes in patients' scores across 6 domains of the Quality of Life after Brain Injury (QOLIBRI) instrument 1 year after mild traumatic brain injury (mTBI). DESIGN This was a longitudinal cohort study. PARTICIPANTS AND SETTING Eligible patients with a new diagnosis of mTBI were recruited from the outpatient clinics of the neurosurgery departments of 3 teaching hospitals in Taipei City, Taiwan. In total, 672 patients participated in the baseline assessment. Postinjury follow-up was conducted at 6 and 12 months. MAIN OUTCOME MEASURE Six domains of the 37-item QOLIBRI: Cognition, Self, Daily Life and Autonomy, Social Relationships, Emotions, and Physical Problems. RESULTS Linear mixed-effects analyses revealed that, among patients younger than 60 years, the scores of the Cognition, Self, Daily Life and Autonomy, and Social Relationships domains significantly increased 6 months after injury; furthermore, their scores of the Cognition, Self, and Daily Life and Autonomy significantly increased 12 months after injury. By contrast, among patients 60 years and older, the scores of these domains reduced from baseline to 6 and 12 months. No significant sex-based difference was observed in the changes in scores of any QOLIBRI domain. At 6 and 12 months post-injury, the scores of the Cognition, Emotions, and Physical Problems domains were significantly higher for patients with postconcussive symptoms than for those without these symptoms. CONCLUSIONS Although multiple characteristics of patients significantly affected their baseline scores on the 6 domains of the QOLIBRI, only age and postconcussive symptoms were significantly associated with longitudinal changes in their scores 6 and 12 months after mTBI.
Collapse
Affiliation(s)
- Sy-Jou Chen
- Author Affiliations: Department of Emergency Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan (Dr Chen); Institute of Injury Prevention and Control, College of Public Health, Taipei Medical University, Taipei, Taiwan (Drs Chen and Lin); Departments of Emergency Medicine (Dr Li) and Nursing (Ms Hong), Taipei Medical University Hospital, Taipei, Taiwan; Department of Nursing, National Taipei University of Nursing and Health Sciences, Taipei, Taiwan (Dr Hwang); and Programs in Medical Neuroscience, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan (Dr Lin)
| | | | | | | | | |
Collapse
|
15
|
Zhang D, She Y, Sun J, Cui Y, Yang X, Zeng X, Qin W. Brain Age Estimation from Overnight Sleep Electroencephalography with Multi-Flow Sequence Learning. Nat Sci Sleep 2024; 16:879-896. [PMID: 38974693 PMCID: PMC11227046 DOI: 10.2147/nss.s463495] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/10/2024] [Accepted: 06/19/2024] [Indexed: 07/09/2024] Open
Abstract
Purpose This study aims to improve brain age estimation by developing a novel deep learning model utilizing overnight electroencephalography (EEG) data. Methods We address limitations in current brain age prediction methods by proposing a model trained and evaluated on multiple cohort data, covering a broad age range. The model employs a one-dimensional Swin Transformer to efficiently extract complex patterns from sleep EEG signals and a convolutional neural network with attentional mechanisms to summarize sleep structural features. A multi-flow learning-based framework attentively merges these two features, employing sleep structural information to direct and augment the EEG features. A post-prediction model is designed to integrate the age-related features throughout the night. Furthermore, we propose a DecadeCE loss function to address the problem of an uneven age distribution. Results We utilized 18,767 polysomnograms (PSGs) from 13,616 subjects to develop and evaluate the proposed model. The model achieves a mean absolute error (MAE) of 4.19 and a correlation of 0.97 on the mixed-cohort test set, and an MAE of 6.18 years and a correlation of 0.78 on an independent test set. Our brain age estimation work reduced the error by more than 1 year compared to other studies that also used EEG, achieving the level of neuroimaging. The estimated brain age index demonstrated longitudinal sensitivity and exhibited a significant increase of 1.27 years in individuals with psychiatric or neurological disorders relative to healthy individuals. Conclusion The multi-flow deep learning model proposed in this study, based on overnight EEG, represents a more accurate approach for estimating brain age. The utilization of overnight sleep EEG for the prediction of brain age is both cost-effective and adept at capturing dynamic changes. These findings demonstrate the potential of EEG in predicting brain age, presenting a noninvasive and accessible method for assessing brain aging.
Collapse
Affiliation(s)
- Di Zhang
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| | - Yichong She
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| | - Jinbo Sun
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| | - Yapeng Cui
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| | - Xuejuan Yang
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| | - Xiao Zeng
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| | - Wei Qin
- Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China
- Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of China
| |
Collapse
|
16
|
Carr LM, Mustafa S, Care A, Collins-Praino LE. More than a number: Incorporating the aged phenotype to improve in vitro and in vivo modeling of neurodegenerative disease. Brain Behav Immun 2024; 119:554-571. [PMID: 38663775 DOI: 10.1016/j.bbi.2024.04.023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/22/2023] [Revised: 03/04/2024] [Accepted: 04/22/2024] [Indexed: 04/29/2024] Open
Abstract
Age is the number one risk factor for developing a neurodegenerative disease (ND), such as Alzheimer's disease (AD) or Parkinson's disease (PD). With our rapidly ageing world population, there will be an increased burden of ND and need for disease-modifying treatments. Currently, however, translation of research from bench to bedside in NDs is poor. This may be due, at least in part, to the failure to account for the potential effect of ageing in preclinical modelling of NDs. While ageing can impact upon physiological response in multiple ways, only a limited number of preclinical studies of ND have incorporated ageing as a factor of interest. Here, we evaluate the aged phenotype and highlight the critical, but unmet, need to incorporate aspects of this phenotype into both the in vitro and in vivo models used in ND research. Given technological advances in the field over the past several years, we discuss how these could be harnessed to create novel models of ND that more readily incorporate aspects of the aged phenotype. This includes a recently described in vitro panel of ageing markers, which could help lead to more standardised models and improve reproducibility across studies. Importantly, we cannot assume that young cells or animals yield the same responses as seen in the context of ageing; thus, an improved understanding of the biology of ageing, and how to appropriately incorporate this into the modelling of ND, will ensure the best chance for successful translation of new therapies to the aged patient.
Collapse
Affiliation(s)
- Laura M Carr
- School of Biomedicine, University of Adelaide, Adelaide, SA, Australia
| | - Sanam Mustafa
- School of Biomedicine, University of Adelaide, Adelaide, SA, Australia; Australian Research Council Centre of Excellence for Nanoscale Biophotonics, The University of Adelaide, Adelaide, SA, Australia; Davies Livestock Research Centre, The University of Adelaide, Roseworthy, SA, Australia
| | - Andrew Care
- School of Life Sciences, University of Technology Sydney, Sydney, NSW, Australia
| | - Lyndsey E Collins-Praino
- School of Biomedicine, University of Adelaide, Adelaide, SA, Australia; Australian Research Council Centre of Excellence for Nanoscale Biophotonics, The University of Adelaide, Adelaide, SA, Australia.
| |
Collapse
|
17
|
Pang Y, Cai Y, Xia Z, Gao X. Predicting brain age using Tri-UNet and various MRI scale features. Sci Rep 2024; 14:13742. [PMID: 38877107 PMCID: PMC11178849 DOI: 10.1038/s41598-024-63998-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Accepted: 06/04/2024] [Indexed: 06/16/2024] Open
Abstract
In the process of human aging, significant age-related changes occur in brain tissue. To assist individuals in assessing the degree of brain aging, screening for disease risks, and further diagnosing age-related diseases, it is crucial to develop an accurate method for predicting brain age. This paper proposes a multi-scale feature fusion method called Tri-UNet based on the U-Net network structure, as well as a brain region information fusion method based on multi-channel input networks. These methods address the issue of insufficient image feature learning in brain neuroimaging data. They can effectively utilize features at different scales of MRI and fully leverage feature information from different regions of the brain. In the end, experiments were conducted on the Cam-CAN dataset, resulting in a minimum Mean Absolute Error (MAE) of 7.46. The results demonstrate that this method provides a new approach to feature learning at different scales in brain age prediction tasks, contributing to the advancement of the field and holding significance for practical applications in the context of elderly education.
Collapse
Affiliation(s)
- Yu Pang
- School of Science, Jilin Institute of Chemical Technology, Jilin, 130000, China.
| | - Yihuai Cai
- School of Science, Jilin Institute of Chemical Technology, Jilin, 130000, China.
| | - Zonghui Xia
- Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, 430079, China
| | - Xujie Gao
- School of Information Science and Technology, Beijing Forestry University, Beijing, 100083, China
| |
Collapse
|
18
|
An WW, Bhowmik AC, Nelson CA, Wilkinson CL. Prediction of chronological age from resting-state EEG power in the first three years of life. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.05.31.24308275. [PMID: 38853932 PMCID: PMC11160894 DOI: 10.1101/2024.05.31.24308275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2024]
Abstract
The infant brain undergoes rapid and significant developmental changes in the first three years of life. Understanding these changes through the prediction of chronological age using neuroimaging data can provide insights into typical and atypical brain development. We utilized longitudinal resting-state EEG data from 457 typically developing infants, comprising 938 recordings, to develop age prediction models. The multilayer perceptron model demonstrated the highest accuracy with an R2 of 0.82 and a mean absolute error of 92.4 days. Aperiodic offset and periodic theta, alpha, and beta power were identified as key predictors of age via Shapley values. Application of the model to EEG data from infants later diagnosed with autism spectrum disorder or Down syndrome revealed significant underestimations of chronological age. This study establishes the feasibility of using EEG to assess brain maturation in early childhood and supports its potential as a clinical tool for early identification of alterations in brain development.
Collapse
Affiliation(s)
- Winko W. An
- Developmental Medicine, Boston Children’s Hospital, 300 Longwood Avenue, Boston, 02115, MA, USA
- Rosamund Stone Zander Translational Neuroscience Center, Boston Children’s Hospital, 300 Longwood Avenue, Boston, 02115, MA, USA
- Harvard Medical School, 25 Shattuck St, Boston, 02115, MA, USA
| | - Aprotim C. Bhowmik
- Developmental Medicine, Boston Children’s Hospital, 300 Longwood Avenue, Boston, 02115, MA, USA
| | - Charles A. Nelson
- Developmental Medicine, Boston Children’s Hospital, 300 Longwood Avenue, Boston, 02115, MA, USA
- Harvard Medical School, 25 Shattuck St, Boston, 02115, MA, USA
- Harvard Graduate School of Education, 13 Appian Way, Cambridge, 02138, MA, USA
| | - Carol L. Wilkinson
- Developmental Medicine, Boston Children’s Hospital, 300 Longwood Avenue, Boston, 02115, MA, USA
- Harvard Medical School, 25 Shattuck St, Boston, 02115, MA, USA
| |
Collapse
|
19
|
Downing MG, Carty M, Olver J, Ponsford M, Acher R, Mckenzie D, Ponsford JL. The impact of age on outcome 2 years after traumatic brain injury: Case control study. Ann Phys Rehabil Med 2024; 67:101834. [PMID: 38518520 DOI: 10.1016/j.rehab.2024.101834] [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: 10/23/2022] [Revised: 02/07/2024] [Accepted: 02/10/2024] [Indexed: 03/24/2024]
Abstract
BACKGROUND Age is associated with outcome after traumatic brain injury (TBI). However, there are mixed findings across outcome domains and most studies lack controls. OBJECTIVES This cross-sectional study examined the association between age group (15-24 years, 25-34 years, 35-44 years, 45-54 years, 55-64 years, and 65 years or more) and outcomes 2 years after TBI in independence in daily activities, driving, public transportation use, employment, leisure activities, social integration, relationships and emotional functioning, relative to healthy controls. It was hypothesized that older individuals with TBI would have significantly poorer outcomes than controls in all domains except anxiety and depression, for which it was expected they would show better outcomes. Global functional outcome (measured using the Glasgow Outcome Scale-Extended) was also examined, and we hypothesized that older adults would have poorer outcomes than younger adults. METHODS Participants were 1897 individuals with TBI (mean, SD age 36.7, 17.7 years) who completed measures 2 years post-injury and 110 healthy controls (age 38.3, 17.5 years). RESULTS Compared to controls, individuals with TBI were less independent in most activities of daily living, participated less in leisure activities and employment, and were more socially isolated, anxious and depressed (p < 0.001). Those who were older in age were disproportionately less likely to be independent in light domestic activities, shopping and driving; and participated less in occupational activities relative to controls. Functional outcome was significantly higher in the youngest age group than in all older age groups (p < 0.001), but the younger groups were more likely to report being socially isolated (p < 0.001), depressed (p = 0.005) and anxious (p = 0.02), and less likely to be married or in a relationship (p < 0.001). CONCLUSION A greater focus is needed on addressing psychosocial issues in younger individuals with TBI, whereas those who are older may require more intensive therapy to maximise independence in activities of daily living and return to employment.
Collapse
Affiliation(s)
- Marina G Downing
- Turner Institute for Brain and Mental Health, School of Psychological Science, Monash University, Melbourne, Australia; Monash-Epworth Rehabilitation Research Centre, Melbourne, Australia; Epworth HealthCare, Melbourne, Australia.
| | - Meagan Carty
- Monash-Epworth Rehabilitation Research Centre, Melbourne, Australia; Epworth HealthCare, Melbourne, Australia
| | - John Olver
- Epworth HealthCare, Melbourne, Australia; Faculty of Medicine, Monash University, Melbourne, Australia
| | | | - Rose Acher
- Epworth HealthCare, Melbourne, Australia
| | | | - Jennie L Ponsford
- Turner Institute for Brain and Mental Health, School of Psychological Science, Monash University, Melbourne, Australia; Monash-Epworth Rehabilitation Research Centre, Melbourne, Australia; Epworth HealthCare, Melbourne, Australia
| |
Collapse
|
20
|
Villa C, Combi R. Epigenetics in Alzheimer's Disease: A Critical Overview. Int J Mol Sci 2024; 25:5970. [PMID: 38892155 PMCID: PMC11173284 DOI: 10.3390/ijms25115970] [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: 04/29/2024] [Revised: 05/27/2024] [Accepted: 05/28/2024] [Indexed: 06/21/2024] Open
Abstract
Epigenetic modifications have been implicated in a number of complex diseases as well as being a hallmark of organismal aging. Several reports have indicated an involvement of these changes in Alzheimer's disease (AD) risk and progression, most likely contributing to the dysregulation of AD-related gene expression measured by DNA methylation studies. Given that DNA methylation is tissue-specific and that AD is a brain disorder, the limitation of these studies is the ability to identify clinically useful biomarkers in a proxy tissue, reflective of the tissue of interest, that would be less invasive, more cost-effective, and easily obtainable. The age-related DNA methylation changes have also been used to develop different generations of epigenetic clocks devoted to measuring the aging in different tissues that sometimes suggests an age acceleration in AD patients. This review critically discusses epigenetic changes and aging measures as potential biomarkers for AD detection, prognosis, and progression. Given that epigenetic alterations are chemically reversible, treatments aiming at reversing these modifications will be also discussed as promising therapeutic strategies for AD.
Collapse
Affiliation(s)
| | - Romina Combi
- School of Medicine and Surgery, University of Milano-Bicocca, 20900 Monza, Italy;
| |
Collapse
|
21
|
Valdes-Hernandez PA, Johnson AJ, Montesino-Goicolea S, Nodarse CL, Bashyam V, Davatzikos C, Fillingim RB, Cruz-Almeida Y. Accelerated Brain Aging Mediates the Association Between Psychological Profiles and Clinical Pain in Knee Osteoarthritis. THE JOURNAL OF PAIN 2024; 25:104423. [PMID: 37952863 PMCID: PMC11144298 DOI: 10.1016/j.jpain.2023.11.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/28/2023] [Revised: 10/12/2023] [Accepted: 11/02/2023] [Indexed: 11/14/2023]
Abstract
Chronic pain is driven by factors across the biopsychosocial spectrum. Previously, we demonstrated that magnetic resonance images (MRI)-based brain-predicted age differences (brain-PAD: brain-predicted age minus chronological age) were significantly associated with pain severity in individuals with chronic knee pain. We also previously identified four distinct, replicable, multidimensional psychological profiles significantly associated with clinical pain. The brain aging-psychological characteristics interface in persons with chronic pain promises elucidating factors contributing to their poor health outcomes, yet this relationship is barely understood. That is why we examined the interplay between the psychological profiles in participants having chronic knee pain impacting function, brain-PAD, and clinical pain severity. Controlling for demographics and MRI scanner, we compared the brain-PAD among psychological profiles at baseline (n = 164) and over two years (n = 90). We also explored whether profile-related differences in pain severity were mediated by brain-PAD. Brain-PAD differed significantly between profiles (ANOVA's omnibus test, P = .039). Specifically, participants in the profile 3 group (high negative/low positive emotions) had an average brain-PAD ∼4 years higher than those in profile- (low somatic reactivity), with P = .047, Bonferroni-corrected, and than those in profile 2 (high coping), with P = .027, uncorrected. Repeated measures ANOVA revealed no significant change in profile-related brain-PAD differences over time, but there was a significant decrease in brain-PAD for profile 4 (high optimism/high positive affect), with P = .045. Moreover, profile-related differences in pain severity at baseline were partly explained by brain-PAD differences between profile 3 and 1, or 2; but brain-PAD did not significantly mediate the influence of variations in profiles on changes in pain severity over time. PERSPECTIVE: Accelerated brain aging could underlie the psychological-pain relationship, and psychological characteristics may predispose individuals with chronic knee pain to worse health outcomes via neuropsychological processes.
Collapse
Affiliation(s)
- Pedro A. Valdes-Hernandez
- Department of Community Dentistry and Behavioral Science, University of Florida, USA
- Pain Research and Intervention Center of Excellence, University of Florida, USA
- Center for Cognitive Aging and Memory, McKnight Brain Institute, University of Florida, USA
| | - Alisa J. Johnson
- Department of Community Dentistry and Behavioral Science, University of Florida, USA
- Pain Research and Intervention Center of Excellence, University of Florida, USA
| | - Soamy Montesino-Goicolea
- Department of Community Dentistry and Behavioral Science, University of Florida, USA
- Pain Research and Intervention Center of Excellence, University of Florida, USA
- Center for Cognitive Aging and Memory, McKnight Brain Institute, University of Florida, USA
| | - Chavier Laffitte Nodarse
- Department of Community Dentistry and Behavioral Science, University of Florida, USA
- Pain Research and Intervention Center of Excellence, University of Florida, USA
- Center for Cognitive Aging and Memory, McKnight Brain Institute, University of Florida, USA
| | - Vishnu Bashyam
- Center for Biomedical Image Computing & Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, USA
- Artificial Intelligence in Biomedical Imaging Lab (AIBIL), Department of Radiology, Perelman School of Medicine, University of Pennsylvania, USA
| | - Christos Davatzikos
- Center for Biomedical Image Computing & Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, USA
| | - Roger B. Fillingim
- Department of Community Dentistry and Behavioral Science, University of Florida, USA
- Pain Research and Intervention Center of Excellence, University of Florida, USA
| | - Yenisel Cruz-Almeida
- Department of Community Dentistry and Behavioral Science, University of Florida, USA
- Pain Research and Intervention Center of Excellence, University of Florida, USA
- Center for Cognitive Aging and Memory, McKnight Brain Institute, University of Florida, USA
- Department of Neuroscience, College of Medicine, University of Florida, USA
| |
Collapse
|
22
|
Zimmerman KA, Hain JA, Graham NSN, Rooney EJ, Lee Y, Del-Giovane M, Parker TD, Friedland D, Cross MJ, Kemp S, Wilson MG, Sylvester RJ, Sharp DJ. Prospective cohort study of long-term neurological outcomes in retired elite athletes: the Advanced BiomaRker, Advanced Imaging and Neurocognitive (BRAIN) Health Study protocol. BMJ Open 2024; 14:e082902. [PMID: 38663922 PMCID: PMC11043776 DOI: 10.1136/bmjopen-2023-082902] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Accepted: 03/26/2024] [Indexed: 04/28/2024] Open
Abstract
INTRODUCTION Although limited, recent research suggests that contact sport participation might have an adverse long-term effect on brain health. Further work is required to determine whether this includes an increased risk of neurodegenerative disease and/or subsequent changes in cognition and behaviour. The Advanced BiomaRker, Advanced Imaging and Neurocognitive Health Study will prospectively examine the neurological, psychiatric, psychological and general health of retired elite-level rugby union and association football/soccer players. METHODS AND ANALYSIS 400 retired athletes will be recruited (200 rugby union and 200 association football players, male and female). Athletes will undergo a detailed clinical assessment, advanced neuroimaging, blood testing for a range of brain health outcomes and neuropsychological assessment longitudinally. Follow-up assessments will be completed at 2 and 4 years after baseline visit. 60 healthy volunteers will be recruited and undergo an aligned assessment protocol including advanced neuroimaging, blood testing and neuropsychological assessment. We will describe the previous exposure to head injuries across the cohort and investigate relationships between biomarkers of brain injury and clinical outcomes including cognitive performance, clinical diagnoses and psychiatric symptom burden. ETHICS AND DISSEMINATION Relevant ethical approvals have been granted by the Camberwell St Giles Research Ethics Committee (Ref: 17/LO/2066). The study findings will be disseminated through manuscripts in clinical/academic journals, presentations at professional conferences and through participant and stakeholder communications.
Collapse
Affiliation(s)
- Karl A Zimmerman
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
- Centre for Injury Studies, Imperial College London, London, UK
| | - Jessica A Hain
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
| | - Neil S N Graham
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
- Centre for Injury Studies, Imperial College London, London, UK
| | - Erin Jane Rooney
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
- Institute of Sport, Exercise and Health (ISEH), University College London, London, UK
| | - Ying Lee
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
- Institute of Sport, Exercise and Health (ISEH), University College London, London, UK
| | - Martina Del-Giovane
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
| | - Thomas D Parker
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
- Department of Neurodegenerative Disease, The Dementia Research Centre, UCL Queen Square Institute of Neurology, London, UK
| | - Daniel Friedland
- Department of Brain Sciences, Imperial College London, London, UK
- Institute of Sport, Exercise and Health (ISEH), University College London, London, UK
| | - Matthew J Cross
- Carnegie Applied Rugby Research Centre, Carnegie School of Sport, Leeds Beckett University, Leeds, UK
- Premiership Rugby, London, UK
| | - Simon Kemp
- Rugby Football Union, Twickenham, UK
- London School of Hygiene & Tropical Medicine, London, UK
| | - Mathew G Wilson
- Institute of Sport, Exercise and Health (ISEH), University College London, London, UK
- HCA Healthcare Research Institute, London, UK
| | - Richard J Sylvester
- Institute of Sport, Exercise and Health (ISEH), University College London, London, UK
- Acute Stroke and Brain Injury Unit, National Hospital for Neurology and Neurosurgery, London, UK
| | - David J Sharp
- Centre for Care, Research and Technology, UK Dementia Research Institute, Imperial College London, London, UK
- Department of Brain Sciences, Imperial College London, London, UK
- Centre for Injury Studies, Imperial College London, London, UK
| |
Collapse
|
23
|
Wing D, Eyler LT, Lenze EJ, Wetherell JL, Nichols JF, Meeusen R, Godino J, Shimony JS, Snyder AZ, Nishino T, Nicol GE, Nagels G, Roelands B. Fatness but Not Fitness Linked to BrainAge: Longitudinal Changes in Brain Aging during an Exercise Intervention. Med Sci Sports Exerc 2024; 56:655-662. [PMID: 38079309 PMCID: PMC10947938 DOI: 10.1249/mss.0000000000003337] [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: 03/16/2024]
Abstract
PURPOSE Fitness, physical activity, body composition, and sleep have all been proposed to explain differences in brain health. We hypothesized that an exercise intervention would result in improved fitness and body composition and would be associated with improved structural brain health. METHODS In a randomized controlled trial, we studied 485 older adults who engaged in an exercise intervention ( n = 225) or a nonexercise comparison condition ( n = 260). Using magnetic resonance imaging, we estimated the physiological age of the brain (BrainAge) and derived a predicted age difference compared with chronological age (brain-predicted age difference (BrainPAD)). Aerobic capacity, physical activity, sleep, and body composition were assessed and their impact on BrainPAD explored. RESULTS There were no significant differences between experimental groups for any variable at any time point. The intervention group gained fitness, improved body composition, and increased total sleep time but did not have significant changes in BrainPAD. Analyses of changes in BrainPAD independent of group assignment indicated significant associations with changes in body fat percentage ( r (479) = 0.154, P = 0.001), and visceral adipose tissue (VAT) ( r (478) = 0.141, P = 0.002), but not fitness ( r (406) = -0.075, P = 0.129), sleep ( r (467) range, -0.017 to 0.063; P range, 0.171 to 0.710), or physical activity ( r (471) = -0.035, P = 0.444). With linear regression, changes in body fat percentage and VAT significantly predicted changes in BrainPAD ( β = 0.948, P = 0.003) with 1-kg change in VAT predicting 0.948 yr of change in BrainPAD. CONCLUSIONS In cognitively normal older adults, exercise did not appear to impact BrainPAD, although it was effective in improving fitness and body composition. Changes in body composition, but not fitness, physical activity, or sleep impacted BrainPAD. These findings suggest that focus on weight control, particularly reduction of central obesity, could be an interventional target to promote healthier brains.
Collapse
Affiliation(s)
- David Wing
- Herbert Wertheim School of Public Health; University of California, San Diego, CA
- Exercise and Physical Activity Resource Center (EPARC); University of California, San Diego, CA
| | - Lisa T. Eyler
- Department of Psychiatry, University of California, San Diego, CA
- Desert-Pacific Mental Illness Research, Education, and Clinical Center, San Diego Veterans Administration Healthcare System, San Diego, CA
| | - Eric J. Lenze
- Department of Psychiatry, Washington University School of Medicine, St. Louis, MO
| | - Julie Loebach Wetherell
- Mental Health Service, VA San Diego Healthcare System, San Diego, CA
- Department of Psychiatry, University of California, San Diego, CA
| | - Jeanne F. Nichols
- Herbert Wertheim School of Public Health; University of California, San Diego, CA
- Exercise and Physical Activity Resource Center (EPARC); University of California, San Diego, CA
| | - Romain Meeusen
- Human Physiology & Sports Physiotherapy Research Group, Faculty of Physical Education and Physiotherapy, Vrije Universiteit Brussel, Brussels, BELGIUM
- Brubotics, Vrije Universiteit Brussel, Brussels, BELGIUM
| | - Job Godino
- Herbert Wertheim School of Public Health; University of California, San Diego, CA
- Exercise and Physical Activity Resource Center (EPARC); University of California, San Diego, CA
| | - Joshua S. Shimony
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO
| | - Abraham Z. Snyder
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO
| | - Tomoyuki Nishino
- Department of Psychiatry, Washington University School of Medicine, St. Louis, MO
| | - Ginger E. Nicol
- Department of Psychiatry, Washington University School of Medicine, St. Louis, MO
| | - Guy Nagels
- Department of Neurology, UZ Brussel, Brussel, Belgium/Center for Neurosciences (C4N) Vrije Universiteit Brussel (VUB), Brussels, BELGIUM
| | - Bart Roelands
- Human Physiology & Sports Physiotherapy Research Group, Faculty of Physical Education and Physiotherapy, Vrije Universiteit Brussel, Brussels, BELGIUM
- Brubotics, Vrije Universiteit Brussel, Brussels, BELGIUM
| |
Collapse
|
24
|
Phyo AZZ, Fransquet PD, Wrigglesworth J, Woods RL, Espinoza SE, Ryan J. Sex differences in biological aging and the association with clinical measures in older adults. GeroScience 2024; 46:1775-1788. [PMID: 37747619 PMCID: PMC10828143 DOI: 10.1007/s11357-023-00941-z] [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: 07/31/2023] [Accepted: 09/11/2023] [Indexed: 09/26/2023] Open
Abstract
Females live longer than males, and there are sex disparities in physical health and disease incidence. However, sex differences in biological aging have not been consistently reported and may differ depending on the measure used. This study aimed to determine the correlations between epigenetic age acceleration (AA), and other markers of biological aging, separately in males and females. We additionally explored the extent to which these AA measures differed according to socioeconomic characteristics, clinical markers, and diseases. Epigenetic clocks (HorvathAge, HannumAge, PhenoAge, GrimAge, GrimAge2, and DunedinPACE) were estimated in blood from 560 relatively healthy Australians aged ≥ 70 years (females, 50.7%) enrolled in the ASPREE study. A system-wide deficit accumulation frailty index (FI) composed of 67 health-related measures was generated. Brain age and subsequently brain-predicted age difference (brain-PAD) were estimated from neuroimaging. Females had significantly reduced AA than males, but higher FI, and there was no difference in brain-PAD. FI had the strongest correlation with DunedinPACE (range r: 0.21 to 0.24 in both sexes). Brain-PAD was not correlated with any biological aging measures. Significant correlations between AA and sociodemographic characteristics and health markers were more commonly found in females (e.g., for DunedinPACE and systolic blood pressure r = 0.2, p < 0.001) than in males. GrimAA and Grim2AA were significantly associated with obesity and depression in females, while in males, hypertension, diabetes, and chronic kidney disease were associated with these clocks, as well as DunedinPACE. Our findings highlight the importance of considering sex differences when investigating the link between biological age and clinical measures.
Collapse
Affiliation(s)
- Aung Zaw Zaw Phyo
- Biological Neuropsychiatry & Dementia Unit, School of Public Health and Preventive Medicine, Monash University, 553, St. Kilda Road, Melbourne, VIC, 3004, Australia.
| | - Peter D Fransquet
- Biological Neuropsychiatry & Dementia Unit, School of Public Health and Preventive Medicine, Monash University, 553, St. Kilda Road, Melbourne, VIC, 3004, Australia
- School of Psychology, Deakin University, Burwood, Melbourne, VIC, 3125, Australia
| | - Jo Wrigglesworth
- Biological Neuropsychiatry & Dementia Unit, School of Public Health and Preventive Medicine, Monash University, 553, St. Kilda Road, Melbourne, VIC, 3004, Australia
| | - Robyn L Woods
- ASPREE Research Unit, School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, 3004, Australia
| | - Sara E Espinoza
- Center for Translational Geroscience, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Joanne Ryan
- Biological Neuropsychiatry & Dementia Unit, School of Public Health and Preventive Medicine, Monash University, 553, St. Kilda Road, Melbourne, VIC, 3004, Australia
| |
Collapse
|
25
|
Lim H, Joo Y, Ha E, Song Y, Yoon S, Shin T. Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network. Bioengineering (Basel) 2024; 11:265. [PMID: 38534539 DOI: 10.3390/bioengineering11030265] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 02/28/2024] [Accepted: 03/01/2024] [Indexed: 03/28/2024] Open
Abstract
Convolutional neural networks (CNNs) have been used widely to predict biological brain age based on brain magnetic resonance (MR) images. However, CNNs focus mainly on spatially local features and their aggregates and barely on the connective information between distant regions. To overcome this issue, we propose a novel multi-hop graph attention (MGA) module that exploits both the local and global connections of image features when combined with CNNs. After insertion between convolutional layers, MGA first converts the convolution-derived feature map into graph-structured data by using patch embedding and embedding-distance-based scoring. Multi-hop connections between the graph nodes are modeled by using the Markov chain process. After performing multi-hop graph attention, MGA re-converts the graph into an updated feature map and transfers it to the next convolutional layer. We combined the MGA module with sSE (spatial squeeze and excitation)-ResNet18 for our final prediction model (MGA-sSE-ResNet18) and performed various hyperparameter evaluations to identify the optimal parameter combinations. With 2788 three-dimensional T1-weighted MR images of healthy subjects, we verified the effectiveness of MGA-sSE-ResNet18 with comparisons to four established, general-purpose CNNs and two representative brain age prediction models. The proposed model yielded an optimal performance with a mean absolute error of 2.822 years and Pearson's correlation coefficient (PCC) of 0.968, demonstrating the potential of the MGA module to improve the accuracy of brain age prediction.
Collapse
Affiliation(s)
- Heejoo Lim
- Division of Mechanical and Biomedical Engineering, Ewha W. University, Seoul 03760, Republic of Korea
- Graduate Program in Smart Factory, Ewha W. University, Seoul 03760, Republic of Korea
| | - Yoonji Joo
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
| | - Eunji Ha
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
| | - Yumi Song
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
- Department of Brain and Cognitive Sciences, Ewha W. University, Seoul 03760, Republic of Korea
| | - Sujung Yoon
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
- Department of Brain and Cognitive Sciences, Ewha W. University, Seoul 03760, Republic of Korea
| | - Taehoon Shin
- Division of Mechanical and Biomedical Engineering, Ewha W. University, Seoul 03760, Republic of Korea
- Graduate Program in Smart Factory, Ewha W. University, Seoul 03760, Republic of Korea
| |
Collapse
|
26
|
Geleta U, Prajapati P, Bachstetter A, Nelson PT, Wang WX. Sex-Biased Expression and Response of microRNAs in Neurological Diseases and Neurotrauma. Int J Mol Sci 2024; 25:2648. [PMID: 38473893 PMCID: PMC10931569 DOI: 10.3390/ijms25052648] [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: 01/27/2024] [Revised: 02/16/2024] [Accepted: 02/21/2024] [Indexed: 03/14/2024] Open
Abstract
Neurological diseases and neurotrauma manifest significant sex differences in prevalence, progression, outcome, and therapeutic responses. Genetic predisposition, sex hormones, inflammation, and environmental exposures are among many physiological and pathological factors that impact the sex disparity in neurological diseases. MicroRNAs (miRNAs) are a powerful class of gene expression regulator that are extensively involved in mediating biological pathways. Emerging evidence demonstrates that miRNAs play a crucial role in the sex dimorphism observed in various human diseases, including neurological diseases. Understanding the sex differences in miRNA expression and response is believed to have important implications for assessing the risk of neurological disease, defining therapeutic intervention strategies, and advancing both basic research and clinical investigations. However, there is limited research exploring the extent to which miRNAs contribute to the sex disparities observed in various neurological diseases. Here, we review the current state of knowledge related to the sexual dimorphism in miRNAs in neurological diseases and neurotrauma research. We also discuss how sex chromosomes may contribute to the miRNA sexual dimorphism phenomenon. We attempt to emphasize the significance of sexual dimorphism in miRNA biology in human diseases and to advocate a gender/sex-balanced science.
Collapse
Affiliation(s)
- Urim Geleta
- Sanders-Brown Center on Aging, College of Medicine, University of Kentucky, Lexington, KY 40536, USA; (U.G.); (P.P.); (A.B.); (P.T.N.)
| | - Paresh Prajapati
- Sanders-Brown Center on Aging, College of Medicine, University of Kentucky, Lexington, KY 40536, USA; (U.G.); (P.P.); (A.B.); (P.T.N.)
| | - Adam Bachstetter
- Sanders-Brown Center on Aging, College of Medicine, University of Kentucky, Lexington, KY 40536, USA; (U.G.); (P.P.); (A.B.); (P.T.N.)
- Spinal Cord and Brain Injury Research Center, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
- Neuroscience, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
| | - Peter T. Nelson
- Sanders-Brown Center on Aging, College of Medicine, University of Kentucky, Lexington, KY 40536, USA; (U.G.); (P.P.); (A.B.); (P.T.N.)
- Spinal Cord and Brain Injury Research Center, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
- Pathology and Laboratory Medicine, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
| | - Wang-Xia Wang
- Sanders-Brown Center on Aging, College of Medicine, University of Kentucky, Lexington, KY 40536, USA; (U.G.); (P.P.); (A.B.); (P.T.N.)
- Spinal Cord and Brain Injury Research Center, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
- Pathology and Laboratory Medicine, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
| |
Collapse
|
27
|
Kalc P, Dahnke R, Hoffstaedter F, Gaser C. BrainAGE: Revisited and reframed machine learning workflow. Hum Brain Mapp 2024; 45:e26632. [PMID: 38379519 PMCID: PMC10879910 DOI: 10.1002/hbm.26632] [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: 08/18/2023] [Revised: 01/23/2024] [Accepted: 02/05/2024] [Indexed: 02/22/2024] Open
Abstract
Since the introduction of the BrainAGE method, novel machine learning methods for brain age prediction have continued to emerge. The idea of estimating the chronological age from magnetic resonance images proved to be an interesting field of research due to the relative simplicity of its interpretation and its potential use as a biomarker of brain health. We revised our previous BrainAGE approach, originally utilising relevance vector regression (RVR), and substituted it with Gaussian process regression (GPR), which enables more stable processing of larger datasets, such as the UK Biobank (UKB). In addition, we extended the global BrainAGE approach to regional BrainAGE, providing spatially specific scores for five brain lobes per hemisphere. We tested the performance of the new algorithms under several different conditions and investigated their validity on the ADNI and schizophrenia samples, as well as on a synthetic dataset of neocortical thinning. The results show an improved performance of the reframed global model on the UKB sample with a mean absolute error (MAE) of less than 2 years and a significant difference in BrainAGE between healthy participants and patients with Alzheimer's disease and schizophrenia. Moreover, the workings of the algorithm show meaningful effects for a simulated neocortical atrophy dataset. The regional BrainAGE model performed well on two clinical samples, showing disease-specific patterns for different levels of impairment. The results demonstrate that the new improved algorithms provide reliable and valid brain age estimations.
Collapse
Affiliation(s)
- Polona Kalc
- Structural Brain Mapping Group, Department of NeurologyJena University HospitalJenaGermany
| | - Robert Dahnke
- Structural Brain Mapping Group, Department of NeurologyJena University HospitalJenaGermany
- Department of Psychiatry and PsychotherapyJena University HospitalJenaGermany
| | - Felix Hoffstaedter
- Forschungszentrum Jülich, Institute of Neuroscience and Medicine, Brain and Behaviour (INM‐7)JülichGermany
- Institute of Systems Neuroscience, Medical Faculty, Heinrich Heine University DüsseldorfDüsseldorfGermany
| | - Christian Gaser
- Structural Brain Mapping Group, Department of NeurologyJena University HospitalJenaGermany
- Department of Psychiatry and PsychotherapyJena University HospitalJenaGermany
- German Center for Mental Health (DZPG)Jena‐Halle‐MagdeburgGermany
| | | |
Collapse
|
28
|
Domínguez D JF, Stewart A, Burmester A, Akhlaghi H, O'Brien K, Bollmann S, Caeyenberghs K. Improving quantitative susceptibility mapping for the identification of traumatic brain injury neurodegeneration at the individual level. Z Med Phys 2024:S0939-3889(24)00001-1. [PMID: 38336583 DOI: 10.1016/j.zemedi.2024.01.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 12/19/2023] [Accepted: 01/07/2024] [Indexed: 02/12/2024]
Abstract
BACKGROUND Emerging evidence suggests that traumatic brain injury (TBI) is a major risk factor for developing neurodegenerative disease later in life. Quantitative susceptibility mapping (QSM) has been used by an increasing number of studies in investigations of pathophysiological changes in TBI. However, generating artefact-free quantitative susceptibility maps in brains with large focal lesions, as in the case of moderate-to-severe TBI (ms-TBI), is particularly challenging. To address this issue, we utilized a novel two-pass masking technique and reconstruction procedure (two-pass QSM) to generate quantitative susceptibility maps (QSMxT; Stewart et al., 2022, Magn Reson Med.) in combination with the recently developed virtual brain grafting (VBG) procedure for brain repair (Radwan et al., 2021, NeuroImage) to improve automated delineation of brain areas. We used QSMxT and VBG to generate personalised QSM profiles of individual patients with reference to a sample of healthy controls. METHODS Chronic ms-TBI patients (N = 8) and healthy controls (N = 12) underwent (multi-echo) GRE, and anatomical MRI (MPRAGE) on a 3T Siemens PRISMA scanner. We reconstructed the magnetic susceptibility maps using two-pass QSM from QSMxT. We then extracted values of magnetic susceptibility in grey matter (GM) regions (following brain repair via VBG) across the whole brain and determined if they deviate from a reference healthy control group [Z-score < -3.43 or > 3.43, relative to the control mean], with the aim of obtaining personalised QSM profiles. RESULTS Using two-pass QSM, we achieved susceptibility maps with a substantial increase in quality and reduction in artefacts irrespective of the presence of large focal lesions, compared to single-pass QSM. In addition, VBG minimised the loss of GM regions and exclusion of patients due to failures in the region delineation step. Our findings revealed deviations in magnetic susceptibility measures from the HC group that differed across individual TBI patients. These changes included both increases and decreases in magnetic susceptibility values in multiple GM regions across the brain. CONCLUSIONS We illustrate how to obtain magnetic susceptibility values at the individual level and to build personalised QSM profiles in ms-TBI patients. Our approach opens the door for QSM investigations in more severely injured patients. Such profiles are also critical to overcome the inherent heterogeneity of clinical populations, such as ms-TBI, and to characterize the underlying mechanisms of neurodegeneration at the individual level more precisely. Moreover, this new personalised QSM profiling could in the future assist clinicians in assessing recovery and formulating a neuroscience-guided integrative rehabilitation program tailored to individual TBI patients.
Collapse
Affiliation(s)
- Juan F Domínguez D
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia.
| | - Ashley Stewart
- School of Information Technology and Electrical Engineering, Faculty of Engineering, Architecture, and Information Technology, The University of Queensland, Brisbane, Australia
| | - Alex Burmester
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia
| | - Hamed Akhlaghi
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia; Department of Emergency Medicine, St. Vincent's Hospital, Melbourne, Australia
| | - Kieran O'Brien
- Siemens Healthcare Pty Ltd, Brisbane, Queensland, Australia
| | - Steffen Bollmann
- School of Information Technology and Electrical Engineering, Faculty of Engineering, Architecture, and Information Technology, The University of Queensland, Brisbane, Australia; Centre for Advanced Imaging, The University of Queensland, Brisbane, Australia
| | - Karen Caeyenberghs
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia
| |
Collapse
|
29
|
Guan S, Jiang R, Meng C, Biswal B. Brain age prediction across the human lifespan using multimodal MRI data. GeroScience 2024; 46:1-20. [PMID: 37733220 PMCID: PMC10828281 DOI: 10.1007/s11357-023-00924-0] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 08/22/2023] [Indexed: 09/22/2023] Open
Abstract
Measuring differences between an individual's age and biological age with biological information from the brain have the potential to provide biomarkers of clinically relevant neurological syndromes that arise later in human life. To explore the effect of multimodal brain magnetic resonance imaging (MRI) features on the prediction of brain age, we investigated how multimodal brain imaging data improved age prediction from more imaging features of structural or functional MRI data by using partial least squares regression (PLSR) and longevity data sets (age 6-85 years). First, we found that the age-predicted values for each of these ten features ranged from high to low: cortical thickness (R = 0.866, MAE = 7.904), all seven MRI features (R = 0.8594, MAE = 8.24), four features in structural MRI (R = 0.8591, MAE = 8.24), fALFF (R = 0.853, MAE = 8.1918), gray matter volume (R = 0.8324, MAE = 8.931), three rs-fMRI feature (R = 0.7959, MAE = 9.744), mean curvature (R = 0.7784, MAE = 10.232), ReHo (R = 0.7833, MAE = 10.122), ALFF (R = 0.7517, MAE = 10.844), and surface area (R = 0.719, MAE = 11.33). In addition, the significance of the volume and size of brain MRI data in predicting age was also studied. Second, our results suggest that all multimodal imaging features, except cortical thickness, improve brain-based age prediction. Third, we found that the left hemisphere contributed more to the age prediction, that is, the left hemisphere showed a greater weight in the age prediction than the right hemisphere. Finally, we found a nonlinear relationship between the predicted age and the amount of MRI data. Combined with multimodal and lifespan brain data, our approach provides a new perspective for chronological age prediction and contributes to a better understanding of the relationship between brain disorders and aging.
Collapse
Affiliation(s)
- Sihai Guan
- College of Electronic and Information, Southwest Minzu University, Chengdu, 610041, China.
- Key Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Chengdu, 610041, China.
| | - Runzhou Jiang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China
- Medical Equipment Department, Xiangyang No. 1 People's Hospital, Xiangyang, 441000, China
| | - Chun Meng
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China
| | - Bharat Biswal
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China.
- Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ, 07102, USA.
| |
Collapse
|
30
|
Gao C, Kim ME, Lee HH, Yang Q, Khairi NM, Kanakaraj P, Newlin NR, Archer DB, Jefferson AL, Taylor WD, Boyd BD, Beason-Held LL, Resnick SM, Huo Y, Van Schaik KD, Schilling KG, Moyer D, Išgum I, Landman BA. Predicting Age from White Matter Diffusivity with Residual Learning. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2024; 12926:129262I. [PMID: 39310214 PMCID: PMC11415267 DOI: 10.1117/12.3006525] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/25/2024]
Abstract
Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI's advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction.
Collapse
Affiliation(s)
- Chenyu Gao
- Dept. of Electrical and Computer Engineering, Vanderbilt University, Nashville, USA
| | - Michael E. Kim
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Ho Hin Lee
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Qi Yang
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Nazirah Mohd Khairi
- Dept. of Electrical and Computer Engineering, Vanderbilt University, Nashville, USA
| | | | - Nancy R. Newlin
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Derek B. Archer
- Vanderbilt Memory and Alzheimer’s Center, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Neurology, Vanderbilt University Medical Center, Nashville, USA
| | - Angela L. Jefferson
- Vanderbilt Memory and Alzheimer’s Center, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Neurology, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Medicine, Vanderbilt University Medical Center, Nashville, USA
| | - Warren D. Taylor
- Dept. of Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, USA
| | - Brian D. Boyd
- Vanderbilt Center for Cognitive Medicine, Vanderbilt University Medical Center, Nashville, USA
| | - Lori L. Beason-Held
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, USA
| | - Susan M. Resnick
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, USA
| | | | - Yuankai Huo
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Katherine D. Van Schaik
- Dept. of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, USA
| | - Kurt G. Schilling
- Dept. of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, USA
| | - Daniel Moyer
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Ivana Išgum
- Dept. of Biomedical Engineering and Physics, Dept. of Radiology and Nuclear Medicine, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, Netherlands
| | - Bennett A. Landman
- Dept. of Electrical and Computer Engineering, Vanderbilt University, Nashville, USA
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
- Dept. of Neurology, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, USA
| |
Collapse
|
31
|
Zhang Y, Xie R, Beheshti I, Liu X, Zheng G, Wang Y, Zhang Z, Zheng W, Yao Z, Hu B. Improving brain age prediction with anatomical feature attention-enhanced 3D-CNN. Comput Biol Med 2024; 169:107873. [PMID: 38181606 DOI: 10.1016/j.compbiomed.2023.107873] [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: 03/31/2023] [Revised: 11/17/2023] [Accepted: 12/17/2023] [Indexed: 01/07/2024]
Abstract
Currently, significant progress has been made in predicting brain age from structural Magnetic Resonance Imaging (sMRI) data using deep learning techniques. However, despite the valuable structural information they contain, the traditional engineering features known as anatomical features have been largely overlooked in this context. To address this issue, we propose an attention-based network design that integrates anatomical and deep convolutional features, leveraging an anatomical feature attention (AFA) module to effectively capture salient anatomical features. In addition, we introduce a fully convolutional network, which simplifies the extraction of deep convolutional features and overcomes the high computational memory requirements associated with deep learning. Our approach outperforms several widely-used models on eight publicly available datasets (n = 2501), with a mean absolute error (MAE) of 2.20 years in predicting brain age. Comparisons with deep learning models lacking the AFA module demonstrate that our fusion model effectively improves overall performance. These findings provide a promising approach for combining anatomical and deep convolutional features from sMRI data to predict brain age, with potential applications in clinical diagnosis and treatment, particularly for populations with age-related cognitive decline or neurological disorders.
Collapse
Affiliation(s)
- Yu Zhang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China
| | - Rui Xie
- Department of Psychiatric, Tianshui Third People's Hospital, Tianshui, 741000, China
| | - Iman Beheshti
- Department of Human Anatomy and Cell Science, University of Manitoba, Canada
| | - Xia Liu
- School of Computer Science, Qinghai Normal University, Xining, Qinghai Province, China
| | - Guowei Zheng
- School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China
| | - Yin Wang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China
| | - Zhenwen Zhang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China
| | - Weihao Zheng
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China.
| | - Zhijun Yao
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China.
| | - Bin Hu
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China; School of Medical Technology, Beijing Institute of Technology, China; CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, China; Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors, Chinese Academy of Sciences, China.
| |
Collapse
|
32
|
Liu L, Lin L, Sun S, Wu S. Elucidating Multimodal Imaging Patterns in Accelerated Brain Aging: Heterogeneity through a Discriminant Analysis Approach Using the UK Biobank Dataset. Bioengineering (Basel) 2024; 11:124. [PMID: 38391610 PMCID: PMC10886122 DOI: 10.3390/bioengineering11020124] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 01/17/2024] [Accepted: 01/24/2024] [Indexed: 02/24/2024] Open
Abstract
Accelerated brain aging (ABA) intricately links with age-associated neurodegenerative and neuropsychiatric diseases, emphasizing the critical need for a nuanced exploration of heterogeneous ABA patterns. This investigation leveraged data from the UK Biobank (UKB) for a comprehensive analysis, utilizing structural magnetic resonance imaging (sMRI), diffusion magnetic resonance imaging (dMRI), and resting-state functional magnetic resonance imaging (rsfMRI) from 31,621 participants. Pre-processing employed tools from the FMRIB Software Library (FSL, version 5.0.10), FreeSurfer, DTIFIT, and MELODIC, seamlessly integrated into the UKB imaging processing pipeline. The Lasso algorithm was employed for brain-age prediction, utilizing derived phenotypes obtained from brain imaging data. Subpopulations of accelerated brain aging (ABA) and resilient brain aging (RBA) were delineated based on the error between actual age and predicted brain age. The ABA subgroup comprised 1949 subjects (experimental group), while the RBA subgroup comprised 3203 subjects (control group). Semi-supervised heterogeneity through discriminant analysis (HYDRA) refined and characterized the ABA subgroups based on distinctive neuroimaging features. HYDRA systematically stratified ABA subjects into three subtypes: SubGroup 2 exhibited extensive gray-matter atrophy, distinctive white-matter patterns, and unique connectivity features, displaying lower cognitive performance; SubGroup 3 demonstrated minimal atrophy, superior cognitive performance, and higher physical activity; and SubGroup 1 occupied an intermediate position. This investigation underscores pronounced structural and functional heterogeneity in ABA, revealing three subtypes and paving the way for personalized neuroprotective treatments for age-related neurological, neuropsychiatric, and neurodegenerative diseases.
Collapse
Affiliation(s)
- Lingyu Liu
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China
| | - Lan Lin
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China
- Intelligent Physiological Measurement and Clinical Translation, Beijing International Base for Scientific and Technological Cooperation, Beijing University of Technology, Beijing 100124, China
| | - Shen Sun
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China
- Intelligent Physiological Measurement and Clinical Translation, Beijing International Base for Scientific and Technological Cooperation, Beijing University of Technology, Beijing 100124, China
| | - Shuicai Wu
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China
- Intelligent Physiological Measurement and Clinical Translation, Beijing International Base for Scientific and Technological Cooperation, Beijing University of Technology, Beijing 100124, China
| |
Collapse
|
33
|
Gao C, Kim ME, Lee HH, Yang Q, Khairi NM, Kanakaraj P, Newlin NR, Archer DB, Jefferson AL, Taylor WD, Boyd BD, Beason-Held LL, Resnick SM, Huo Y, Van Schaik KD, Schilling KG, Moyer D, Išgum I, Landman BA. Predicting Age from White Matter Diffusivity with Residual Learning. ARXIV 2024:arXiv:2311.03500v2. [PMID: 37986731 PMCID: PMC10659451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 11/22/2023]
Abstract
Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI's advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction.
Collapse
Affiliation(s)
- Chenyu Gao
- Dept. of Electrical and Computer Engineering, Vanderbilt University, Nashville, USA
| | - Michael E. Kim
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Ho Hin Lee
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Qi Yang
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Nazirah Mohd Khairi
- Dept. of Electrical and Computer Engineering, Vanderbilt University, Nashville, USA
| | | | - Nancy R. Newlin
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Derek B. Archer
- Vanderbilt Memory and Alzheimer’s Center, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Neurology, Vanderbilt University Medical Center, Nashville, USA
| | - Angela L. Jefferson
- Vanderbilt Memory and Alzheimer’s Center, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Neurology, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Medicine, Vanderbilt University Medical Center, Nashville, USA
| | - Warren D. Taylor
- Dept. of Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, USA
| | - Brian D. Boyd
- Vanderbilt Center for Cognitive Medicine, Vanderbilt University Medical Center, Nashville, USA
| | - Lori L. Beason-Held
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, USA
| | - Susan M. Resnick
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, USA
| | | | - Yuankai Huo
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Katherine D. Van Schaik
- Dept. of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, USA
| | - Kurt G. Schilling
- Dept. of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, USA
| | - Daniel Moyer
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
| | - Ivana Išgum
- Dept. of Biomedical Engineering and Physics, Dept. of Radiology and Nuclear Medicine, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, Netherlands
| | - Bennett A. Landman
- Dept. of Electrical and Computer Engineering, Vanderbilt University, Nashville, USA
- Dept. of Computer Science, Vanderbilt University, Nashville, USA
- Dept. of Neurology, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, USA
- Dept. of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, USA
| |
Collapse
|
34
|
Bi S, Guan Y, Tian L. Prediction of individual brain age using movie and resting-state fMRI. Cereb Cortex 2024; 34:bhad407. [PMID: 37885127 DOI: 10.1093/cercor/bhad407] [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: 08/28/2023] [Revised: 10/07/2023] [Accepted: 10/09/2023] [Indexed: 10/28/2023] Open
Abstract
Brain age is a promising biomarker for predicting chronological age based on brain imaging data. Although movie and resting-state functional MRI techniques have attracted much research interest for the investigation of brain function, whether the 2 different imaging paradigms show similarities and differences in terms of their capabilities and properties for predicting brain age remains largely unexplored. Here, we used movie and resting-state functional MRI data from 528 participants aged from 18 to 87 years old in the Cambridge Centre for Ageing and Neuroscience data set for functional network construction and further used elastic net for age prediction model building. The connectivity properties of movie and resting-state functional MRI were evaluated based on the connections supporting predictive model building. We found comparable predictive abilities of movie and resting-state connectivity in estimating brain age of individuals, as evidenced by correlation coefficients of 0.868 and 0.862 between actual and predicted age, respectively. Despite some similarities, notable differences in connectivity properties were observed between the predictive models using movie and resting-state functional MRI data, primarily involving components of the default mode network. Our results highlight that both movie and resting-state functional MRI are effective and promising techniques for predicting brain age. Leveraging its data acquisition advantages, such as improved child and patient compliance resulting in reduced motion artifacts, movie functional MRI is emerging as an important paradigm for studying brain function in pediatric and clinical populations.
Collapse
Affiliation(s)
- Suyu Bi
- School of International Journalism and Communication, Beijing Foreign Studies University, Beijing 100081, China
| | - Yun Guan
- School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
- Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China
| | - Lixia Tian
- School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
| |
Collapse
|
35
|
Tseng WYI, Hsu YC, Huang LK, Hong CT, Lu YH, Chen JH, Fu CK, Chan L. Brain Age Is Associated with Cognitive Outcomes of Cholinesterase Inhibitor Treatment in Patients with Mild Cognitive Impairment. J Alzheimers Dis 2024; 98:1095-1106. [PMID: 38517785 DOI: 10.3233/jad-231109] [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] [Indexed: 03/24/2024]
Abstract
Background The effect of cholinesterase inhibitor (ChEI) on mild cognitive impairment (MCI) is controversial. Brain age has been shown to predict Alzheimer's disease conversion from MCI. Objective The study aimed to show that brain age is related to cognitive outcomes of ChEI treatment in MCI. Methods Brain MRI, the Clinical Dementia Rating (CDR) and Mini-Mental State Exam (MMSE) scores were retrospectively retrieved from a ChEI treatment database. Patients who presented baseline CDR of 0.5 and received ChEI treatment for at least 2 years were selected. Patients with stationary or improved cognition as verified by the CDR and MMSE were categorized to the ChEI-responsive group, and those with worsened cognition were assigned to the ChEI-unresponsive group. A gray matter brain age model was built with a machine learning algorithm by training T1-weighted MRI data of 362 healthy participants. The model was applied to each patient to compute predicted age difference (PAD), i.e. the difference between brain age and chronological age. The PADs were compared between the two groups. Results 58 patients were found to fit the ChEI-responsive criteria in the patient data, and 58 matched patients that fit the ChEI-unresponsive criteria were compared. ChEI-unresponsive patients showed significantly larger PAD than ChEI-responsive patients (8.44±8.78 years versus 3.87±9.02 years, p = 0.0067). Conclusions Gray matter brain age is associated with cognitive outcomes after 2 years of ChEI treatment in patients with the CDR of 0.5. It might facilitate the clinical trials of novel therapeutics for MCI.
Collapse
Affiliation(s)
| | | | - Li-Kai Huang
- Department of Neurology, Taipei Medical University-Shuang Ho Hospital, Ministry of Health and Welfare, Taipei Medical University, New Taipei City, Taiwan (R.O.C.)
- Taipei Neuroscience Institute, Taipei Medical University, Taipei, Taiwan (R.O.C.)
| | - Chien-Tai Hong
- Department of Neurology, Taipei Medical University-Shuang Ho Hospital, Ministry of Health and Welfare, Taipei Medical University, New Taipei City, Taiwan (R.O.C.)
- Taipei Neuroscience Institute, Taipei Medical University, Taipei, Taiwan (R.O.C.)
- Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan (R.O.C.)
| | - Yueh-Hsun Lu
- Taipei Neuroscience Institute, Taipei Medical University, Taipei, Taiwan (R.O.C.)
- Department of Radiology, Shuang-Ho Hospital, Taipei Medical University, New Taipei City, Taiwan (R.O.C.)
- Department of Radiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan (R.O.C.)
| | - Jia-Hung Chen
- Department of Neurology, Taipei Medical University-Shuang Ho Hospital, Ministry of Health and Welfare, Taipei Medical University, New Taipei City, Taiwan (R.O.C.)
- Taipei Neuroscience Institute, Taipei Medical University, Taipei, Taiwan (R.O.C.)
| | | | - Lung Chan
- Department of Neurology, Taipei Medical University-Shuang Ho Hospital, Ministry of Health and Welfare, Taipei Medical University, New Taipei City, Taiwan (R.O.C.)
- Taipei Neuroscience Institute, Taipei Medical University, Taipei, Taiwan (R.O.C.)
- Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan (R.O.C.)
| |
Collapse
|
36
|
Shah J, Siddiquee MMR, Su Y, Wu T, Li B. Ordinal Classification with Distance Regularization for Robust Brain Age Prediction. IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION. IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION 2024; 2024:7867-7876. [PMID: 38606366 PMCID: PMC11008505 DOI: 10.1109/wacv57701.2024.00770] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/13/2024]
Abstract
Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at https://github.com/jaygshah/Robust-Brain-Age-Prediction.
Collapse
Affiliation(s)
- Jay Shah
- Arizona State University
- ASU-Mayo Center for Innovative Imaging
| | | | - Yi Su
- ASU-Mayo Center for Innovative Imaging
- Banner Alzheimer's Institute
| | - Teresa Wu
- Arizona State University
- ASU-Mayo Center for Innovative Imaging
| | - Baoxin Li
- Arizona State University
- ASU-Mayo Center for Innovative Imaging
| |
Collapse
|
37
|
Kozhemiako N, Buckley AW, Chervin RD, Redline S, Purcell SM. Mapping neurodevelopment with sleep macro- and micro-architecture across multiple pediatric populations. Neuroimage Clin 2023; 41:103552. [PMID: 38150746 PMCID: PMC10788305 DOI: 10.1016/j.nicl.2023.103552] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 10/30/2023] [Accepted: 12/12/2023] [Indexed: 12/29/2023]
Abstract
Profiles of sleep duration and timing and corresponding electroencephalographic activity reflect brain changes that support cognitive and behavioral maturation and may provide practical markers for tracking typical and atypical neurodevelopment. To build and evaluate a sleep-based, quantitative metric of brain maturation, we used whole-night polysomnography data, initially from two large National Sleep Research Resource samples, spanning childhood and adolescence (total N = 4,013, aged 2.5 to 17.5 years): the Childhood Adenotonsillectomy Trial (CHAT), a research study of children with snoring without neurodevelopmental delay, and Nationwide Children's Hospital (NCH) Sleep Databank, a pediatric sleep clinic cohort. Among children without neurodevelopmental disorders (NDD), sleep metrics derived from the electroencephalogram (EEG) displayed robust age-related changes consistently across datasets. During non-rapid eye movement (NREM) sleep, spindles and slow oscillations further exhibited characteristic developmental patterns, with respect to their rate of occurrence, temporal coupling and morphology. Based on these metrics in NCH, we constructed a model to predict an individual's chronological age. The model performed with high accuracy (r = 0.93 in the held-out NCH sample and r = 0.85 in a second independent replication sample - the Pediatric Adenotonsillectomy Trial for Snoring (PATS)). EEG-based age predictions reflected clinically meaningful neurodevelopmental differences; for example, children with NDD showed greater variability in predicted age, and children with Down syndrome or intellectual disability had significantly younger brain age predictions (respectively, 2.1 and 0.8 years less than their chronological age) compared to age-matched non-NDD children. Overall, our results indicate that sleep architectureoffers a sensitive window for characterizing brain maturation, suggesting the potential for scalable, objective sleep-based biomarkers to measure neurodevelopment.
Collapse
Affiliation(s)
- N Kozhemiako
- Brigham and Women's Hospital & Harvard Medical School, Boston, MA, USA
| | - A W Buckley
- Sleep & Neurodevelopment Core, National Institute of Mental Health, NIH, Bethesda, MD, USA
| | - R D Chervin
- Sleep Disorders Center and Department of Neurology, University of Michigan, Ann Arbor, MI, USA
| | - S Redline
- Brigham and Women's Hospital & Harvard Medical School, Boston, MA, USA; Beth Israel Deaconess Medical Center, Boston, MA, USA
| | - S M Purcell
- Brigham and Women's Hospital & Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
38
|
Millar PR, Gordon BA, Wisch JK, Schultz SA, Benzinger TL, Cruchaga C, Hassenstab JJ, Ibanez L, Karch C, Llibre-Guerra JJ, Morris JC, Perrin RJ, Supnet-Bell C, Xiong C, Allegri RF, Berman SB, Chhatwal JP, Chrem Mendez PA, Day GS, Hofmann A, Ikeuchi T, Jucker M, Lee JH, Levin J, Lopera F, Niimi Y, Sánchez-González VJ, Schofield PR, Sosa-Ortiz AL, Vöglein J, Bateman RJ, Ances BM, McDade EM. Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease. Mol Neurodegener 2023; 18:98. [PMID: 38111006 PMCID: PMC10729487 DOI: 10.1186/s13024-023-00688-3] [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: 07/03/2023] [Accepted: 11/28/2023] [Indexed: 12/20/2023] Open
Abstract
BACKGROUND "Brain-predicted age" estimates biological age from complex, nonlinear features in neuroimaging scans. The brain age gap (BAG) between predicted and chronological age is elevated in sporadic Alzheimer disease (AD), but is underexplored in autosomal dominant AD (ADAD), in which AD progression is highly predictable with minimal confounding age-related co-pathology. METHODS We modeled BAG in 257 deeply-phenotyped ADAD mutation-carriers and 179 non-carriers from the Dominantly Inherited Alzheimer Network using minimally-processed structural MRI scans. We then tested whether BAG differed as a function of mutation and cognitive status, or estimated years until symptom onset, and whether it was associated with established markers of amyloid (PiB PET, CSF amyloid-β-42/40), phosphorylated tau (CSF and plasma pTau-181), neurodegeneration (CSF and plasma neurofilament-light-chain [NfL]), and cognition (global neuropsychological composite and CDR-sum of boxes). We compared BAG to other MRI measures, and examined heterogeneity in BAG as a function of ADAD mutation variants, APOE ε4 carrier status, sex, and education. RESULTS Advanced brain aging was observed in mutation-carriers approximately 7 years before expected symptom onset, in line with other established structural indicators of atrophy. BAG was moderately associated with amyloid PET and strongly associated with pTau-181, NfL, and cognition in mutation-carriers. Mutation variants, sex, and years of education contributed to variability in BAG. CONCLUSIONS We extend prior work using BAG from sporadic AD to ADAD, noting consistent results. BAG associates well with markers of pTau, neurodegeneration, and cognition, but to a lesser extent, amyloid, in ADAD. BAG may capture similar signal to established MRI measures. However, BAG offers unique benefits in simplicity of data processing and interpretation. Thus, results in this unique ADAD cohort with few age-related confounds suggest that brain aging attributable to AD neuropathology can be accurately quantified from minimally-processed MRI.
Collapse
Affiliation(s)
- Peter R Millar
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA.
| | - Brian A Gordon
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, MO, USA
| | - Julie K Wisch
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
| | - Stephanie A Schultz
- Department of Neurology, Harvard Medical School, Boston, MA, USA
- Department of Neurology, Massachusetts General Hospital, Boston, MA, USA
| | - Tammie Ls Benzinger
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, MO, USA
| | - Carlos Cruchaga
- Department of Psychiatry, Washington University in St. Louis, St. Louis, MO, USA
| | - Jason J Hassenstab
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
| | - Laura Ibanez
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
- Department of Psychiatry, Washington University in St. Louis, St. Louis, MO, USA
- NeuroGenomics & Informatics Center, Washington University in St. Louis, St. Louis, MO, USA
| | - Celeste Karch
- Department of Psychiatry, Washington University in St. Louis, St. Louis, MO, USA
| | | | - John C Morris
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
| | - Richard J Perrin
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
- Department of Pathology & Immunology, Washington University in St. Louis, St. Louis, MO, USA
| | | | - Chengjie Xiong
- Department of Biostatistics, Washington University in St. Louis, St. Louis, MO, USA
| | | | - Sarah B Berman
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, USA
| | - Jasmeer P Chhatwal
- Department of Neurology, Harvard Medical School, Boston, MA, USA
- Department of Neurology, Massachusetts General Hospital, Boston, MA, USA
| | | | - Gregory S Day
- Department of Neurology, Mayo Clinic, Jacksonville, FL, USA
| | - Anna Hofmann
- German Center for Neurodegenerative Diseases (DZNE), 72076, Tübingen, Germany
- Department of Cellular Neurology, Hertie Institute for Clinical Brain Research, University of Tübingen, 72076, Tübingen, Germany
| | - Takeshi Ikeuchi
- Department of Molecular Genetics, Brain Research Institute, Niigata University, Niigata, Japan
| | - Mathias Jucker
- German Center for Neurodegenerative Diseases (DZNE), 72076, Tübingen, Germany
- Department of Cellular Neurology, Hertie Institute for Clinical Brain Research, University of Tübingen, 72076, Tübingen, Germany
| | - Jae-Hong Lee
- Department of Neurology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
| | - Johannes Levin
- Department of Neurology, Ludwig-Maximilians-Universität München, Munich, Germany
- German Center for Neurodegenerative Diseases, Munich, Germany
- Munich Cluster for Systems Neurology (SyNergy), Munich, Germany
| | | | - Yoshiki Niimi
- Unit for Early and Exploratory Clinical Development, The University of Tokyo Hospital, Bunkyo-Ku, Tokyo, Japan
| | - Victor J Sánchez-González
- Departamento de Clínicas, CUALTOS, Universidad de Guadalajara, Tepatitlán de Morelos, Jalisco, México
| | - Peter R Schofield
- Neuroscience Research Australia, Sydney, NSW, Australia
- School of Biomedical Sciences, University of New South Wales, Sydney, NSW, Australia
| | - Ana Luisa Sosa-Ortiz
- Instituto Nacional de Neurologia y Neurocirugía MVS, CDMX, Ciudad de México, Mexico
| | - Jonathan Vöglein
- Department of Neurology, Ludwig-Maximilians-Universität München, Munich, Germany
- German Center for Neurodegenerative Diseases, Munich, Germany
| | - Randall J Bateman
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
| | - Beau M Ances
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, MO, USA
| | - Eric M McDade
- Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA
| |
Collapse
|
39
|
Mayer AR, Meier TB, Ling JM, Dodd AB, Brett BL, Robertson-Benta CR, Huber DL, Van der Horn HJ, Broglio SP, McCrea MA, McAllister T. Increased brain age and relationships with blood-based biomarkers following concussion in younger populations. J Neurol 2023; 270:5835-5848. [PMID: 37594499 PMCID: PMC10632216 DOI: 10.1007/s00415-023-11931-8] [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: 06/09/2023] [Revised: 07/19/2023] [Accepted: 08/03/2023] [Indexed: 08/19/2023]
Abstract
OBJECTIVE Brain age is increasingly being applied to the spectrum of brain injury to define neuropathological changes in conjunction with blood-based biomarkers. However, data from the acute/sub-acute stages of concussion are lacking, especially among younger cohorts. METHODS Predicted brain age differences were independently calculated in large, prospectively recruited cohorts of pediatric concussion and matched healthy controls (total N = 446), as well as collegiate athletes with sport-related concussion and matched non-contact sport controls (total N = 184). Effects of repetitive head injury (i.e., exposure) were examined in a separate cohort of contact sport athletes (N = 82), as well as by quantifying concussion history through semi-structured interviews and years of contact sport participation. RESULTS Findings of increased brain age during acute and sub-acute concussion were independently replicated across both cohorts, with stronger evidence of recovery for pediatric (4 months) relative to concussed athletes (6 months). Mixed evidence existed for effects of repetitive head injury, as brain age was increased in contact sport athletes, but was not associated with concussion history or years of contact sport exposure. There was no difference in brain age between concussed and contact sport athletes. Total tau decreased immediately (~ 1.5 days) post-concussion relative to the non-contact group, whereas pro-inflammatory markers were increased in both concussed and contact sport athletes. Anti-inflammatory markers were inversely related to brain age, whereas markers of axonal injury (neurofilament light) exhibited a trend positive association. CONCLUSION Current and previous findings collectively suggest that the chronicity of brain age differences may be mediated by age at injury (adults > children), with preliminary findings suggesting that exposure to contact sports may also increase brain age.
Collapse
Affiliation(s)
- Andrew R Mayer
- The Mind Research Network/Lovelace Biomedical and Environmental Research Institute, 1101 Yale Blvd. NE, Albuquerque, NM, 87106, USA.
- Neurology and Psychiatry Departments, University of New Mexico School of Medicine, Albuquerque, NM, USA.
- Department of Psychology, University of New Mexico, Albuquerque, NM, USA.
| | - Timothy B Meier
- Department of Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, USA
- Department of Biomedical Engineering, Medical College of Wisconsin, Milwaukee, WI, USA
- Department of Cell Biology, Neurobiology and Anatomy, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Josef M Ling
- The Mind Research Network/Lovelace Biomedical and Environmental Research Institute, 1101 Yale Blvd. NE, Albuquerque, NM, 87106, USA
| | - Andrew B Dodd
- The Mind Research Network/Lovelace Biomedical and Environmental Research Institute, 1101 Yale Blvd. NE, Albuquerque, NM, 87106, USA
| | - Benjamin L Brett
- Department of Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, USA
- Department of Neurology, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Cidney R Robertson-Benta
- The Mind Research Network/Lovelace Biomedical and Environmental Research Institute, 1101 Yale Blvd. NE, Albuquerque, NM, 87106, USA
| | - Daniel L Huber
- Department of Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Harm J Van der Horn
- The Mind Research Network/Lovelace Biomedical and Environmental Research Institute, 1101 Yale Blvd. NE, Albuquerque, NM, 87106, USA
| | - Steven P Broglio
- Michigan Concussion Center, University of Michigan, Ann Arbor, MI, USA
| | - Michael A McCrea
- Department of Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, USA
- Department of Neurology, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Thomas McAllister
- Department of Psychiatry, Indiana University School of Medicine, Bloomington, IN, USA
| |
Collapse
|
40
|
Yip PK, Liu ZH, Hasan S, Pepys MB, Uff CEG. Serum amyloid P component accumulates and persists in neurones following traumatic brain injury. Open Biol 2023; 13:230253. [PMID: 38052249 DOI: 10.1098/rsob.230253] [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: 07/31/2023] [Accepted: 10/19/2023] [Indexed: 12/07/2023] Open
Abstract
The mechanisms underlying neurodegenerative sequelae of traumatic brain injury (TBI) are poorly understood. The normal plasma protein, serum amyloid P component (SAP), which is normally rigorously excluded from the brain, is directly neurocytotoxic for cerebral neurones and also binds to Aβ amyloid fibrils and neurofibrillary tangles, promoting formation and persistence of Aβ fibrils. Increased brain exposure to SAP is common to many risk factors for dementia, including TBI, and dementia at death in the elderly is significantly associated with neocortical SAP content. Here, in 18 of 30 severe TBI cases, we report immunohistochemical staining for SAP in contused brain tissue with blood-brain barrier disruption. The SAP was localized to neurofilaments in a subset of neurones and their processes, particularly damaged axons and cell bodies, and was present regardless of the time after injury. No SAP was detected on astrocytes, microglia, cerebral capillaries or serotoninergic neurones and was absent from undamaged brain. C-reactive protein, the control plasma protein most closely similar to SAP, was only detected within capillary lumina. The appearance of neurocytotoxic SAP in the brain after TBI, and its persistent, selective deposition in cerebral neurones, are consistent with a potential contribution to subsequent neurodegeneration.
Collapse
Affiliation(s)
- Ping K Yip
- Centre for Neuroscience, Surgery & Trauma, Blizard Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London E1 2AT, UK
| | - Zhou-Hao Liu
- Department of Neurosurgery, Chang Gung Memorial Hospital at Linkou, Chang Gung University, Taoyuan 33302, Taiwan
| | - Shumaila Hasan
- Department of Neurosurgery, Royal London Hospital, Whitechapel, London E1 1FR, UK
| | - Mark B Pepys
- Wolfson Drug Discovery Unit, University College London, London NW3 2PG, UK
| | - Christopher E G Uff
- Centre for Neuroscience, Surgery & Trauma, Blizard Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London E1 2AT, UK
- Department of Neurosurgery, Royal London Hospital, Whitechapel, London E1 1FR, UK
| |
Collapse
|
41
|
He S, Guan Y, Cheng CH, Moore TL, Luebke JI, Killiany RJ, Rosene DL, Koo BB, Ou Y. Human-to-monkey transfer learning identifies the frontal white matter as a key determinant for predicting monkey brain age. Front Aging Neurosci 2023; 15:1249415. [PMID: 38020785 PMCID: PMC10646581 DOI: 10.3389/fnagi.2023.1249415] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Accepted: 10/10/2023] [Indexed: 12/01/2023] Open
Abstract
The application of artificial intelligence (AI) to summarize a whole-brain magnetic resonance image (MRI) into an effective "brain age" metric can provide a holistic, individualized, and objective view of how the brain interacts with various factors (e.g., genetics and lifestyle) during aging. Brain age predictions using deep learning (DL) have been widely used to quantify the developmental status of human brains, but their wider application to serve biomedical purposes is under criticism for requiring large samples and complicated interpretability. Animal models, i.e., rhesus monkeys, have offered a unique lens to understand the human brain - being a species in which aging patterns are similar, for which environmental and lifestyle factors are more readily controlled. However, applying DL methods in animal models suffers from data insufficiency as the availability of animal brain MRIs is limited compared to many thousands of human MRIs. We showed that transfer learning can mitigate the sample size problem, where transferring the pre-trained AI models from 8,859 human brain MRIs improved monkey brain age estimation accuracy and stability. The highest accuracy and stability occurred when transferring the 3D ResNet [mean absolute error (MAE) = 1.83 years] and the 2D global-local transformer (MAE = 1.92 years) models. Our models identified the frontal white matter as the most important feature for monkey brain age predictions, which is consistent with previous histological findings. This first DL-based, anatomically interpretable, and adaptive brain age estimator could broaden the application of AI techniques to various animal or disease samples and widen opportunities for research in non-human primate brains across the lifespan.
Collapse
Affiliation(s)
- Sheng He
- Harvard Medical School, Boston Children's Hospital, Boston, MA, United States
| | - Yi Guan
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Chia Hsin Cheng
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Tara L. Moore
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Jennifer I. Luebke
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Ronald J. Killiany
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Douglas L. Rosene
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Bang-Bon Koo
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| | - Yangming Ou
- Department of Anatomy & Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United States
| |
Collapse
|
42
|
Garcia Condado J, Cortes JM. NeuropsychBrainAge: A biomarker for conversion from mild cognitive impairment to Alzheimer's disease. ALZHEIMER'S & DEMENTIA (AMSTERDAM, NETHERLANDS) 2023; 15:e12493. [PMID: 37908437 PMCID: PMC10614125 DOI: 10.1002/dad2.12493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Revised: 08/21/2023] [Accepted: 09/26/2023] [Indexed: 11/02/2023]
Abstract
INTRODUCTION BrainAge models based on neuroimaging data have diagnostic classification power but have replicability issues due to site and patient variability. BrainAge models trained on neuropsychological tests could help distinguish stable mild cognitive impairment (sMCI) from progressive MCI (pMCI) to Alzheimer's disease (AD). METHODS A linear regressor BrainAge model was trained on healthy controls using neuropsychological tests and neuroimaging features separately. The BrainAge delta, predicted age minus chronological age, was used to distinguish between sMCI and pMCI. RESULTS The cross-validated area under the receiver-operating characteristic (ROC) curve for sMCI versus pMCI was 0.91 for neuropsychological features in contrast to 0.68 for neuroimaging features. The BrainAge delta was correlated with the time to conversion, the time taken for a pMCI subject to convert to AD. DISCUSSION The BrainAge delta from neuropsychological tests is a good biomarker to distinguish between sMCI and pMCI. Other neurological and psychiatric disorders could be studied using this strategy. Highlights BrainAge models based on neuropsychological tests outperform models based on neuroimaging features when distinguishing between stable mild cognitive impairment (sMCI) from progressive MCI (pMCI) to Alzheimer's disease (AD).The combination of neuropsychological tests with neuroimaging features does not lead to an improvement in sMCI versus pMCI classification compared to using neuropsychological tests on their own.BrainAge delta of both neuroimaging and neuropsychological models was correlated with the time to conversion, the time taken for a pMCI subject to convert to AD.
Collapse
Affiliation(s)
- Jorge Garcia Condado
- Computational Neuroimaging LaboratoryBiobizkaia Health Research InstituteBarakaldo, BizkaiaSpain
- Biomedical Research Doctorate ProgramUniversity of the Basque CountryLeioa, BizkaiaSpain
| | - Jesus M. Cortes
- Computational Neuroimaging LaboratoryBiobizkaia Health Research InstituteBarakaldo, BizkaiaSpain
- Department of Cell Biology and HistologyUniversity of the Basque CountryLeioa, BizkaiaSpain
- IKERBASQUE Basque Foundation for ScienceBilbaoSpain
| | | |
Collapse
|
43
|
Khan AR, Zehra S, Baranwal AK, Kumar D, Ali R, Javed S, Bhaisora K. Whole-Blood Metabolomics of a Rat Model of Repetitive Concussion. J Mol Neurosci 2023; 73:843-852. [PMID: 37801210 DOI: 10.1007/s12031-023-02162-7] [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: 07/22/2023] [Accepted: 09/27/2023] [Indexed: 10/07/2023]
Abstract
Mild traumatic brain injury (mTBI) and repetitive mTBI (RmTBI) are silent epidemics, and so far, there is no objective diagnosis. The severity of the injury is solely based on the Glasgow Coma Score (GCS) scale. Most patients suffer from one or more behavioral abnormalities, such as headache, amnesia, cognitive decline, disturbed sleep pattern, anxiety, depression, and vision abnormalities. Additionally, most neuroimaging modalities are insensitive to capture structural and functional alterations in the brain, leading to inefficient patient management. Metabolomics is one of the established omics technologies to identify metabolic alterations, mostly in biofluids. NMR-based metabolomics provides quantitative metabolic information with non-destructive and minimal sample preparation. We employed whole-blood NMR analysis to identify metabolic markers using a high-field NMR spectrometer (800 MHz). Our approach involves chemical-free sample pretreatment and minimal sample preparation to obtain a robust whole-blood metabolic profile from a rat model of concussion. A single head injury was given to the mTBI group, and three head injuries to the RmTBI group. We found significant alterations in blood metabolites in both mTBI and RmTBI groups compared with the control, such as alanine, branched amino acid (BAA), adenosine diphosphate/adenosine try phosphate (ADP/ATP), creatine, glucose, pyruvate, and glycerphosphocholine (GPC). Choline was significantly altered only in the mTBI group and formate in the RmTBI group compared with the control. These metabolites corroborate previous findings in clinical and preclinical cohorts. Comprehensive whole-blood metabolomics can provide a robust metabolic marker for more accurate diagnosis and treatment intervention for a disease population.
Collapse
Affiliation(s)
- Ahmad Raza Khan
- Department of Advanced Spectroscopy and Imaging, Centre of Biomedical Research (CBMR), SGPGI Campus, Raebareli Road, Lucknow, India.
| | - Samiya Zehra
- Department of Advanced Spectroscopy and Imaging, Centre of Biomedical Research (CBMR), SGPGI Campus, Raebareli Road, Lucknow, India
| | | | - Dinesh Kumar
- Department of Advanced Spectroscopy and Imaging, Centre of Biomedical Research (CBMR), SGPGI Campus, Raebareli Road, Lucknow, India
| | - Raisuddin Ali
- Department of Pharmaceutics, College of Pharmacy, King Saud University, P.O. Box 2457, Riyadh 11451, Saudi Arabia
| | - Saleem Javed
- Department of Biochemistry, Aligarh Muslim University (AMU), Aligarh, India
| | - Kamlesh Bhaisora
- Department of Neurosurgery, SGPGIMS, Raebareli Road, Lucknow, India
| |
Collapse
|
44
|
Hansson MJ, Elmér E. Cyclosporine as Therapy for Traumatic Brain Injury. Neurotherapeutics 2023; 20:1482-1495. [PMID: 37561274 PMCID: PMC10684836 DOI: 10.1007/s13311-023-01414-z] [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: 07/19/2023] [Indexed: 08/11/2023] Open
Abstract
Drug development in traumatic brain injury (TBI) has been impeded by the complexity and heterogeneity of the disease pathology, as well as limited understanding of the secondary injury cascade that follows the initial trauma. As a result, patients with TBI have an unmet need for effective pharmacological therapies. One promising drug candidate is cyclosporine, a polypeptide traditionally used to achieve immunosuppression in transplant recipients. Cyclosporine inhibits mitochondrial permeability transition, thereby reducing secondary brain injury, and has shown neuroprotective effects in multiple preclinical models of TBI. Moreover, the cyclosporine formulation NeuroSTAT® displayed positive effects on injury biomarker levels in patients with severe TBI enrolled in the Phase Ib/IIa Copenhagen Head Injury Ciclosporin trial (NCT01825044). Future research on neuroprotective compounds such as cyclosporine should take advantage of recent advances in fluid-based biomarkers and neuroimaging to select patients with similar disease pathologies for clinical trials. This would increase statistical power and allow for more accurate assessment of long-term outcomes.
Collapse
Affiliation(s)
- Magnus J Hansson
- Abliva AB, Lund, Sweden.
- Department of Clinical Sciences, Mitochondrial Medicine, Lund University, Lund, Sweden.
| | - Eskil Elmér
- Abliva AB, Lund, Sweden
- Department of Clinical Sciences, Mitochondrial Medicine, Lund University, Lund, Sweden
| |
Collapse
|
45
|
Somach RT, Jean ID, Farrugia AM, Cohen AS. Mild Traumatic Brain Injury Affects Orexin/Hypocretin Physiology Differently in Male and Female Mice. J Neurotrauma 2023; 40:2146-2163. [PMID: 37476962 PMCID: PMC10701510 DOI: 10.1089/neu.2023.0125] [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: 07/22/2023] Open
Abstract
Traumatic brain injury (TBI) is known to affect the physiology of neural circuits in several brain regions, which can contribute to behavioral changes after injury. Disordered sleep is a behavior that is often seen after TBI, but there is little research into how injury affects the circuitry that contributes to disrupted sleep regulation. Orexin/hypocretin neurons (hereafter referred to as orexin neurons) located in the lateral hypothalamus normally stabilize wakefulness in healthy animals and have been suggested as a source of dysregulated sleep behavior. Despite this, few studies have examined how TBI affects orexin neuron circuitry. Further, almost no animal studies of orexin neurons after TBI have included female animals. Here, we address these gaps by studying changes to orexin physiology using ex vivo acute brain slices and whole-cell patch clamp recording. We hypothesized that orexin neurons would have reduced afferent excitatory activity after injury. Ultimately, this hypothesis was supported but there were additional physiological changes that occurred that we did not originally hypothesize. We studied physiological properties in orexin neurons approximately 1 week after mild traumatic brain injury (mTBI) in 6-8-week-old male and female mice. mTBI was performed with a lateral fluid percussion injury between 1.4 and 1.6 atmospheres. Mild TBI increased the size of action potential afterhyperpolarization in orexin neurons from female mice, but not male mice and reduced the action potential threshold in male mice, but not in female mice. Mild TBI reduced afferent excitatory activity and increased afferent inhibitory activity onto orexin neurons. Alterations in afferent excitatory activity occurred in different parameters in male and female animals. The increased afferent inhibitory activity after injury is more pronounced in recordings from female animals. Our results indicate that mTBI changes the physiology of orexin neuron circuitry and that these changes are not the same in male and female animals.
Collapse
Affiliation(s)
- Rebecca T. Somach
- Department of Anesthesiology and Critical Care Medicine, the Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
- Department of Anesthesiology and Critical Care Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
- Neuroscience Graduate Group, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Ian D. Jean
- Department of Anesthesiology and Critical Care Medicine, the Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
| | - Anthony M. Farrugia
- Department of Anesthesiology and Critical Care Medicine, the Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
- Department of Anesthesiology and Critical Care Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Akiva S. Cohen
- Department of Anesthesiology and Critical Care Medicine, the Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
- Department of Anesthesiology and Critical Care Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
- Neuroscience Graduate Group, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| |
Collapse
|
46
|
Griffiths-King D, Wood AG, Novak J. Predicting 'Brainage' in late childhood to adolescence (6-17yrs) using structural MRI, morphometric similarity, and machine learning. Sci Rep 2023; 13:15591. [PMID: 37730747 PMCID: PMC10511546 DOI: 10.1038/s41598-023-42414-5] [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: 02/13/2023] [Accepted: 09/10/2023] [Indexed: 09/22/2023] Open
Abstract
Brain development is regularly studied using structural MRI. Recently, studies have used a combination of statistical learning and large-scale imaging databases of healthy children to predict an individual's age from structural MRI. This data-driven, predicted 'Brainage' typically differs from the subjects chronological age, with this difference a potential measure of individual difference. Few studies have leveraged higher-order or connectomic representations of structural MRI data for this Brainage approach. We leveraged morphometric similarity as a network-level approach to structural MRI to generate predictive models of age. We benchmarked these novel Brainage approaches using morphometric similarity against more typical, single feature (i.e., cortical thickness) approaches. We showed that these novel methods did not outperform cortical thickness or cortical volume measures. All models were significantly biased by age, but robust to motion confounds. The main results show that, whilst morphometric similarity mapping may be a novel way to leverage additional information from a T1-weighted structural MRI beyond individual features, in the context of a Brainage framework, morphometric similarity does not provide more accurate predictions of age. Morphometric similarity as a network-level approach to structural MRI may be poorly positioned to study individual differences in brain development in healthy participants in this way.
Collapse
Affiliation(s)
- Daniel Griffiths-King
- Aston Institute of Health and Neurodevelopment, College of Health and Life Sciences, Aston University, Birmingham, B4 7ET, UK
| | - Amanda G Wood
- Aston Institute of Health and Neurodevelopment, College of Health and Life Sciences, Aston University, Birmingham, B4 7ET, UK
- School of Psychology, Faculty of Health, Melbourne Burwood Campus, Deakin University, Geelong, VIC, Australia
- Murdoch Children's Research Institute, Melbourne, VIC, Australia
| | - Jan Novak
- Aston Institute of Health and Neurodevelopment, College of Health and Life Sciences, Aston University, Birmingham, B4 7ET, UK.
| |
Collapse
|
47
|
Buchwald H, McGlennon T, Roberts A, Ahnfeldt E, Buchwald J, Pories W. Who Would Have Thought It? : Intestinal Surgery May Prove To Be the Most Effective Therapy For Traumatic Brain Injury (TBI): a Hypothesis and a Challenge. Obes Surg 2023; 33:2629-2631. [PMID: 37458863 DOI: 10.1007/s11695-023-06613-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Revised: 04/17/2023] [Accepted: 04/17/2023] [Indexed: 08/18/2023]
Affiliation(s)
- Henry Buchwald
- Emeritus Professor of Surgery and Biomedical Engineering, Owen H. & Sarah Davidson Wangensteen Chair in Experimental Surgery, University of Minnesota, Minneapolis, MN, USA.
| | | | | | - Eric Ahnfeldt
- Uniformed Services University of the Health Sciences, Bethesda, MD, USA
| | - Jane Buchwald
- Medwrite Medical Communications, Maiden Rock, WI, USA
| | | |
Collapse
|
48
|
Verovnik B, Hajduk S, Hulle MV. Predicting phenotypes of elderly from resting state fMRI. RESEARCH SQUARE 2023:rs.3.rs-3201603. [PMID: 37609310 PMCID: PMC10441519 DOI: 10.21203/rs.3.rs-3201603/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/24/2023]
Abstract
Machine learning techniques are increasingly embraced in neuroimaging studies of healthy and diseased human brains. They have been used successfully in predicting phenotypes, or even clinical outcomes, and in turning functional connectome metrics into phenotype biomarkers of both healthy individuals and patients. In this study, we used functional connectivity characteristics based on resting state functional magnetic resonance imaging data to accurately classify healthy elderly in terms of their phenotype status. Additionally, as the functional connections that contribute to the classification can be identified, we can draw inferences about the network that is predictive of the investigated phenotypes. Our proposed pipeline for phenotype classification can be expanded to other phenotypes (cognitive, psychological, clinical) and possibly be used to shed light on the modifiable risk and protective factors in normative and pathological brain aging.
Collapse
|
49
|
Shida AF, Massett RJ, Imms P, Vegesna RV, Amgalan A, Irimia A. Significant Acceleration of Regional Brain Aging and Atrophy After Mild Traumatic Brain Injury. J Gerontol A Biol Sci Med Sci 2023; 78:1328-1338. [PMID: 36879433 PMCID: PMC10395568 DOI: 10.1093/gerona/glad079] [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: 08/01/2022] [Indexed: 03/08/2023] Open
Abstract
Brain regions' rates of age-related volumetric change after traumatic brain injury (TBI) are unknown. Here, we quantify these rates cross-sectionally in 113 persons with recent mild TBI (mTBI), whom we compare against 3 418 healthy controls (HCs). Regional gray matter (GM) volumes were extracted from magnetic resonance images. Linear regression yielded regional brain ages and the annualized average rates of regional GM volume loss. These results were compared across groups after accounting for sex and intracranial volume. In HCs, the steepest rates of volume loss were recorded in the nucleus accumbens, amygdala, and lateral orbital sulcus. In mTBI, approximately 80% of GM structures had significantly steeper rates of annual volume loss than in HCs. The largest group differences involved the short gyri of the insula and both the long gyrus and central sulcus of the insula. No significant sex differences were found in the mTBI group, regional brain ages being the oldest in prefrontal and temporal structures. Thus, mTBI involves significantly steeper regional GM loss rates than in HCs, reflecting older-than-expected regional brain ages.
Collapse
Affiliation(s)
- Alexander F Shida
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA
| | - Roy J Massett
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA
| | - Phoebe Imms
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA
| | - Ramanand V Vegesna
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA
| | - Anar Amgalan
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA
| | - Andrei Irimia
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA
- Corwin D. Denney Research Center, Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA
- Department of Quantitative & Computational Biology, Dana and David Dornsife College of Arts & Sciences, University of Southern California, Los Angeles, California, USA
| |
Collapse
|
50
|
Russell ER, Lyall DM, Stewart W. HEalth And Dementia outcomes following Traumatic Brain Injury (HEAD-TBI): protocol for a retrospective cohort study. BMJ Open 2023; 13:e073726. [PMID: 37491097 PMCID: PMC10373748 DOI: 10.1136/bmjopen-2023-073726] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/27/2023] Open
Abstract
BACKGROUND It is estimated that by 2050 the global incidence of dementia will have exceeded 152 million. At present, there are no effective therapies for dementia, with a focus in research now turning to strategies for disease prevention. Traumatic brain injury (TBI) is recognised as a major risk factor for dementia; estimated to be responsible for at least 3% of cases in the community. However, adverse health outcomes after TBI are not restricted to dementia. A wide range of conditions are documented among TBI survivors, many of which also increase dementia risk. 'HEalth And Dementia outcomes following Traumatic Brain Injury' is a study aiming to explore the hypothesis that increased dementia risk following TBI reflects both the direct effect of the injury on the brain and the indirect effects of wider, adverse health outcomes associated with TBI which, in turn, increase dementia risk. METHODS AND ANALYSIS Comprehensive electronic medical and death certification records will be analysed for individuals with a documented history of TBI, compared with those of a matched general population control cohort with no documented TBI exposure. Cox proportional hazard regression models will be run to compare outcomes. Furthermore, existing diagnostic imaging and radiological reports for the cohort will be analysed to identify evidence of specific white matter abnormalities in TBI exposed individuals and their controls, and establish their potential diagnostic utility. ETHICS AND DISSEMINATION Approvals for the study have been obtained from the University of Glasgow College of Medical, Veterinary, and Life Sciences Research Ethics Committee (project number 200220038) and from National Health Service Scotland's Public Benefits and Privacy Panel (application 2122-0224). As results emerge, these will be presented at appropriate multidisciplinary research conferences and made available through open access platforms where possible.
Collapse
Affiliation(s)
| | - Donald M Lyall
- School of Health and Wellbeing, University of Glasgow, Glasgow, UK
| | - William Stewart
- School of Psychology and Neuroscience, University of Glasgow, Glasgow, UK
- Neuropathology Research Laboratory, NHS Greater Glasgow and Clyde, Glasgow, UK
| |
Collapse
|