1
|
Zabihi M, Kia SM, Wolfers T, de Boer S, Fraza C, Dinga R, Arenas AL, Bzdok D, Beckmann CF, Marquand A. Nonlinear latent representations of high-dimensional task-fMRI data: Unveiling cognitive and behavioral insights in heterogeneous spatial maps. PLoS One 2024; 19:e0308329. [PMID: 39116147 PMCID: PMC11309387 DOI: 10.1371/journal.pone.0308329] [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: 10/18/2023] [Accepted: 07/22/2024] [Indexed: 08/10/2024] Open
Abstract
Finding an interpretable and compact representation of complex neuroimaging data is extremely useful for understanding brain behavioral mapping and hence for explaining the biological underpinnings of mental disorders. However, hand-crafted representations, as well as linear transformations, may inadequately capture the considerable variability across individuals. Here, we implemented a data-driven approach using a three-dimensional autoencoder on two large-scale datasets. This approach provides a latent representation of high-dimensional task-fMRI data which can account for demographic characteristics whilst also being readily interpretable both in the latent space learned by the autoencoder and in the original voxel space. This was achieved by addressing a joint optimization problem that simultaneously reconstructs the data and predicts clinical or demographic variables. We then applied normative modeling to the latent variables to define summary statistics ('latent indices') and establish a multivariate mapping to non-imaging measures. Our model, trained with multi-task fMRI data from the Human Connectome Project (HCP) and UK biobank task-fMRI data, demonstrated high performance in age and sex predictions and successfully captured complex behavioral characteristics while preserving individual variability through a latent representation. Our model also performed competitively with respect to various baseline models including several variants of principal components analysis, independent components analysis and classical regions of interest, both in terms of reconstruction accuracy and strength of association with behavioral variables.
Collapse
Affiliation(s)
- Mariam Zabihi
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
- MRC Unit for Lifelong Health & Ageing, University College London (UCL), London, United Kingdom
| | - Seyed Mostafa Kia
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
- Department of Psychiatry, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Thomas Wolfers
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
- NORMENT, KG Jebsen Centre for Psychosis Research, Division of Mental Health and Addiction, Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway
- Department of Psychiatry and Psychotherapy, Tübingen Center for Mental Health, University of Tübingen, Tübingen, Germany
| | - Stijn de Boer
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
| | - Charlotte Fraza
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
| | - Richard Dinga
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
| | - Alberto Llera Arenas
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
| | - Danilo Bzdok
- Multimodal Imaging and Connectome Analysis Lab, McConnell Brain Imaging Centre, Montreal Neurological Institute and Hospital, McGill University, Montreal, Quebec, Canada
- Mila ‐ Quebec Artificial Intelligence Institute, Montreal, Quebec, Canada
| | - Christian F. Beckmann
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
- Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
| | - Andre Marquand
- Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, the Netherlands
- Department for Cognitive Neuroscience, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands
- Department of Neuroimaging, Institute of Psychiatry, Psychology, & Neuroscience, King’s College London, London, United Kingdom
| |
Collapse
|
2
|
Yan Y, He X, Xu Y, Zhao F, Peng J, Shao Y. Pattern of heterogeneity in normal brain ageing: screening for mild cognitive impairment and its risk of progression with a radiomics model. Age Ageing 2024; 53:afae140. [PMID: 38984695 DOI: 10.1093/ageing/afae140] [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: 11/23/2023] [Revised: 05/01/2024] [Indexed: 07/11/2024] Open
Abstract
PURPOSE This study aimed to develop a normal brain ageing model based on magnetic resonance imaging and radiomics, therefore identifying radscore, an imaging indicator representing white matter heterogeneity and exploring the significance of radscore in detecting people's cognitive changes. METHODS Three hundred sixty cognitively normal (CN) subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and 105 CN subjects from the Parkinson's Progression Markers Initiative database were used to develop the model. In ADNI, 230 mild cognitive impairment (MCI) subjects were matched with 230 CN old-aged subjects to evaluate their heterogeneity difference. One hundred four MCI subjects with 48 months of follow-up were divided into low and high heterogeneity groups. Kaplan-Meier survival curve analysis was used to observe the importance of heterogeneity results for predicting MCI progression. RESULTS The area under the receiver operating characteristic curve of the model in the training, internal test and external test sets was 0.7503, 0.7512 and 0.7514, respectively. There was a significantly positive correlation between age and radscore of CN subjects (r = 0.501; P < .001). The radscore of MCI subjects was significantly higher than that of matched CN subjects (P < .001). The median radscore ratios of MCI to CN from four age groups (66-70y, 71-75y, 76-80y and 81-85y) were 1.611, 1.760, 1.340 and 1.266, respectively. The probability to progression of low and high heterogeneity groups had a significant difference (P = .002). CONCLUSION When radscore is significantly higher than that of normal ageing, it is necessary to alert the possibility of cognitive impairment and deterioration.
Collapse
Affiliation(s)
- Yuting Yan
- Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou 310014, Zhejiang, China
| | - Xiaodong He
- Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou 310014, Zhejiang, China
| | - Yuyun Xu
- Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou 310014, Zhejiang, China
| | - Fanfan Zhao
- Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou 310014, Zhejiang, China
| | - Jiaxuan Peng
- Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou 310014, Zhejiang, China
| | - Yuan Shao
- Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou 310014, Zhejiang, China
| |
Collapse
|
3
|
Zhang X, Duan SY, Wang SQ, Chen YW, Lai SX, Zou JS, Cheng Y, Guan JT, Wu RH, Zhang XL. A ResNet mini architecture for brain age prediction. Sci Rep 2024; 14:11185. [PMID: 38755275 PMCID: PMC11098808 DOI: 10.1038/s41598-024-61915-5] [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: 01/30/2024] [Accepted: 05/10/2024] [Indexed: 05/18/2024] Open
Abstract
The brain presents age-related structural and functional changes in the human life, with different extends between subjects and groups. Brain age prediction can be used to evaluate the development and aging of human brain, as well as providing valuable information for neurodevelopment and disease diagnosis. Many contributions have been made for this purpose, resorting to different machine learning methods. To solve this task and reduce memory resource consumption, we develop a mini architecture of only 10 layers by modifying the deep residual neural network (ResNet), named ResNet mini architecture. To support the ResNet mini architecture in brain age prediction, the brain age dataset (OpenNeuro #ds000228) that consists of 155 study participants (three classes) and the Alzheimer MRI preprocessed dataset that consists of 6400 images (four classes) are employed. We compared the performance of the ResNet mini architecture with other popular networks using the two considered datasets. Experimental results show that the proposed architecture exhibits generality and robustness with high accuracy and less parameter number.
Collapse
Affiliation(s)
- Xuan Zhang
- College of Engineering, Shantou University, Shantou, 515063, China
| | - Si-Yuan Duan
- College of Computer Science, Sichuan University, Chengdu, 610065, China
| | - Si-Qi Wang
- College of Engineering, Shantou University, Shantou, 515063, China
| | - Yao-Wen Chen
- College of Engineering, Shantou University, Shantou, 515063, China
| | - Shi-Xin Lai
- College of Engineering, Shantou University, Shantou, 515063, China
| | - Ji-Sheng Zou
- College of Engineering, Shantou University, Shantou, 515063, China
| | - Yan Cheng
- Department of Radiology, Second Hospital of Shandong University, Jinan, 250033, China
| | - Ji-Tian Guan
- Department of Radiology, Second Affiliated Hospital of Shantou University Medical College, Shantou, 515041, China
| | - Ren-Hua Wu
- Department of Radiology, Second Affiliated Hospital of Shantou University Medical College, Shantou, 515041, China.
| | - Xiao-Lei Zhang
- Department of Radiology, Second Affiliated Hospital of Shantou University Medical College, Shantou, 515041, China.
| |
Collapse
|
4
|
Aiskovich M, Castro E, Reinen JM, Fadnavis S, Mehta A, Li H, Dhurandhar A, Cecchi GA, Polosecki P. Fusion of biomedical imaging studies for increased sample size and diversity: a case study of brain MRI. FRONTIERS IN RADIOLOGY 2024; 4:1283392. [PMID: 38645773 PMCID: PMC11026619 DOI: 10.3389/fradi.2024.1283392] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Accepted: 03/11/2024] [Indexed: 04/23/2024]
Abstract
Data collection, curation, and cleaning constitute a crucial phase in Machine Learning (ML) projects. In biomedical ML, it is often desirable to leverage multiple datasets to increase sample size and diversity, but this poses unique challenges, which arise from heterogeneity in study design, data descriptors, file system organization, and metadata. In this study, we present an approach to the integration of multiple brain MRI datasets with a focus on homogenization of their organization and preprocessing for ML. We use our own fusion example (approximately 84,000 images from 54,000 subjects, 12 studies, and 88 individual scanners) to illustrate and discuss the issues faced by study fusion efforts, and we examine key decisions necessary during dataset homogenization, presenting in detail a database structure flexible enough to accommodate multiple observational MRI datasets. We believe our approach can provide a basis for future similarly-minded biomedical ML projects.
Collapse
Affiliation(s)
| | - Eduardo Castro
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Jenna M. Reinen
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Shreyas Fadnavis
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Anushree Mehta
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Hongyang Li
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Amit Dhurandhar
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Guillermo A. Cecchi
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| | - Pablo Polosecki
- IBM T. J. Watson Research Center, Yorktown Heights, New York, NY, United States
| |
Collapse
|
5
|
Seitz-Holland J, Haas SS, Penzel N, Reichenberg A, Pasternak O. BrainAGE, brain health, and mental disorders: A systematic review. Neurosci Biobehav Rev 2024; 159:105581. [PMID: 38354871 PMCID: PMC11119273 DOI: 10.1016/j.neubiorev.2024.105581] [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: 11/09/2023] [Revised: 02/05/2024] [Accepted: 02/09/2024] [Indexed: 02/16/2024]
Abstract
The imaging-based method of brainAGE aims to characterize an individual's vulnerability to age-related brain changes. The present study systematically reviewed brainAGE findings in neuropsychiatric conditions and discussed the potential of brainAGE as a marker for biological age. A systematic PubMed search (from inception to March 6th, 2023) identified 273 articles. The 30 included studies compared brainAGE between neuropsychiatric and healthy groups (n≥50). We presented results qualitatively and adapted a bias risk assessment questionnaire. The imaging modalities, design, and input features varied considerably between studies. While the studies found higher brainAGE in neuropsychiatric conditions (11 mild cognitive impairment/ dementia, 11 schizophrenia spectrum/ other psychotic and bipolar disorder, six depression/ anxiety, two multiple groups), the associations with clinical characteristics were mixed. While brainAGE is sensitive to group differences, limitations include the lack of diverse training samples, multi-modal studies, and external validation. Only a few studies obtained longitudinal data, and all have used algorithms built solely to predict chronological age. These limitations impede the validity of brainAGE as a biological age marker.
Collapse
Affiliation(s)
- Johanna Seitz-Holland
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA; Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
| | - Shalaila S Haas
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Nora Penzel
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Abraham Reichenberg
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Mindich Child Health and Development Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Ofer Pasternak
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA; Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
6
|
Liu R, Li X, Liu Y, Du L, Zhu Y, Wu L, Hu B. A high-speed microscopy system based on deep learning to detect yeast-like fungi cells in blood. Bioanalysis 2024; 16:289-303. [PMID: 38334080 DOI: 10.4155/bio-2023-0193] [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: 02/10/2024] Open
Abstract
Background: Blood-invasive fungal infections can cause the death of patients, while diagnosis of fungal infections is challenging. Methods: A high-speed microscopy detection system was constructed that included a microfluidic system, a microscope connected to a high-speed camera and a deep learning analysis section. Results: For training data, the sensitivity and specificity of the convolutional neural network model were 93.5% (92.7-94.2%) and 99.5% (99.1-99.5%), respectively. For validating data, the sensitivity and specificity were 81.3% (80.0-82.5%) and 99.4% (99.2-99.6%), respectively. Cryptococcal cells were found in 22.07% of blood samples. Conclusion: This high-speed microscopy system can analyze fungal pathogens in blood samples rapidly with high sensitivity and specificity and can help dramatically accelerate the diagnosis of fungal infectious diseases.
Collapse
Affiliation(s)
- Ruiqi Liu
- Guangxi Key Laboratory of Special Biomedicine, School of Medicine, Guangxi University, Nanning, Guangxi, P.R. China
| | - Xiaojie Li
- Department of Laboratory Medicine, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, P.R. China
| | - Yingyi Liu
- Guangxi Key Laboratory of Special Biomedicine, School of Medicine, Guangxi University, Nanning, Guangxi, P.R. China
| | - Lijun Du
- Department of Clinical Laboratory, Huadu District People's Hospital of Guangzhou, Guangdong, China
| | - Yingzhu Zhu
- Guangzhou Waterrock Gene Technology, Guangdong, China
| | - Lichuan Wu
- Guangxi Key Laboratory of Special Biomedicine, School of Medicine, Guangxi University, Nanning, Guangxi, P.R. China
| | - Bo Hu
- Department of Laboratory Medicine, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, P.R. China
| |
Collapse
|
7
|
Chen M, Wang Y, Shi Y, Feng J, Feng R, Guan X, Xu X, Zhang Y, Jin C, Wei H. Brain Age Prediction Based on Quantitative Susceptibility Mapping Using the Segmentation Transformer. IEEE J Biomed Health Inform 2024; 28:1012-1021. [PMID: 38090820 DOI: 10.1109/jbhi.2023.3341629] [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: 12/19/2023]
Abstract
The process of brain aging is intricate, encompassing significant structural and functional changes, including myelination and iron deposition in the brain. Brain age could act as a quantitative marker to evaluate the degree of the individual's brain evolution. Quantitative susceptibility mapping (QSM) is sensitive to variations in magnetically responsive substances such as iron and myelin, making it a favorable tool for estimating brain age. In this study, we introduce an innovative 3D convolutional network named Segmentation-Transformer-Age-Network (STAN) to predict brain age based on QSM data. STAN employs a two-stage network architecture. The first-stage network learns to extract informative features from the QSM data through segmentation training, while the second-stage network predicts brain age by integrating the global and local features. We collected QSM images from 712 healthy participants, with 548 for training and 164 for testing. The results demonstrate that the proposed method achieved a high accuracy brain age prediction with a mean absolute error (MAE) of 4.124 years and a coefficient of determination (R2) of 0.933. Furthermore, the gaps between the predicted brain age and the chronological age of Parkinson's disease patients were significantly higher than those of healthy subjects (P<0.01). We thus believe that using QSM-based predicted brain age offers a more reliable and accurate phenotype, with the potentiality to serve as a biomarker to explore the process of advanced brain aging.
Collapse
|
8
|
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
|
9
|
Dartora C, Marseglia A, Mårtensson G, Rukh G, Dang J, Muehlboeck JS, Wahlund LO, Moreno R, Barroso J, Ferreira D, Schiöth HB, Westman E. A deep learning model for brain age prediction using minimally preprocessed T1w images as input. Front Aging Neurosci 2024; 15:1303036. [PMID: 38259636 PMCID: PMC10800627 DOI: 10.3389/fnagi.2023.1303036] [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: 09/27/2023] [Accepted: 12/04/2023] [Indexed: 01/24/2024] Open
Abstract
Introduction In the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction. Methods We used a multicohort dataset of cognitively healthy individuals (age range = 32.0-95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2-4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset's images in the cross-validation training (CNN3). To ensure that our model used only the brain signal on the image, we also predicted brain age using skull-stripped images (CNN4). Results The trained models achieved a mean absolute error of 2.99, 2.67, 2.67, and 3.08 years for CNN1-4, respectively. The model's performance in the external dataset was in the typical range of mean absolute error (MAE) found in the literature for testing sets. Adding the external dataset to the training set (CNN3), overall, MAE is unaffected, but individual cohort MAE improves (5.63-2.25 years). Salience maps of predictions reveal that periventricular, temporal, and insular regions are the most important for age prediction. Discussion We provide indicators for using biological (predicted) brain age as a metric for age correction in neuroimaging studies as an alternative to the traditional chronological age. In conclusion, using different approaches, our CNN-based model showed good performance using one T1w brain MRI preprocessing step. The proposed CNN model is made publicly available for the research community to be easily implemented and used to study ageing and age-related disorders.
Collapse
Affiliation(s)
- Caroline Dartora
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Anna Marseglia
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Gustav Mårtensson
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Gull Rukh
- Department of Surgical Sciences, Functional Pharmacology and Neuroscience, Uppsala University, Uppsala, Sweden
| | - Junhua Dang
- Department of Surgical Sciences, Functional Pharmacology and Neuroscience, Uppsala University, Uppsala, Sweden
| | - J-Sebastian Muehlboeck
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Lars-Olof Wahlund
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Rodrigo Moreno
- Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Stockholm, Sweden
| | - José Barroso
- Facultad de Ciencias de la Salud, Universidad Fernando Pessoa Canarias, Las Palmas, España
| | - Daniel Ferreira
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
- Facultad de Ciencias de la Salud, Universidad Fernando Pessoa Canarias, Las Palmas, España
| | - Helgi B. Schiöth
- Department of Surgical Sciences, Functional Pharmacology and Neuroscience, Uppsala University, Uppsala, Sweden
| | - Eric Westman
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
- Department of Neuroimaging, Centre for Neuroimaging Sciences, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United Kingdom
| | | | | | | | | |
Collapse
|
10
|
Diniz BS, Seitz-Holland J, Sehgal R, Kasamoto J, Higgins-Chen AT, Lenze E. Geroscience-Centric Perspective for Geriatric Psychiatry: Integrating Aging Biology With Geriatric Mental Health Research. Am J Geriatr Psychiatry 2024; 32:1-16. [PMID: 37845116 PMCID: PMC10841054 DOI: 10.1016/j.jagp.2023.09.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 08/30/2023] [Accepted: 09/14/2023] [Indexed: 10/18/2023]
Abstract
The geroscience hypothesis asserts that physiological aging is caused by a small number of biological pathways. Despite the explosion of geroscience research over the past couple of decades, the research on how serious mental illnesses (SMI) affects the biological aging processes is still in its infancy. In this review, we aim to provide a critical appraisal of the emerging literature focusing on how we measure biological aging systematically, and in the brain and how SMIs affect biological aging measures in older adults. We will also review recent developments in the field of cellular senescence and potential targets for interventions for SMIs in older adults, based on the geroscience hypothesis.
Collapse
Affiliation(s)
- Breno S Diniz
- UConn Center on Aging & Department of Psychiatry (BSD), School of Medicine, University of Connecticut Health Center, Farmington, CT.
| | - Johanna Seitz-Holland
- Department of Psychiatry (JSH), Brigham and Women's Hospital, Harvard Medical School, Boston, MA; Department of Psychiatry (JSH), Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | - Raghav Sehgal
- Program in Computational Biology and Bioinformatics (RS, JK), Yale University, New Haven, CT
| | - Jessica Kasamoto
- Program in Computational Biology and Bioinformatics (RS, JK), Yale University, New Haven, CT
| | - Albert T Higgins-Chen
- Department of Psychiatry (ATHC), Yale University School of Medicine, New Haven, CT; Department of Pathology (ATHC), Yale University School of Medicine, New Haven, CT
| | - Eric Lenze
- Department of Psychiatry (EL), School of Medicine, Washington University at St. Louis, St. Louis, MO
| |
Collapse
|
11
|
Joo Y, Namgung E, Jeong H, Kang I, Kim J, Oh S, Lyoo IK, Yoon S, Hwang J. Brain age prediction using combined deep convolutional neural network and multi-layer perceptron algorithms. Sci Rep 2023; 13:22388. [PMID: 38104173 PMCID: PMC10725434 DOI: 10.1038/s41598-023-49514-2] [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: 04/06/2023] [Accepted: 12/08/2023] [Indexed: 12/19/2023] Open
Abstract
The clinical applications of brain age prediction have expanded, particularly in anticipating the onset and prognosis of various neurodegenerative diseases. In the current study, we proposed a deep learning algorithm that leverages brain structural imaging data and enhances prediction accuracy by integrating biological sex information. Our model for brain age prediction, built on deep neural networks, employed a dataset of 3004 healthy subjects aged 18 and above. The T1-weighted images were minimally preprocessed and analyzed using the convolutional neural network (CNN) algorithm. The categorical sex information was then incorporated using the multi-layer perceptron (MLP) algorithm. We trained and validated both a CNN-only algorithm (utilizing only brain structural imaging data), and a combined CNN-MLP algorithm (using both structural brain imaging data and sex information) for age prediction. By integrating sex information with T1-weighted imaging data, our proposed CNN-MLP algorithm outperformed not only the CNN-only algorithm but also established algorithms, such as brainageR, in prediction accuracy. Notably, this hybrid CNN-MLP algorithm effectively distinguished between mild cognitive impairment and Alzheimer's disease groups by identifying variances in brain age gaps between them, highlighting the algorithm's potential for clinical application. Overall, these results underscore the enhanced precision of the CNN-MLP algorithm in brain age prediction, achieved through the integration of sex information.
Collapse
Affiliation(s)
- Yoonji Joo
- Ewha Brain Institute, Ewha Womans University, Seoul, South Korea
| | - Eun Namgung
- Asan Institute for Life Sciences, Asan Medical Center, Seoul, South Korea
| | - Hyeonseok Jeong
- Department of Radiology, Incheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea
| | - Ilhyang Kang
- Ewha Brain Institute, Ewha Womans University, Seoul, South Korea
| | - Jinsol Kim
- Ewha Brain Institute, Ewha Womans University, Seoul, South Korea
| | - Sohyun Oh
- Ewha Brain Institute, Ewha Womans University, Seoul, South Korea
- Department of Brain and Cognitive Sciences, Ewha Womans University, Seoul, South Korea
| | - In Kyoon Lyoo
- Ewha Brain Institute, Ewha Womans University, Seoul, South Korea
- Department of Brain and Cognitive Sciences, Ewha Womans University, Seoul, South Korea
- Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul, South Korea
| | - Sujung Yoon
- Ewha Brain Institute, Ewha Womans University, Seoul, South Korea.
- Department of Brain and Cognitive Sciences, Ewha Womans University, Seoul, South Korea.
| | - Jaeuk Hwang
- Department of Psychiatry, Soonchunhyang University College of Medicine, Seoul, South Korea.
| |
Collapse
|
12
|
Jönemo J, Eklund A. Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes. J Imaging 2023; 9:271. [PMID: 38132689 PMCID: PMC10743800 DOI: 10.3390/jimaging9120271] [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: 10/19/2023] [Revised: 11/30/2023] [Accepted: 12/04/2023] [Indexed: 12/23/2023] Open
Abstract
Brain age prediction from 3D MRI volumes using deep learning has recently become a popular research topic, as brain age has been shown to be an important biomarker. Training deep networks can be very computationally demanding for large datasets like the U.K. Biobank (currently 29,035 subjects). In our previous work, it was demonstrated that using a few 2D projections (mean and standard deviation along three axes) instead of each full 3D volume leads to much faster training at the cost of a reduction in prediction accuracy. Here, we investigated if another set of 2D projections, based on higher-order statistical central moments and eigenslices, leads to a higher accuracy. Our results show that higher-order moments do not lead to a higher accuracy, but that eigenslices provide a small improvement. We also show that an ensemble of such models provides further improvement.
Collapse
Affiliation(s)
- Johan Jönemo
- Division of Medical Informatics, Department of Biomedical Engineering, Linköping University, 581 83 Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden
| | - Anders Eklund
- Division of Medical Informatics, Department of Biomedical Engineering, Linköping University, 581 83 Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden
- Division of Statistics and Machine Learning, Department of Computer and Information Science, Linköping University, 581 83 Linköping, Sweden
| |
Collapse
|
13
|
Antonopoulos G, More S, Raimondo F, Eickhoff SB, Hoffstaedter F, Patil KR. A systematic comparison of VBM pipelines and their application to age prediction. Neuroimage 2023; 279:120292. [PMID: 37572766 PMCID: PMC10529438 DOI: 10.1016/j.neuroimage.2023.120292] [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: 02/05/2023] [Revised: 06/23/2023] [Accepted: 07/21/2023] [Indexed: 08/14/2023] Open
Abstract
Voxel-based morphometry (VBM) analysis is commonly used for localized quantification of gray matter volume (GMV). Several alternatives exist to implement a VBM pipeline. However, how these alternatives compare and their utility in applications, such as the estimation of aging effects, remain largely unclear. This leaves researchers wondering which VBM pipeline they should use for their project. In this study, we took a user-centric perspective and systematically compared five VBM pipelines, together with registration to either a general or a study-specific template, utilizing three large datasets (n>500 each). Considering the known effect of aging on GMV, we first compared the pipelines in their ability of individual-level age prediction and found markedly varied results. To examine whether these results arise from systematic differences between the pipelines, we classified them based on their GMVs, resulting in near-perfect accuracy. To gain deeper insights, we examined the impact of different VBM steps using the region-wise similarity between pipelines. The results revealed marked differences, largely driven by segmentation and registration steps. We observed large variability in subject-identification accuracies, highlighting the interpipeline differences in individual-level quantification of GMV. As a biologically meaningful criterion we correlated regional GMV with age. The results were in line with the age-prediction analysis, and two pipelines, CAT and the combination of fMRIPrep for tissue characterization with FSL for registration, reflected age information better.
Collapse
Affiliation(s)
- Georgios Antonopoulos
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany; Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour), Research Centre Jülich, Jülich, Germany
| | - Shammi More
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany; Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour), Research Centre Jülich, Jülich, Germany
| | - Federico Raimondo
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany; Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour), Research Centre Jülich, Jülich, Germany
| | - Simon B Eickhoff
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany; Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour), Research Centre Jülich, Jülich, Germany
| | - Felix Hoffstaedter
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany; Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour), Research Centre Jülich, Jülich, Germany
| | - Kaustubh R Patil
- Institute of Systems Neuroscience, Heinrich Heine University Düsseldorf, Düsseldorf, Germany; Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour), Research Centre Jülich, Jülich, Germany.
| |
Collapse
|
14
|
Jönemo J, Akbar MU, Kämpe R, Hamilton JP, Eklund A. Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections. Brain Sci 2023; 13:1329. [PMID: 37759930 PMCID: PMC10526282 DOI: 10.3390/brainsci13091329] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2023] [Revised: 09/09/2023] [Accepted: 09/13/2023] [Indexed: 09/29/2023] Open
Abstract
Using 3D CNNs on high-resolution medical volumes is very computationally demanding, especially for large datasets like UK Biobank, which aims to scan 100,000 subjects. Here, we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of 3D volumes leads to reasonable test accuracy (mean absolute error of about 3.5 years) when predicting age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 20-50 s using a single GPU, which is two orders of magnitude faster than a small 3D CNN. This speedup is explained by the fact that 3D brain volumes contain a lot of redundant information, which can be efficiently compressed using 2D projections. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs.
Collapse
Affiliation(s)
- Johan Jönemo
- Division of Medical Informatics, Department of Biomedical Engineering, Linköping University, 581 83 Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden
| | - Muhammad Usman Akbar
- Division of Medical Informatics, Department of Biomedical Engineering, Linköping University, 581 83 Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden
| | - Robin Kämpe
- Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden
- Center for Social and Affective Neuroscience, Department of Biomedical and Clinical Sciences, Linköping University, 581 83 Linköping, Sweden
| | - J. Paul Hamilton
- Department of Biological and Medical Psychology, University of Bergen, 5020 Bergen, Norway
| | - Anders Eklund
- Division of Medical Informatics, Department of Biomedical Engineering, Linköping University, 581 83 Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden
- Division of Statistics and Machine Learning, Department of Computer and Information Science, Linköping University, 581 83 Linköping, Sweden
| |
Collapse
|
15
|
Fletcher E, Farias S, DeCarli C, Gavett B, Widaman K, De Leon F, Mungas D. Toward a statistical validation of brain signatures as robust measures of behavioral substrates. Hum Brain Mapp 2023; 44:3094-3111. [PMID: 36939069 PMCID: PMC10171525 DOI: 10.1002/hbm.26265] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Revised: 02/10/2023] [Accepted: 02/21/2023] [Indexed: 03/21/2023] Open
Abstract
The "brain signature of cognition" concept has garnered interest as a data-driven, exploratory approach to better understand key brain regions involved in specific cognitive functions, with the potential to maximally characterize brain substrates of behavioral outcomes. Previously we presented a method for computing signatures of episodic memory. However, to be a robust brain measure, the signature approach requires a rigorous validation of model performance across a variety of cohorts. Here we report validation results and provide an example of extending it to a second behavioral domain. In each of two discovery data cohorts, we derived regional brain gray matter thickness associations for two domains: neuropsychological and everyday cognition memory. We computed regional association to outcome in 40 randomly selected discovery subsets of size 400 in each cohort. We generated spatial overlap frequency maps and defined high-frequency regions as "consensus" signature masks. Using separate validation datasets, we evaluated replicability of cohort-based consensus model fits and explanatory power by comparing signature model fits with each other and with competing theory-based models. Spatial replications produced convergent consensus signature regions. Consensus signature model fits were highly correlated in 50 random subsets of each validation cohort, indicating high replicability. In comparisons over each full cohort, signature models outperformed other models. In this validation study, we produced signature models that replicated model fits to outcome and outperformed other commonly used measures. Signatures in two memory domains suggested strongly shared brain substrates. Robust brain signatures may therefore be achievable, yielding reliable and useful measures for modeling substrates of behavioral domains.
Collapse
Affiliation(s)
- Evan Fletcher
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Sarah Farias
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Charles DeCarli
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Brandon Gavett
- School of Psychological ScienceUniversity of Western AustraliaPerthAustralia
| | - Keith Widaman
- School of EducationUniversity of California, RiversideRiversideCaliforniaUSA
| | - Fransia De Leon
- School of MedicineUniversity of California, DavisDavisCaliforniaUSA
| | - Dan Mungas
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| |
Collapse
|
16
|
Tian YE, Cropley V, Maier AB, Lautenschlager NT, Breakspear M, Zalesky A. Heterogeneous aging across multiple organ systems and prediction of chronic disease and mortality. Nat Med 2023; 29:1221-1231. [PMID: 37024597 DOI: 10.1038/s41591-023-02296-6] [Citation(s) in RCA: 80] [Impact Index Per Article: 80.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Accepted: 03/09/2023] [Indexed: 04/08/2023]
Abstract
Biological aging of human organ systems reflects the interplay of age, chronic disease, lifestyle and genetic risk. Using longitudinal brain imaging and physiological phenotypes from the UK Biobank, we establish normative models of biological age for three brain and seven body systems. Here we find that an organ's biological age selectively influences the aging of other organ systems, revealing a multiorgan aging network. We report organ age profiles for 16 chronic diseases, where advanced biological aging extends from the organ of primary disease to multiple systems. Advanced body age associates with several lifestyle and environmental factors, leukocyte telomere lengths and mortality risk, and predicts survival time (area under the curve of 0.77) and premature death (area under the curve of 0.86). Our work reveals the multisystem nature of human aging in health and chronic disease. It may enable early identification of individuals at increased risk of aging-related morbidity and inform new strategies to potentially limit organ-specific aging in such individuals.
Collapse
Affiliation(s)
- Ye Ella Tian
- Melbourne Neuropsychiatry Centre, Department of Psychiatry, Melbourne Medical School, The University of Melbourne, Melbourne, Victoria, Australia.
| | - Vanessa Cropley
- Melbourne Neuropsychiatry Centre, Department of Psychiatry, Melbourne Medical School, The University of Melbourne, Melbourne, Victoria, Australia
| | - Andrea B Maier
- Healthy Longevity Translational Research Program, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
- Centre for Healthy Longevity, @AgeSingapore, National University Health System, Singapore, Singapore
- Department of Human Movement Sciences, @AgeAmsterdam, Amsterdam Movement Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| | - Nicola T Lautenschlager
- Academic Unit for Psychiatry of Old Age, Department of Psychiatry, Melbourne Medical School, The University of Melbourne, Melbourne, Victoria, Australia
- NorthWestern Mental Health, Royal Melbourne Hospital, Melbourne, Victoria, Australia
| | - Michael Breakspear
- Discipline of Psychiatry, College of Health, Medicine and Wellbeing, The University of Newcastle, Newcastle, New South Wales, Australia
- School of Psychological Sciences, College of Engineering, Science and Environment, The University of Newcastle, Newcastle, New South Wales, Australia
| | - Andrew Zalesky
- Melbourne Neuropsychiatry Centre, Department of Psychiatry, Melbourne Medical School, The University of Melbourne, Melbourne, Victoria, Australia.
- Department of Biomedical Engineering, Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Victoria, Australia.
| |
Collapse
|
17
|
Thomas AW, Ré C, Poldrack RA. Benchmarking explanation methods for mental state decoding with deep learning models. Neuroimage 2023; 273:120109. [PMID: 37059157 DOI: 10.1016/j.neuroimage.2023.120109] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Revised: 04/04/2023] [Accepted: 04/11/2023] [Indexed: 04/16/2023] Open
Abstract
Deep learning (DL) models find increasing application in mental state decoding, where researchers seek to understand the mapping between mental states (e.g., experiencing anger or joy) and brain activity by identifying those spatial and temporal features of brain activity that allow to accurately identify (i.e., decode) these states. Once a DL model has been trained to accurately decode a set of mental states, neuroimaging researchers often make use of methods from explainable artificial intelligence research to understand the model's learned mappings between mental states and brain activity. Here, we benchmark prominent explanation methods in a mental state decoding analysis of multiple functional Magnetic Resonance Imaging (fMRI) datasets. Our findings demonstrate a gradient between two key characteristics of an explanation in mental state decoding, namely, its faithfulness and its alignment with other empirical evidence on the mapping between brain activity and decoded mental state: explanation methods with high explanation faithfulness, which capture the model's decision process well, generally provide explanations that align less well with other empirical evidence than the explanations of methods with less faithfulness. Based on our findings, we provide guidance for neuroimaging researchers on how to choose an explanation method to gain insight into the mental state decoding decisions of DL models.
Collapse
Affiliation(s)
- Armin W Thomas
- Stanford Data Science, Stanford University, 450 Serra Mall, 94305, Stanford, USA.
| | - Christopher Ré
- Dept. of Computer Science, Stanford University, 450 Serra Mall, 94305, Stanford, USA
| | - Russell A Poldrack
- Dept. of Psychology, Stanford University, 450 Serra Mall, Stanford, 94305, USA
| |
Collapse
|
18
|
Bass C, Silva MD, Sudre C, Williams LZJ, Sousa HS, Tudosiu PD, Alfaro-Almagro F, Fitzgibbon SP, Glasser MF, Smith SM, Robinson EC. ICAM-Reg: Interpretable Classification and Regression With Feature Attribution for Mapping Neurological Phenotypes in Individual Scans. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:959-970. [PMID: 36374873 DOI: 10.1109/tmi.2022.3221890] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
An important goal of medical imaging is to be able to precisely detect patterns of disease specific to individual scans; however, this is challenged in brain imaging by the degree of heterogeneity of shape and appearance. Traditional methods, based on image registration, historically fail to detect variable features of disease, as they utilise population-based analyses, suited primarily to studying group-average effects. In this paper we therefore take advantage of recent developments in generative deep learning to develop a method for simultaneous classification, or regression, and feature attribution (FA). Specifically, we explore the use of a VAE-GAN (variational autoencoder - general adversarial network) for translation called ICAM, to explicitly disentangle class relevant features, from background confounds, for improved interpretability and regression of neurological phenotypes. We validate our method on the tasks of Mini-Mental State Examination (MMSE) cognitive test score prediction for the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, as well as brain age prediction, for both neurodevelopment and neurodegeneration, using the developing Human Connectome Project (dHCP) and UK Biobank datasets. We show that the generated FA maps can be used to explain outlier predictions and demonstrate that the inclusion of a regression module improves the disentanglement of the latent space. Our code is freely available on GitHub https://github.com/CherBass/ICAM.
Collapse
|
19
|
Zhou Z, Li H, Srinivasan D, Abdulkadir A, Nasrallah IM, Wen J, Doshi J, Erus G, Mamourian E, Bryan NR, Wolk DA, Beason-Held L, Resnick SM, Satterthwaite TD, Davatzikos C, Shou H, Fan Y. Multiscale functional connectivity patterns of the aging brain learned from harmonized rsfMRI data of the multi-cohort iSTAGING study. Neuroimage 2023; 269:119911. [PMID: 36731813 PMCID: PMC9992322 DOI: 10.1016/j.neuroimage.2023.119911] [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: 10/14/2022] [Revised: 01/06/2023] [Accepted: 01/28/2023] [Indexed: 02/03/2023] Open
Abstract
To learn multiscale functional connectivity patterns of the aging brain, we built a brain age prediction model of functional connectivity measures at seven scales on a large fMRI dataset, consisting of resting-state fMRI scans of 4186 individuals with a wide age range (22 to 97 years, with an average of 63) from five cohorts. We computed multiscale functional connectivity measures of individual subjects using a personalized functional network computational method, harmonized the functional connectivity measures of subjects from multiple datasets in order to build a functional brain age model, and finally evaluated how functional brain age gap correlated with cognitive measures of individual subjects. Our study has revealed that functional connectivity measures at multiple scales were more informative than those at any single scale for the brain age prediction, the data harmonization significantly improved the brain age prediction performance, and the data harmonization in the functional connectivity measures' tangent space worked better than in their original space. Moreover, brain age gap scores of individual subjects derived from the brain age prediction model were significantly correlated with clinical and cognitive measures. Overall, these results demonstrated that multiscale functional connectivity patterns learned from a large-scale multi-site rsfMRI dataset were informative for characterizing the aging brain and the derived brain age gap was associated with cognitive and clinical measures.
Collapse
Affiliation(s)
- Zhen Zhou
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA.
| | - Hongming Li
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Dhivya Srinivasan
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Ahmed Abdulkadir
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Ilya M Nasrallah
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Junhao Wen
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Jimit Doshi
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Guray Erus
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Elizabeth Mamourian
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Nick R Bryan
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Diagnostic Medicine, University of Texas at Austin, Austin, TX, 78705, USA
| | - David A Wolk
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Neurology and Penn Memory Center, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Lori Beason-Held
- Laboratory of Behavioral Neuroscience, National Institute on Aging, Baltimore, MD, 20892, USA
| | - Susan M Resnick
- Laboratory of Behavioral Neuroscience, National Institute on Aging, Baltimore, MD, 20892, USA
| | - Theodore D Satterthwaite
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Penn Statistic in Imaging and Visualization Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Psychiatry, Lifespan Informatics and Neuroimaging Center, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Psychiatry, Brain Behavior Laboratory and Penn-CHOP Lifespan Brain Institute, University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA, 19104, USA
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Haochang Shou
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Penn Statistic in Imaging and Visualization Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Yong Fan
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA.
| |
Collapse
|
20
|
Intracranial Hemorrhage Detection Using Parallel Deep Convolutional Models and Boosting Mechanism. Diagnostics (Basel) 2023; 13:diagnostics13040652. [PMID: 36832137 PMCID: PMC9955715 DOI: 10.3390/diagnostics13040652] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 01/31/2023] [Accepted: 02/02/2023] [Indexed: 02/12/2023] Open
Abstract
Intracranial hemorrhage (ICH) can lead to death or disability, which requires immediate action from radiologists. Due to the heavy workload, less experienced staff, and the complexity of subtle hemorrhages, a more intelligent and automated system is necessary to detect ICH. In literature, many artificial-intelligence-based methods are proposed. However, they are less accurate for ICH detection and subtype classification. Therefore, in this paper, we present a new methodology to improve the detection and subtype classification of ICH based on two parallel paths and a boosting technique. The first path employs the architecture of ResNet101-V2 to extract potential features from windowed slices, whereas Inception-V4 captures significant spatial information in the second path. Afterwards, the detection and subtype classification of ICH is performed by the light gradient boosting machine (LGBM) using the outputs of ResNet101-V2 and Inception-V4. Thus, the combined solution, known as ResNet101-V2, Inception-V4, and LGBM (Res-Inc-LGBM), is trained and tested over the brain computed tomography (CT) scans of CQ500 and Radiological Society of North America (RSNA) datasets. The experimental results state that the proposed solution efficiently obtains 97.7% accuracy, 96.5% sensitivity, and 97.4% F1 score using the RSNA dataset. Moreover, the proposed Res-Inc-LGBM outperforms the standard benchmarks for the detection and subtype classification of ICH regarding the accuracy, sensitivity, and F1 score. The results prove the significance of the proposed solution for its real-time application.
Collapse
|
21
|
Pan D, Zeng A, Yang B, Lai G, Hu B, Song X, Jiang T. Deep Learning for Brain MRI Confirms Patterned Pathological Progression in Alzheimer's Disease. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2023; 10:e2204717. [PMID: 36575159 PMCID: PMC9951348 DOI: 10.1002/advs.202204717] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 11/29/2022] [Indexed: 06/17/2023]
Abstract
Deep learning (DL) on brain magnetic resonance imaging (MRI) data has shown excellent performance in differentiating individuals with Alzheimer's disease (AD). However, the value of DL in detecting progressive structural MRI (sMRI) abnormalities linked to AD pathology has yet to be established. In this study, an interpretable DL algorithm named the Ensemble of 3-dimensional convolutional neural network (Ensemble 3DCNN) with enhanced parsing techniques is proposed to investigate the longitudinal trajectories of whole-brain sMRI changes denoting AD onset and progression. A set of 2369 T1-weighted images from the multi-centre Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies cohorts are applied to model derivation, validation, testing, and pattern analysis. An Ensemble-3DCNN-based P-score is generated, based on which multiple brain regions, including amygdala, insular, parahippocampal, and temporal gyrus, exhibit early and connected progressive neurodegeneration. Complex individual variability in the sMRI is also observed. This study combining non-invasive sMRI and interpretable DL in detecting patterned sMRI changes confirmed AD pathological progression, shedding new light on predicting AD progression using whole-brain sMRI.
Collapse
Affiliation(s)
- Dan Pan
- School of Electronics and InformationGuangdong Polytechnic Normal UniversityGuangzhou510665China
| | - An Zeng
- Faculty of Computers, Guangdong University of TechnologyGuangzhou510006China
| | - Baoyao Yang
- Faculty of Computers, Guangdong University of TechnologyGuangzhou510006China
| | - Gangyong Lai
- Faculty of Computers, Guangdong University of TechnologyGuangzhou510006China
| | - Bing Hu
- Department of RadiologyThe Third Affiliated Hospital of SUN Yat‐sen UniversityGuangzhou510630China
| | - Xiaowei Song
- Clinical Research CentreSurrey Memorial HospitalFraser HealthSurreyBritish ColumbiaV3V 1Z2Canada
| | - Tianzi Jiang
- Brainnetome Center & National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing100190China
| | | |
Collapse
|
22
|
Cai H, Gao Y, Liu M. Graph Transformer Geometric Learning of Brain Networks Using Multimodal MR Images for Brain Age Estimation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:456-466. [PMID: 36374874 DOI: 10.1109/tmi.2022.3222093] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Brain age is considered as an important biomarker for detecting aging-related diseases such as Alzheimer's Disease (AD). Magnetic resonance imaging (MRI) have been widely investigated with deep neural networks for brain age estimation. However, most existing methods cannot make full use of multimodal MRIs due to the difference in data structure. In this paper, we propose a graph transformer geometric learning framework to model the multimodal brain network constructed by structural MRI (sMRI) and diffusion tensor imaging (DTI) for brain age estimation. First, we build a two-stream convolutional autoencoder to learn the latent representations for each imaging modality. The brain template with prior knowledge is utilized to calculate the features from the regions of interest (ROIs). Then, a multi-level construction of the brain network is proposed to establish the hybrid ROI connections in space, feature and modality. Next, a graph transformer network is proposed to model the cross-modal interaction and fusion by geometric learning for brain age estimation. Finally, the difference between the estimated age and the chronological age is used as an important biomarker for AD diagnosis. Our method is evaluated with the sMRI and DTI data from UK Biobank and Alzheimer's Disease Neuroimaging Initiative database. Experimental results demonstrate that our method has achieved promising performances for brain age estimation and AD diagnosis.
Collapse
|
23
|
Kim J, Lee J, Nam K, Lee S. Investigation of genetic variants and causal biomarkers associated with brain aging. Sci Rep 2023; 13:1526. [PMID: 36707530 PMCID: PMC9883521 DOI: 10.1038/s41598-023-27903-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2022] [Accepted: 01/10/2023] [Indexed: 01/29/2023] Open
Abstract
Delta age is a biomarker of brain aging that captures differences between the chronological age and the predicted biological brain age. Using multimodal data of brain MRI, genomics, and blood-based biomarkers and metabolomics in UK Biobank, this study investigates an explainable and causal basis of high delta age. A visual saliency map of brain regions showed that lower volumes in the fornix and the lower part of the thalamus are key predictors of high delta age. Genome-wide association analysis of the delta age using the SNP array data identified associated variants in gene regions such as KLF3-AS1 and STX1. GWAS was also performed on the volumes in the fornix and the lower part of the thalamus, showing a high genetic correlation with delta age, indicating that they share a genetic basis. Mendelian randomization (MR) for all metabolomic biomarkers and blood-related phenotypes showed that immune-related phenotypes have a causal impact on increasing delta age. Our analysis revealed regions in the brain that are susceptible to the aging process and provided evidence of the causal and genetic connections between immune responses and brain aging.
Collapse
Affiliation(s)
- Jangho Kim
- Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea
| | - Junhyeong Lee
- Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea
| | - Kisung Nam
- Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea
| | - Seunggeun Lee
- Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea.
| |
Collapse
|
24
|
Mouches P, Wilms M, Aulakh A, Langner S, Forkert ND. Multimodal brain age prediction fusing morphometric and imaging data and association with cardiovascular risk factors. Front Neurol 2022; 13:979774. [PMID: 36588902 PMCID: PMC9794870 DOI: 10.3389/fneur.2022.979774] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Accepted: 11/16/2022] [Indexed: 12/15/2022] Open
Abstract
Introduction The difference between the chronological and biological brain age, called the brain age gap (BAG), has been identified as a promising biomarker to detect deviation from normal brain aging and to indicate the presence of neurodegenerative diseases. Moreover, the BAG has been shown to encode biological information about general health, which can be measured through cardiovascular risk factors. Current approaches for biological brain age estimation, and therefore BAG estimation, either depend on hand-crafted, morphological measurements extracted from brain magnetic resonance imaging (MRI) or on direct analysis of brain MRI images. The former can be processed with traditional machine learning models while the latter is commonly processed with convolutional neural networks (CNNs). Using a multimodal setting, this study aims to compare both approaches in terms of biological brain age prediction accuracy and biological information captured in the BAG. Methods T1-weighted MRI, containing brain tissue information, and magnetic resonance angiography (MRA), providing information about brain arteries, from 1,658 predominantly healthy adults were used. The volumes, surface areas, and cortical thickness of brain structures were extracted from the T1-weighted MRI data, while artery density and thickness within the major blood flow territories and thickness of the major arteries were extracted from MRA data. Independent multilayer perceptron and CNN models were trained to estimate the brain age from the hand-crafted features and image data, respectively. Next, both approaches were fused to assess the benefits of combining image data and hand-crafted features for brain age prediction. Results The combined model achieved a mean absolute error of 4 years between the chronological and predicted biological brain age. Among the independent models, the lowest mean absolute error was observed for the CNN using T1-weighted MRI data (4.2 years). When evaluating the BAGs obtained using the different approaches and imaging modalities, diverging associations between cardiovascular risk factors were found. For example, BAGs obtained from the CNN models showed an association with systolic blood pressure, while BAGs obtained from hand-crafted measurements showed greater associations with obesity markers. Discussion In conclusion, the use of more diverse sources of data can improve brain age estimation modeling and capture more diverse biological deviations from normal aging.
Collapse
Affiliation(s)
- Pauline Mouches
- Biomedical Engineering Program, University of Calgary, Calgary, AB, Canada,Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada,Department of Radiology, University of Calgary, Calgary, AB, Canada,*Correspondence: Pauline Mouches
| | - Matthias Wilms
- Department of Paediatrics, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada,Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada,Alberta Children's Hospital Research Institute, University of Calgary, Calgary, AB, Canada
| | - Agampreet Aulakh
- Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
| | - Sönke Langner
- Institute for Diagnostic Radiology and Neuroradiology, Rostock University Medical Center, Rostock, Germany
| | - Nils D. Forkert
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada,Department of Radiology, University of Calgary, Calgary, AB, Canada,Alberta Children's Hospital Research Institute, University of Calgary, Calgary, AB, Canada
| |
Collapse
|
25
|
Dinsdale NK, Bluemke E, Sundaresan V, Jenkinson M, Smith SM, Namburete AIL. Challenges for machine learning in clinical translation of big data imaging studies. Neuron 2022; 110:3866-3881. [PMID: 36220099 DOI: 10.1016/j.neuron.2022.09.012] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2021] [Revised: 08/27/2021] [Accepted: 09/08/2022] [Indexed: 12/15/2022]
Abstract
Combining deep learning image analysis methods and large-scale imaging datasets offers many opportunities to neuroscience imaging and epidemiology. However, despite these opportunities and the success of deep learning when applied to a range of neuroimaging tasks and domains, significant barriers continue to limit the impact of large-scale datasets and analysis tools. Here, we examine the main challenges and the approaches that have been explored to overcome them. We focus on issues relating to data availability, interpretability, evaluation, and logistical challenges and discuss the problems that still need to be tackled to enable the success of "big data" deep learning approaches beyond research.
Collapse
Affiliation(s)
- Nicola K Dinsdale
- Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK; Oxford Machine Learning in NeuroImaging Lab, OMNI, Department of Computer Science, University of Oxford, Oxford, UK.
| | - Emma Bluemke
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
| | - Vaanathi Sundaresan
- Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Charlestown, MA, USA
| | - Mark Jenkinson
- Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK; Australian Institute for Machine Learning (AIML), School of Computer Science, University of Adelaide, Adelaide, SA, Australia; South Australian Health and Medical Research Institute (SAHMRI), North Terrace, Adelaide, SA, Australia
| | - Stephen M Smith
- Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - Ana I L Namburete
- Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK; Oxford Machine Learning in NeuroImaging Lab, OMNI, Department of Computer Science, University of Oxford, Oxford, UK
| |
Collapse
|
26
|
Tinauer C, Heber S, Pirpamer L, Damulina A, Schmidt R, Stollberger R, Ropele S, Langkammer C. Interpretable brain disease classification and relevance-guided deep learning. Sci Rep 2022; 12:20254. [PMID: 36424437 PMCID: PMC9691637 DOI: 10.1038/s41598-022-24541-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 11/16/2022] [Indexed: 11/27/2022] Open
Abstract
Deep neural networks are increasingly used for neurological disease classification by MRI, but the networks' decisions are not easily interpretable by humans. Heat mapping by deep Taylor decomposition revealed that (potentially misleading) image features even outside of the brain tissue are crucial for the classifier's decision. We propose a regularization technique to train convolutional neural network (CNN) classifiers utilizing relevance-guided heat maps calculated online during training. The method was applied using T1-weighted MR images from 128 subjects with Alzheimer's disease (mean age = 71.9 ± 8.5 years) and 290 control subjects (mean age = 71.3 ± 6.4 years). The developed relevance-guided framework achieves higher classification accuracies than conventional CNNs but more importantly, it relies on less but more relevant and physiological plausible voxels within brain tissue. Additionally, preprocessing effects from skull stripping and registration are mitigated. With the interpretability of the decision mechanisms underlying CNNs, these results challenge the notion that unprocessed T1-weighted brain MR images in standard CNNs yield higher classification accuracy in Alzheimer's disease than solely atrophy.
Collapse
Affiliation(s)
- Christian Tinauer
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria
| | - Stefan Heber
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria
| | - Lukas Pirpamer
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria ,grid.6612.30000 0004 1937 0642Medical Image Analysis Center (MIAC) and Department of Biomedical Engineering, University of Basel, Basel, Switzerland
| | - Anna Damulina
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria
| | - Reinhold Schmidt
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria
| | - Rudolf Stollberger
- grid.410413.30000 0001 2294 748XInstitute of Biomedical Imaging, Graz University of Technology, Graz, Austria ,grid.452216.6BioTechMed-Graz, Graz, Austria
| | - Stefan Ropele
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria ,grid.452216.6BioTechMed-Graz, Graz, Austria
| | - Christian Langkammer
- grid.11598.340000 0000 8988 2476Department of Neurology, Medical University of Graz, Graz, Austria ,grid.452216.6BioTechMed-Graz, Graz, Austria
| |
Collapse
|
27
|
Thomas AW, Ré C, Poldrack RA. Interpreting mental state decoding with deep learning models. Trends Cogn Sci 2022; 26:972-986. [PMID: 36223760 DOI: 10.1016/j.tics.2022.07.003] [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: 08/14/2021] [Revised: 07/15/2022] [Accepted: 07/18/2022] [Indexed: 01/12/2023]
Abstract
In mental state decoding, researchers aim to identify the set of mental states (e.g., experiencing happiness or fear) that can be reliably identified from the activity patterns of a brain region (or network). Deep learning (DL) models are highly promising for mental state decoding because of their unmatched ability to learn versatile representations of complex data. However, their widespread application in mental state decoding is hindered by their lack of interpretability, difficulties in applying them to small datasets, and in ensuring their reproducibility and robustness. We recommend approaching these challenges by leveraging recent advances in explainable artificial intelligence (XAI) and transfer learning, and also provide recommendations on how to improve the reproducibility and robustness of DL models in mental state decoding.
Collapse
Affiliation(s)
- Armin W Thomas
- Stanford Data Science, Stanford University, Stanford, CA, USA; Department of Psychology, Stanford University, Stanford, CA, USA.
| | - Christopher Ré
- Department of Computer Science, Stanford University, Stanford, CA, USA
| | - Russell A Poldrack
- Stanford Data Science, Stanford University, Stanford, CA, USA; Department of Psychology, Stanford University, Stanford, CA, USA
| |
Collapse
|
28
|
Accelerated functional brain aging in major depressive disorder: evidence from a large scale fMRI analysis of Chinese participants. Transl Psychiatry 2022; 12:397. [PMID: 36130921 PMCID: PMC9492670 DOI: 10.1038/s41398-022-02162-y] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 09/04/2022] [Accepted: 09/08/2022] [Indexed: 11/12/2022] Open
Abstract
Major depressive disorder (MDD) is one of the most common mental health conditions that has been intensively investigated for its association with brain atrophy and mortality. Recent studies suggest that the deviation between the predicted and the chronological age can be a marker of accelerated brain aging to characterize MDD. However, current conclusions are usually drawn based on structural MRI information collected from Caucasian participants. The universality of this biomarker needs to be further validated by subjects with different ethnic/racial backgrounds and by different types of data. Here we make use of the REST-meta-MDD, a large scale resting-state fMRI dataset collected from multiple cohort participants in China. We develop a stacking machine learning model based on 1101 healthy controls, which estimates a subject's chronological age from fMRI with promising accuracy. The trained model is then applied to 1276 MDD patients from 24 sites. We observe that MDD patients exhibit a +4.43 years (p < 0.0001, Cohen's d = 0.31, 95% CI: 2.23-3.88) higher brain-predicted age difference (brain-PAD) compared to controls. In the MDD subgroup, we observe a statistically significant +2.09 years (p < 0.05, Cohen's d = 0.134525) brain-PAD in antidepressant users compared to medication-free patients. The statistical relationship observed is further checked by three different machine learning algorithms. The positive brain-PAD observed in participants in China confirms the presence of accelerated brain aging in MDD patients. The utilization of functional brain connectivity for age estimation verifies existing findings from a new dimension.
Collapse
|
29
|
Wilms M, Bannister JJ, Mouches P, MacDonald ME, Rajashekar D, Langner S, Forkert ND. Invertible Modeling of Bidirectional Relationships in Neuroimaging With Normalizing Flows: Application to Brain Aging. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:2331-2347. [PMID: 35324436 DOI: 10.1109/tmi.2022.3161947] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Many machine learning tasks in neuroimaging aim at modeling complex relationships between a brain's morphology as seen in structural MR images and clinical scores and variables of interest. A frequently modeled process is healthy brain aging for which many image-based brain age estimation or age-conditioned brain morphology template generation approaches exist. While age estimation is a regression task, template generation is related to generative modeling. Both tasks can be seen as inverse directions of the same relationship between brain morphology and age. However, this view is rarely exploited and most existing approaches train separate models for each direction. In this paper, we propose a novel bidirectional approach that unifies score regression and generative morphology modeling and we use it to build a bidirectional brain aging model. We achieve this by defining an invertible normalizing flow architecture that learns a probability distribution of 3D brain morphology conditioned on age. The use of full 3D brain data is achieved by deriving a manifold-constrained formulation that models morphology variations within a low-dimensional subspace of diffeomorphic transformations. This modeling idea is evaluated on a database of MR scans of more than 5000 subjects. The evaluation results show that our bidirectional brain aging model (1) accurately estimates brain age, (2) is able to visually explain its decisions through attribution maps and counterfactuals, (3) generates realistic age-specific brain morphology templates, (4) supports the analysis of morphological variations, and (5) can be utilized for subject-specific brain aging simulation.
Collapse
|
30
|
Mouches P, Wilms M, Bannister JJ, Aulakh A, Langner S, Forkert ND. An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors. Front Aging Neurosci 2022; 14:941864. [PMID: 36072481 PMCID: PMC9441743 DOI: 10.3389/fnagi.2022.941864] [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] [Subscribe] [Scholar Register] [Received: 05/11/2022] [Accepted: 08/05/2022] [Indexed: 12/02/2022] Open
Abstract
The brain age gap (BAG) has been shown to capture accelerated brain aging patterns and might serve as a biomarker for several neurological diseases. Moreover, it was also shown that it captures other biological information related to modifiable cardiovascular risk factors. Previous studies have explored statistical relationships between the BAG and cardiovascular risk factors. However, none of those studies explored causal relationships between the BAG and cardiovascular risk factors. In this work, we employ causal structure discovery techniques and define a Bayesian network to model the assumed causal relationships between the BAG, estimated using morphometric T1-weighted magnetic resonance imaging brain features from 2025 adults, and several cardiovascular risk factors. This setup allows us to not only assess observed conditional probability distributions of the BAG given cardiovascular risk factors, but also to isolate the causal effect of each cardiovascular risk factor on BAG using causal inference. Results demonstrate the feasibility of the proposed causal analysis approach by illustrating intuitive causal relationships between variables. For example, body-mass-index, waist-to-hip ratio, smoking, and alcohol consumption were found to impact the BAG, with the greatest impact for obesity markers resulting in higher chances of developing accelerated brain aging. Moreover, the findings show that causal effects differ from correlational effects, demonstrating the importance of accounting for variable relationships and confounders when evaluating the information captured by a biomarker. Our work demonstrates the feasibility and advantages of using causal analyses instead of purely correlation-based and univariate statistical analyses in the context of brain aging and related problems.
Collapse
Affiliation(s)
- Pauline Mouches
- Biomedical Engineering Program, University of Calgary, Calgary, AB, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Department of Radiology, University of Calgary, Calgary, AB, Canada
| | - Matthias Wilms
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Department of Radiology, University of Calgary, Calgary, AB, Canada
- Alberta Children’s Hospital Research Institute, University of Calgary, Calgary, AB, Canada
| | - Jordan J. Bannister
- Biomedical Engineering Program, University of Calgary, Calgary, AB, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Department of Radiology, University of Calgary, Calgary, AB, Canada
| | - Agampreet Aulakh
- Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
| | - Sönke Langner
- Institute for Diagnostic Radiology and Neuroradiology, Rostock University Medical Center, Rostock, Germany
| | - Nils D. Forkert
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Department of Radiology, University of Calgary, Calgary, AB, Canada
- Alberta Children’s Hospital Research Institute, University of Calgary, Calgary, AB, Canada
| |
Collapse
|
31
|
Leonardsen EH, Peng H, Kaufmann T, Agartz I, Andreassen OA, Celius EG, Espeseth T, Harbo HF, Høgestøl EA, Lange AMD, Marquand AF, Vidal-Piñeiro D, Roe JM, Selbæk G, Sørensen Ø, Smith SM, Westlye LT, Wolfers T, Wang Y. Deep neural networks learn general and clinically relevant representations of the ageing brain. Neuroimage 2022; 256:119210. [PMID: 35462035 PMCID: PMC7614754 DOI: 10.1016/j.neuroimage.2022.119210] [Citation(s) in RCA: 29] [Impact Index Per Article: 14.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2021] [Revised: 03/16/2022] [Accepted: 04/11/2022] [Indexed: 12/17/2022] Open
Abstract
The discrepancy between chronological age and the apparent age of the brain based on neuroimaging data - the brain age delta - has emerged as a reliable marker of brain health. With an increasing wealth of data, approaches to tackle heterogeneity in data acquisition are vital. To this end, we compiled raw structural magnetic resonance images into one of the largest and most diverse datasets assembled (n=53542), and trained convolutional neural networks (CNNs) to predict age. We achieved state-of-the-art performance on unseen data from unknown scanners (n=2553), and showed that higher brain age delta is associated with diabetes, alcohol intake and smoking. Using transfer learning, the intermediate representations learned by our model complemented and partly outperformed brain age delta in predicting common brain disorders. Our work shows we can achieve generalizable and biologically plausible brain age predictions using CNNs trained on heterogeneous datasets, and transfer them to clinical use cases.
Collapse
Affiliation(s)
- Esten H Leonardsen
- Department of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway.
| | - Han Peng
- Wellcome Centre for Integrative Neuroimaging (WIN FMRIB), University of Oxford, Oxford, OX3 9DU, United Kingdom
| | - Tobias Kaufmann
- Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychiatry and Psychotherapy, Tübingen Center for Mental Health, University of Tübingen, Germany
| | - Ingrid Agartz
- Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychiatric Research, Diakonhjemmet Hospital, Oslo, Norway; Centre for Psychiatry Research, Department of Clinical Neuroscience, Karolinska Institutet & Stockholm Health Care Services, Stockholm County Council, Stockholm, Sweden
| | - Ole A Andreassen
- Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway
| | - Elisabeth Gulowsen Celius
- Department of Neurology, Oslo University Hospital, Norway; Institute of Clinical Medicine, University of Oslo, Oslo, Norway
| | - Thomas Espeseth
- Department of Psychology, University of Oslo, Oslo, Norway; Department of Psychology, Bjørknes University College, Oslo, Norway
| | - Hanne F Harbo
- Department of Neurology, Oslo University Hospital, Norway; Institute of Clinical Medicine, University of Oslo, Oslo, Norway
| | - Einar A Høgestøl
- Department of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Neurology, Oslo University Hospital, Norway
| | - Ann-Marie de Lange
- Department of Psychology, University of Oslo, Oslo, Norway; LREN, Centre for Research in Neurosciences-Department of Clinical Neurosciences, CHUV and University of Lausanne, Lausanne, Switzerland; Department of Psychiatry, University of Oxford, Oxford, UK
| | - Andre F Marquand
- Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Centre, Nijmegen, Netherlands
| | | | - James M Roe
- Department of Psychology, University of Oslo, Oslo, Norway
| | - Geir Selbæk
- Norwegian National Advisory Unit on Aging and Health, Vestfold Hospital Trust, Tønsberg, Norway; Department of Geriatric Medicine, Oslo University Hospital, Oslo, Norway
| | | | - Stephen M Smith
- Wellcome Centre for Integrative Neuroimaging (WIN FMRIB), University of Oxford, Oxford, OX3 9DU, United Kingdom
| | - Lars T Westlye
- Department of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; KG Jebsen Center for Neurodevelopmental Disorders, University of Oslo, Oslo, Norway
| | - Thomas Wolfers
- Department of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway
| | - Yunpeng Wang
- Department of Psychology, University of Oslo, Oslo, Norway
| |
Collapse
|
32
|
Hofmann SM, Beyer F, Lapuschkin S, Goltermann O, Loeffler M, Müller KR, Villringer A, Samek W, Witte AV. Towards the Interpretability of Deep Learning Models for Multi-modal Neuroimaging: Finding Structural Changes of the Ageing Brain. Neuroimage 2022; 261:119504. [PMID: 35882272 DOI: 10.1016/j.neuroimage.2022.119504] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2022] [Revised: 07/15/2022] [Accepted: 07/21/2022] [Indexed: 11/17/2022] Open
Abstract
Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with Layer-wise Relevance Propagation (LRP) to detect which brain features contribute to BA. Trained on magnetic resonance imaging (MRI) data of a population-based study (n=2637, 18-82 years), our models estimated age accurately based on single and multiple modalities, regionally restricted and whole-brain images (mean absolute errors 3.37-3.86 years). We find that BA estimates capture aging at both small and large-scale changes, revealing gross enlargements of ventricles and subarachnoid spaces, as well as white matter lesions, and atrophies that appear throughout the brain. Divergence from expected aging reflected cardiovascular risk factors and accelerated aging was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-aging in healthy and at-risk individuals throughout adulthood.
Collapse
Affiliation(s)
- Simon M Hofmann
- Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany; Department of Artificial Intelligence, Fraunhofer Institute Heinrich Hertz, 10587 Berlin, Germany; Clinic for Cognitive Neurology, University of Leipzig Medical Center, 04103 Leipzig, Germany.
| | - Frauke Beyer
- Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany; Clinic for Cognitive Neurology, University of Leipzig Medical Center, 04103 Leipzig, Germany
| | - Sebastian Lapuschkin
- Department of Artificial Intelligence, Fraunhofer Institute Heinrich Hertz, 10587 Berlin, Germany
| | - Ole Goltermann
- Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany; Max Planck School of Cognition, 04103 Leipzig, Germany; Institute of Systems Neuroscience, University Medical Center Hamburg-Eppendorf, Germany
| | | | - Klaus-Robert Müller
- Department of Electrical Engineering and Computer Science, Technical University Berlin, 10623 Berlin, Germany; Department of Artificial Intelligence, Korea University, 02841 Seoul, Korea (the Republic of); Brain Team, Google Research, 10117 Berlin, Germany; Max Planck Institute for Informatics, 66123 Saarbrücken, Germany; BIFOLD - Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany
| | - Arno Villringer
- Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany; Clinic for Cognitive Neurology, University of Leipzig Medical Center, 04103 Leipzig, Germany; MindBrainBody Institute, Berlin School of Mind and Brain, Humboldt-Universität zu Berlin, 10099 Berlin, Germany; Center for Stroke Research, Charité - Universitätsmedizin Berlin, 10117 Berlin, Germany
| | - Wojciech Samek
- Department of Artificial Intelligence, Fraunhofer Institute Heinrich Hertz, 10587 Berlin, Germany; Department of Electrical Engineering and Computer Science, Technical University Berlin, 10623 Berlin, Germany; BIFOLD - Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany
| | - A Veronica Witte
- Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany; Clinic for Cognitive Neurology, University of Leipzig Medical Center, 04103 Leipzig, Germany
| |
Collapse
|
33
|
Battineni G, Hossain MA, Chintalapudi N, Amenta F. A Survey on the Role of Artificial Intelligence in Biobanking Studies: A Systematic Review. Diagnostics (Basel) 2022; 12:1179. [PMID: 35626333 PMCID: PMC9140088 DOI: 10.3390/diagnostics12051179] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Revised: 05/02/2022] [Accepted: 05/06/2022] [Indexed: 02/04/2023] Open
Abstract
Introduction: In biobanks, participants' biological samples are stored for future research. The application of artificial intelligence (AI) involves the analysis of data and the prediction of any pathological outcomes. In AI, models are used to diagnose diseases as well as classify and predict disease risks. Our research analyzed AI's role in the development of biobanks in the healthcare industry, systematically. Methods: The literature search was conducted using three digital reference databases, namely PubMed, CINAHL, and WoS. Guidelines for preferred reporting elements for systematic reviews and meta-analyses (PRISMA)-2020 in conducting the systematic review were followed. The search terms included "biobanks", "AI", "machine learning", and "deep learning", as well as combinations such as "biobanks with AI", "deep learning in the biobanking field", and "recent advances in biobanking". Only English-language papers were included in the study, and to assess the quality of selected works, the Newcastle-Ottawa scale (NOS) was used. The good quality range (NOS ≥ 7) is only considered for further review. Results: A literature analysis of the above entries resulted in 239 studies. Based on their relevance to the study's goal, research characteristics, and NOS criteria, we included 18 articles for reviewing. In the last decade, biobanks and artificial intelligence have had a relatively large impact on the medical system. Interestingly, UK biobanks account for the highest percentage of high-quality works, followed by Qatar, South Korea, Singapore, Japan, and Denmark. Conclusions: Translational bioinformatics probably represent a future leader in precision medicine. AI and machine learning applications to biobanking research may contribute to the development of biobanks for the utility of health services and citizens.
Collapse
Affiliation(s)
- Gopi Battineni
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy; (M.A.H.); (N.C.); (F.A.)
| | | | | | | |
Collapse
|
34
|
Le Goallec A, Diai S, Collin S, Prost JB, Vincent T, Patel CJ. Using deep learning to predict abdominal age from liver and pancreas magnetic resonance images. Nat Commun 2022; 13:1979. [PMID: 35418184 PMCID: PMC9007982 DOI: 10.1038/s41467-022-29525-9] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2021] [Accepted: 03/18/2022] [Indexed: 11/24/2022] Open
Abstract
With age, the prevalence of diseases such as fatty liver disease, cirrhosis, and type two diabetes increases. Approaches to both predict abdominal age and identify risk factors for accelerated abdominal age may ultimately lead to advances that will delay the onset of these diseases. We build an abdominal age predictor by training convolutional neural networks to predict abdominal age (or "AbdAge") from 45,552 liver magnetic resonance images [MRIs] and 36,784 pancreas MRIs (R-Squared = 73.3 ± 0.6; mean absolute error = 2.94 ± 0.03 years). Attention maps show that the prediction is driven by both liver and pancreas anatomical features, and surrounding organs and tissue. Abdominal aging is a complex trait, partially heritable (h_g2 = 26.3 ± 1.9%), and associated with 16 genetic loci (e.g. in PLEKHA1 and EFEMP1), biomarkers (e.g body impedance), clinical phenotypes (e.g, chest pain), diseases (e.g. hypertension), environmental (e.g smoking), and socioeconomic (e.g education, income) factors.
Collapse
Affiliation(s)
- Alan Le Goallec
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, 02115, USA.,Department of Systems, Synthetic and Quantitative Biology, Harvard University, Cambridge, MA, 02118, USA
| | - Samuel Diai
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, 02115, USA
| | - Sasha Collin
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, 02115, USA
| | - Jean-Baptiste Prost
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, 02115, USA
| | - Théo Vincent
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, 02115, USA
| | - Chirag J Patel
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, 02115, USA.
| |
Collapse
|
35
|
Wrigglesworth J, Harding IH, Ward P, Woods RL, Storey E, Fitzgibbon B, Egan G, Murray A, Shah RC, Trevaks RE, Ward S, McNeil JJ, Ryan J. Factors Influencing Change in Brain-Predicted Age Difference in a Cohort of Healthy Older Individuals. J Alzheimers Dis Rep 2022; 6:163-176. [PMID: 35591948 PMCID: PMC9108625 DOI: 10.3233/adr-220011] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2022] [Accepted: 03/09/2022] [Indexed: 12/11/2022] Open
Abstract
Background There is considerable variability in the rate at which we age biologically, and the brain is particularly susceptible to the effects of aging. Objective We examined the test-retest reliability of brain age at one- and three-year intervals and identified characteristics that predict the longitudinal change in brain-predicted age difference (brain-PAD, defined by deviations of brain age from chronological age). Methods T1-weighted magnetic resonance images were acquired at three timepoints from 497 community-dwelling adults (73.8±3.5 years at baseline, 48% were female). Brain age was estimated from whole brain volume, using a publicly available algorithm trained on an independent dataset. Linear mixed models were used, adjusting for sex, age, and age2. Results Excellent retest reliability of brain age was observed over one and three years. We identified a significant sex difference in brain-PAD, where a faster rate of brain aging (worsening in brain age relative to chronological age) was observed in men, and this finding replicated in secondary analyses. The effect size, however, was relatively weak, equivalent to 0.16 years difference per year. A higher score in physical health related quality of life and verbal fluency were associated with a faster rate of brain aging, while depression was linked to a slower rate of brain aging, but these findings were not robust. Conclusion Our study provides consistent evidence that older men have slightly faster brain atrophy than women. Given the sparsity of longitudinal research on brain age in older populations, future prospective studies are needed to confirm our findings.
Collapse
Affiliation(s)
- Jo Wrigglesworth
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Ian H. Harding
- Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia
- Department of Neuroscience, Central Clinical School, Monash University, Melbourne, VIC, Australia
| | - Phillip Ward
- Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia
- Turner Institute for Brain and Mental Health, Monash University, Clayton, VIC, Australia
- Australian Research Council Centre of Excellence for Integrative Brain Function, Clayton, VIC, Australia
| | - Robyn L. Woods
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Elsdon Storey
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Bernadette Fitzgibbon
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Gary Egan
- Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia
- Australian Research Council Centre of Excellence for Integrative Brain Function, Clayton, VIC, Australia
| | - Anne Murray
- Berman Center for Outcomes & Clinical Research, Hennepin Healthcare Research Institute, Minneapolis, MN, USA
- Department of Medicine, Division of Geriatrics, Hennepin Healthcare, University of Minnesota, Minneapolis, MN, USA
| | - Raj C. Shah
- Department of Family Medicine and the Rush Alzheimer’s Disease Center, Rush University Medical Center, Chicago, IL, USA
| | - Ruth E. Trevaks
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Stephanie Ward
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
- Centre for Healthy Brain Ageing (CHeBA), University of New South Wales, Sydney, NSW, Australia
- Department of Geriatric Medicine, Prince of Wales Hospital, Randwick, NSW, Australia
| | - John J. McNeil
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Joanne Ryan
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - on behalf of the ASPREE investigator group
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
- Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia
- Department of Neuroscience, Central Clinical School, Monash University, Melbourne, VIC, Australia
- Turner Institute for Brain and Mental Health, Monash University, Clayton, VIC, Australia
- Australian Research Council Centre of Excellence for Integrative Brain Function, Clayton, VIC, Australia
- Berman Center for Outcomes & Clinical Research, Hennepin Healthcare Research Institute, Minneapolis, MN, USA
- Department of Medicine, Division of Geriatrics, Hennepin Healthcare, University of Minnesota, Minneapolis, MN, USA
- Department of Family Medicine and the Rush Alzheimer’s Disease Center, Rush University Medical Center, Chicago, IL, USA
- Centre for Healthy Brain Ageing (CHeBA), University of New South Wales, Sydney, NSW, Australia
- Department of Geriatric Medicine, Prince of Wales Hospital, Randwick, NSW, Australia
| |
Collapse
|
36
|
C Monte-Rubio G, Segura B, P Strafella A, van Eimeren T, Ibarretxe-Bilbao N, Diez-Cirarda M, Eggers C, Lucas-Jiménez O, Ojeda N, Peña J, Ruppert MC, Sala-Llonch R, Theis H, Uribe C, Junque C. Parameters from site classification to harmonize MRI clinical studies: Application to a multi-site Parkinson's disease dataset. Hum Brain Mapp 2022; 43:3130-3142. [PMID: 35305545 PMCID: PMC9188966 DOI: 10.1002/hbm.25838] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2021] [Revised: 02/10/2022] [Accepted: 03/07/2022] [Indexed: 11/10/2022] Open
Abstract
Multi‐site MRI datasets are crucial for big data research. However, neuroimaging studies must face the batch effect. Here, we propose an approach that uses the predictive probabilities provided by Gaussian processes (GPs) to harmonize clinical‐based studies. A multi‐site dataset of 216 Parkinson's disease (PD) patients and 87 healthy subjects (HS) was used. We performed a site GP classification using MRI data. The outcomes estimated from this classification, redefined like Weighted HARMonization PArameters (WHARMPA), were used as regressors in two different clinical studies: A PD versus HS machine learning classification using GP, and a VBM comparison (FWE‐p < .05, k = 100). Same studies were also conducted using conventional Boolean site covariates, and without information about site belonging. The results from site GP classification provided high scores, balanced accuracy (BAC) was 98.39% for grey matter images. PD versus HS classification performed better when the WHARMPA were used to harmonize (BAC = 78.60%; AUC = 0.90) than when using the Boolean site information (BAC = 56.31%; AUC = 0.71) and without it (BAC = 57.22%; AUC = 0.73). The VBM analysis harmonized using WHARMPA provided larger and more statistically robust clusters in regions previously reported in PD than when the Boolean site covariates or no corrections were added to the model. In conclusion, WHARMPA might encode global site‐effects quantitatively and allow the harmonization of data. This method is user‐friendly and provides a powerful solution, without complex implementations, to clean the analyses by removing variability associated with the differences between sites.
Collapse
Affiliation(s)
- Gemma C Monte-Rubio
- Institute of Neurosciences, University of Barcelona, Barcelona, Catalonia, Spain.,Medical Psychology Unit, Department of Medicine, University of Barcelona, Barcelona, Catalonia, Spain
| | - Barbara Segura
- Institute of Neurosciences, University of Barcelona, Barcelona, Catalonia, Spain.,Medical Psychology Unit, Department of Medicine, University of Barcelona, Barcelona, Catalonia, Spain.,Institute of Biomedical Research August Pi i Sunyer (IDIBAPS), Barcelona, Catalonia, Spain.,Centro de Investigación Biomédica en Red sobre Enfermedades Neurodegenerativas (CIBERNED: CB06/05/0018-ISCIII) Barcelona, Barcelona, Catalonia, Spain
| | - Antonio P Strafella
- Edmond J. Safra Parkinson Disease Program & Morton and Gloria Shulman Movement Disorder Unit, Neurology Division, University Health Network, University of Toronto, Toronto, Ontario, Canada.,Krembil Brain Institute, University Health Network, University of Toronto, Toronto, Ontario, Canada.,Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health University of Toronto, Toronto, Ontario, Canada
| | - Thilo van Eimeren
- Department of Nuclear Medicine, University of Cologne, Cologne, Germany.,Department of Neurology, University of Cologne, Cologne, Germany
| | - Naroa Ibarretxe-Bilbao
- Department of Psychology, Faculty of Health Sciences, University of Deusto, Bilbao, Spain
| | - Maria Diez-Cirarda
- Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health University of Toronto, Toronto, Ontario, Canada
| | - Carsten Eggers
- Department of Neurology, University Hospital Marburg, Marburg, Germany.,Center for Mind, Brain and Behavior - CMBB, Universities Marburg and Gießen, Marburg and Gießen, Germany.,Department of Neurology, Knappschaftskrankenhaus Bottrop, Bottrop, Germany
| | - Olaia Lucas-Jiménez
- Department of Psychology, Faculty of Health Sciences, University of Deusto, Bilbao, Spain
| | - Natalia Ojeda
- Department of Psychology, Faculty of Health Sciences, University of Deusto, Bilbao, Spain
| | - Javier Peña
- Department of Psychology, Faculty of Health Sciences, University of Deusto, Bilbao, Spain
| | - Marina C Ruppert
- Department of Neurology, University Hospital Marburg, Marburg, Germany.,Center for Mind, Brain and Behavior - CMBB, Universities Marburg and Gießen, Marburg and Gießen, Germany
| | - Roser Sala-Llonch
- Institute of Neurosciences, University of Barcelona, Barcelona, Catalonia, Spain.,Institute of Biomedical Research August Pi i Sunyer (IDIBAPS), Barcelona, Catalonia, Spain.,Department of Biomedicine, University of Barcelona, Barcelona, Catalonia, Spain.,Centro de Investigación Biomédica en Red en Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN), Barcelona, Catalonia, Spain
| | - Hendrik Theis
- Department of Neurology, University of Cologne, Cologne, Germany
| | - Carme Uribe
- Institute of Neurosciences, University of Barcelona, Barcelona, Catalonia, Spain.,Medical Psychology Unit, Department of Medicine, University of Barcelona, Barcelona, Catalonia, Spain.,Institute of Biomedical Research August Pi i Sunyer (IDIBAPS), Barcelona, Catalonia, Spain.,Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health University of Toronto, Toronto, Ontario, Canada
| | - Carme Junque
- Institute of Neurosciences, University of Barcelona, Barcelona, Catalonia, Spain.,Medical Psychology Unit, Department of Medicine, University of Barcelona, Barcelona, Catalonia, Spain.,Institute of Biomedical Research August Pi i Sunyer (IDIBAPS), Barcelona, Catalonia, Spain.,Centro de Investigación Biomédica en Red sobre Enfermedades Neurodegenerativas (CIBERNED: CB06/05/0018-ISCIII) Barcelona, Barcelona, Catalonia, Spain
| |
Collapse
|
37
|
Mouches P, Wilms M, Rajashekar D, Langner S, Forkert ND. Multimodal biological brain age prediction using magnetic resonance imaging and angiography with the identification of predictive regions. Hum Brain Mapp 2022; 43:2554-2566. [PMID: 35138012 PMCID: PMC9057090 DOI: 10.1002/hbm.25805] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 01/24/2022] [Accepted: 01/25/2022] [Indexed: 02/06/2023] Open
Abstract
Biological brain age predicted using machine learning models based on high-resolution imaging data has been suggested as a potential biomarker for neurological and cerebrovascular diseases. In this work, we aimed to develop deep learning models to predict the biological brain age using structural magnetic resonance imaging and angiography datasets from a large database of 2074 adults (21-81 years). Since different imaging modalities can provide complementary information, combining them might allow to identify more complex aging patterns, with angiography data, for instance, showing vascular aging effects complementary to the atrophic brain tissue changes seen in T1-weighted MRI sequences. We used saliency maps to investigate the contribution of cortical, subcortical, and arterial structures to the prediction. Our results show that combining T1-weighted and angiography MR data led to a significantly improved brain age prediction accuracy, with a mean absolute error of 3.85 years comparing the predicted and chronological age. The most predictive brain regions included the lateral sulcus, the fourth ventricle, and the amygdala, while the brain arteries contributing the most to the prediction included the basilar artery, the middle cerebral artery M2 segments, and the left posterior cerebral artery. Our study proposes a framework for brain age prediction using multimodal imaging, which gives accurate predictions and allows identifying the most predictive regions for this task, which can serve as a surrogate for the brain regions that are most affected by aging.
Collapse
Affiliation(s)
- Pauline Mouches
- Department of Radiology, University of Calgary, Calgary, Alberta, Canada.,Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.,Biomedical Engineering Program, University of Calgary, Calgary, Alberta, Canada
| | - Matthias Wilms
- Department of Radiology, University of Calgary, Calgary, Alberta, Canada.,Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.,Alberta Children's Hospital Research Institute, University of Calgary, Calgary, Alberta, Canada
| | - Deepthi Rajashekar
- Department of Radiology, University of Calgary, Calgary, Alberta, Canada.,Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.,Biomedical Engineering Program, University of Calgary, Calgary, Alberta, Canada
| | - Sönke Langner
- Institute for Diagnostic Radiology and Neuroradiology, Rostock University Medical Center, Rostock, Germany
| | - Nils D Forkert
- Department of Radiology, University of Calgary, Calgary, Alberta, Canada.,Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.,Alberta Children's Hospital Research Institute, University of Calgary, Calgary, Alberta, Canada
| |
Collapse
|
38
|
Zhou Z, Srinivasan D, Li H, Abdulkadir A, Shou H, Davatzikos C, Fan Y. Harmonization of multi-site functional connectivity measures in tangent space improves brain age prediction. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2022; 12036:1203608. [PMID: 36845412 PMCID: PMC9951555 DOI: 10.1117/12.2611557] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
Brain age prediction based on functional magnetic resonance imaging (fMRI) data has the potential to serve as a biomarker for quantifying brain health. To predict the brain age based on fMRI data robustly and accurately, we curated a large dataset (n = 4259) of fMRI scans from seven different data acquisition sites and computed personalized functional connectivity measures at multiple scales from each subject's fMRI scan. Particularly, we computed personalized large-scale functional networks and generated functional connectivity measures at multiple scales to characterize each fMRI scan. To account for inter-site effects on the functional connectivity measures, we harmonized the functional connectivity measures in their tangent space and then built brain age prediction models on the harmonized functional connectivity measures. We compared the brain age prediction models with alternatives that were built on the functional connectivity measures computed at a single scale and harmonized using different strategies. Comparison results have demonstrated that the best brain age prediction performance was achieved by the prediction model built on the multi-scale functional connectivity measures that were harmonized in tangent space, indicating that multi-scale functional connectivity measures provided richer information than those computed at any single scales and the harmonization of functional connectivity measures in tangent space improved the brain age prediction.
Collapse
Affiliation(s)
- Zhen Zhou
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Department of Radiology, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| | - Dhivya Srinivasan
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Department of Radiology, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| | - Hongming Li
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Department of Radiology, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| | - Ahmed Abdulkadir
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Department of Radiology, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| | - Haochang Shou
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Penn Statistics in Imaging and Visualization Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Department of Radiology, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| | - Yong Fan
- Center for Biomedical Image Computing and Analytics (CBICA), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
- Department of Radiology, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA, 19104
| |
Collapse
|
39
|
Guo Y, Yang X, Yuan Z, Qiu J, Lu W. A comparison between diffusion tensor imaging and generalized q-sampling imaging in the age prediction of healthy adults via machine learning approaches. J Neural Eng 2022; 19. [PMID: 35038689 DOI: 10.1088/1741-2552/ac4bfe] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2021] [Accepted: 01/17/2022] [Indexed: 11/12/2022]
Abstract
OBJECTIVE Brain age, which is predicted using neuroimaging data, has become an important biomarker in aging research. This study applied diffusion tensor imaging (DTI) and generalized q-sampling imaging (GQI) model to predict age respectively, with the purpose of evaluating which diffusion model is more accurate in estimating age and revealing age-related changes in the brain. APPROACH Diffusion MRI data of 125 subjects from two sites were collected. Fractional anisotropy (FA) and quantitative anisotropy (QA) from the two diffusion models were calculated and were used as features of machine learning models. Sequential backward elimination algorithm was used for feature selection. Six machine learning approaches including linear regression, ridge regression, support vector regression (SVR) with linear kernel, quadratic kernel and radial basis function (RBF) kernel and feedforward neural network were used to predict age using FA and QA features respectively. MAIN RESULTS Age predictions using FA features were more accurate than predictions using QA features for all the 6 machine learning algorithms. Post-hoc analysis revealed that FA was more sensitive to age-related white matter alterations in the brain. In addition, SVR with RBF kernel based on FA features achieved better performances than the competing algorithms with MAE ranging from 7.74 to 10.54, MSE ranging from 87.79 to 150.86, and nMSE ranging from 0.05 to 0.14 Significance: FA from DTI model was more suitable than QA from GQI model in age prediction. FA metric was more sensitive to age-related white matter changes in the brain and FA of several brain regions could be used as white matter biomarkers in aging.
Collapse
Affiliation(s)
- Yingying Guo
- Department of Radiology, Shandong First Medical University, No.619 Changcheng Road, Jinan, Shandong, 250000, CHINA
| | - Xi Yang
- Pennsylvania State University, Department of Mathematics, The Pennsylvania State University, University Park, PA, 16801, USA, State College, Pennsylvania, 16801, UNITED STATES
| | - Zilong Yuan
- Hubei Cancer Hospital, No. 116 South Zhuodaoquan Road, Wuhan, Hubei, 430079, CHINA
| | - Jianfeng Qiu
- Shandong Medical University, No. 6699 Qingdao Road, Jinan, 250100, CHINA
| | - Weizhao Lu
- Department of Radiology, Taishan Medical University, No.619 Changcheng Road, Taian, Shandong, 271016, CHINA
| |
Collapse
|
40
|
Wrigglesworth J, Yaacob N, Ward P, Woods RL, McNeil J, Storey E, Egan G, Murray A, Shah RC, Jamadar SD, Trevaks R, Ward S, Harding IH, Ryan J. Brain-predicted age difference is associated with cognitive processing in later-life. Neurobiol Aging 2022; 109:195-203. [PMID: 34775210 PMCID: PMC8832483 DOI: 10.1016/j.neurobiolaging.2021.10.007] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2021] [Revised: 10/07/2021] [Accepted: 10/12/2021] [Indexed: 01/08/2023]
Abstract
Brain age is a neuroimaging-based biomarker of aging. This study examined whether the difference between brain age and chronological age (brain-PAD) is associated with cognitive function at baseline and longitudinally. Participants were relatively healthy, predominantly white community-dwelling older adults (n = 531, aged ≥70 years), with high educational attainment (61% ≥12 years) and socioeconomic status (59% ≥75th percentile). Brain age was estimated from T1-weighted magnetic resonance images using an algorithm by Cole et al., 2018. After controlling for age, gender, education, depression and body mass index, brain-PAD was negatively associated with psychomotor speed (Symbol Digit Modalities Test) at baseline (Bonferroni p < 0.006), but was not associated with baseline verbal fluency (Controlled Oral Word Association Test), delayed recall (Hopkins Learning Test Revised), or general cognitive status (Mini-Mental State Examination). Baseline brain-PAD was not associated with 3-year change in cognition (Bonferroni p > 0.006). These findings indicate that even in relatively healthy older people, accelerated brain aging is associated with worse psychomotor speed, but future longitudinal research into changes in brain-PAD is needed.
Collapse
Affiliation(s)
- Jo Wrigglesworth
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| | - Nurathifah Yaacob
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| | - Phillip Ward
- Monash Biomedical Imaging, Monash University, Melbourne, Victoria, Australia; Turner Institute for Brain and Mental Health, Monash University, Melbourne, Victoria, Australia; Australian Research Council Centre of Excellence for Integrative Brain Function, Clayton, Victoria, Australia
| | - Robyn L Woods
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| | - John McNeil
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| | - Elsdon Storey
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| | - Gary Egan
- Monash Biomedical Imaging, Monash University, Melbourne, Victoria, Australia; Australian Research Council Centre of Excellence for Integrative Brain Function, Clayton, Victoria, Australia
| | - Anne Murray
- Berman Center for Outcomes & Clinical Research, Hennepin Healthcare Research Institute, Minneapolis, MN, USA; Department of Medicine, Division of Geriatrics, Hennepin Healthcare, University of Minnesota, Minneapolis, MN, USA
| | - Raj C Shah
- Department of Family Medicine and the Rush Alzheimer's Disease Centre, Rush University Medical Centre, Chicago, IL, USA
| | - Sharna D Jamadar
- Monash Biomedical Imaging, Monash University, Melbourne, Victoria, Australia; Turner Institute for Brain and Mental Health, Monash University, Melbourne, Victoria, Australia; Australian Research Council Centre of Excellence for Integrative Brain Function, Clayton, Victoria, Australia
| | - Ruth Trevaks
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| | - Stephanie Ward
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia; Centre for Healthy Brain Ageing (CHeBA), University of New South Wales, Sydney, New South Wales, Australia; Department of Geriatric Medicine, Prince of Wales Hospital, Randwick, New South Wales, Australia
| | - Ian H Harding
- Monash Biomedical Imaging, Monash University, Melbourne, Victoria, Australia; Department of Neuroscience, Central Clinical School, Monash University, Melbourne, Victoria, Australia
| | - Joanne Ryan
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
| |
Collapse
|
41
|
He S, Grant PE, Ou Y. Global-Local Transformer for Brain Age Estimation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:213-224. [PMID: 34460370 PMCID: PMC9746186 DOI: 10.1109/tmi.2021.3108910] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/13/2023]
Abstract
Deep learning can provide rapid brain age estimation based on brain magnetic resonance imaging (MRI). However, most studies use one neural network to extract the global information from the whole input image, ignoring the local fine-grained details. In this paper, we propose a global-local transformer, which consists of a global-pathway to extract the global-context information from the whole input image and a local-pathway to extract the local fine-grained details from local patches. The fine-grained information from the local patches are fused with the global-context information by the attention mechanism, inspired by the transformer, to estimate the brain age. We evaluate the proposed method on 8 public datasets with 8,379 healthy brain MRIs with the age range of 0-97 years. 6 datasets are used for cross-validation and 2 datasets are used for evaluating the generality. Comparing with other state-of-the-art methods, the proposed global-local transformer reduces the mean absolute error of the estimated ages to 2.70 years and increases the correlation coefficient of the estimated age and the chronological age to 0.9853. In addition, our proposed method provides regional information of which local patches are most informative for brain age estimation. Our source code is available on: https://github.com/shengfly/global-local-transformer.
Collapse
|
42
|
Popescu SG, Glocker B, Sharp DJ, Cole JH. Local Brain-Age: A U-Net Model. Front Aging Neurosci 2021; 13:761954. [PMID: 34966266 PMCID: PMC8710767 DOI: 10.3389/fnagi.2021.761954] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2021] [Accepted: 11/03/2021] [Indexed: 11/13/2022] Open
Abstract
We propose a new framework for estimating neuroimaging-derived "brain-age" at a local level within the brain, using deep learning. The local approach, contrary to existing global methods, provides spatial information on anatomical patterns of brain ageing. We trained a U-Net model using brain MRI scans from n = 3,463 healthy people (aged 18-90 years) to produce individualised 3D maps of brain-predicted age. When testing on n = 692 healthy people, we found a median (across participant) mean absolute error (within participant) of 9.5 years. Performance was more accurate (MAE around 7 years) in the prefrontal cortex and periventricular areas. We also introduce a new voxelwise method to reduce the age-bias when predicting local brain-age "gaps." To validate local brain-age predictions, we tested the model in people with mild cognitive impairment or dementia using data from OASIS3 (n = 267). Different local brain-age patterns were evident between healthy controls and people with mild cognitive impairment or dementia, particularly in subcortical regions such as the accumbens, putamen, pallidum, hippocampus, and amygdala. Comparing groups based on mean local brain-age over regions-of-interest resulted in large effects sizes, with Cohen's d values >1.5, for example when comparing people with stable and progressive mild cognitive impairment. Our local brain-age framework has the potential to provide spatial information leading to a more mechanistic understanding of individual differences in patterns of brain ageing in health and disease.
Collapse
Affiliation(s)
- Sebastian G. Popescu
- Biomedical Image Analysis Group, Imperial College London, London, United Kingdom
- Computational, Cognitive & Clinical Neuroimaging Laboratory, Imperial College London, London, United Kingdom
| | - Ben Glocker
- Biomedical Image Analysis Group, Imperial College London, London, United Kingdom
| | - David J. Sharp
- Computational, Cognitive & Clinical Neuroimaging Laboratory, Imperial College London, London, United Kingdom
- Care Research & Technology Centre, UK Dementia Research Institute, London, United Kingdom
| | - James H. Cole
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom
- Dementia Research Centre, Queen Square Institute of Neurology, University College London, London, United Kingdom
| |
Collapse
|
43
|
Cheng J, Liu Z, Guan H, Wu Z, Zhu H, Jiang J, Wen W, Tao D, Liu T. Brain Age Estimation From MRI Using Cascade Networks With Ranking Loss. IEEE TRANSACTIONS ON MEDICAL IMAGING 2021; 40:3400-3412. [PMID: 34086565 DOI: 10.1109/tmi.2021.3085948] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/16/2023]
Abstract
Chronological age of healthy people is able to be predicted accurately using deep neural networks from neuroimaging data, and the predicted brain age could serve as a biomarker for detecting aging-related diseases. In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data. Compared with existing methods, TSAN has the following improvements. First, TSAN uses a two-stage cascade network architecture, where the first-stage network estimates a rough brain age, then the second-stage network estimates the brain age more accurately from the discretized brain age by the first-stage network. Second, to our knowledge, TSAN is the first work to apply novel ranking losses in brain age estimation, together with the traditional mean square error (MSE) loss. Third, densely connected paths are used to combine feature maps with different scales. The experiments with 6586 MRIs showed that TSAN could provide accurate brain age estimation, yielding mean absolute error (MAE) of 2.428 and Pearson's correlation coefficient (PCC) of 0.985, between the estimated and chronological ages. Furthermore, using the brain age gap between brain age and chronological age as a biomarker, Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) can be distinguished from healthy control (HC) subjects by support vector machine (SVM). Classification AUC in AD/HC and MCI/HC was 0.904 and 0.823, respectively. It showed that brain age gap is an effective biomarker associated with risk of dementia, and has potential for early-stage dementia risk screening. The codes and trained models have been released on GitHub: https://github.com/Milan-BUAA/TSAN-brain-age-estimation.
Collapse
|
44
|
Hepp T, Blum D, Armanious K, Schölkopf B, Stern D, Yang B, Gatidis S. Uncertainty estimation and explainability in deep learning-based age estimation of the human brain: Results from the German National Cohort MRI study. Comput Med Imaging Graph 2021; 92:101967. [PMID: 34392229 DOI: 10.1016/j.compmedimag.2021.101967] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2021] [Revised: 07/20/2021] [Accepted: 07/23/2021] [Indexed: 01/22/2023]
Abstract
Brain ageing is a complex neurobiological process associated with morphological changes that can be assessed on MRI scans. Recently, Deep learning (DL)-based approaches have been proposed for the prediction of chronological brain age from MR images yielding high accuracy. These approaches, however, usually do not address quantification of uncertainty and, therefore, intrinsic physiological variability. Considering uncertainty is essential for the interpretation of the difference between predicted and chronological age. In addition, DL-based models lack in explainability compared to classical approaches like voxel-based morphometry. In this study, we aim to address both, modeling uncertainty and providing visual explanations to explore physiological patterns in brain ageing. T1-weighted brain MRI datasets of 10691 participants of the German National Cohort Study, drawn from the general population, were included in this study (chronological age from 20 to 72 years). A regression model based on a 3D Convolutional Neural Network taking into account aleatoric noise was implemented for global as well as regional brain age estimation. We observed high overall accuracy of global brain age estimation with a mean absolute error of 3.2 ± 2.5 years and mean uncertainty of 2.9 ± 0.6 years. Regional brain age estimation revealed higher estimation accuracy and lower uncertainty in central compared to peripheral brain regions. Visual explanations illustrating the importance of brain sub-regions were generated using Grad-CAM: the derived saliency maps showed a high relevance of the lateral and third ventricles, the insular lobe as well as parts of the basal ganglia and the internal capsule.
Collapse
Affiliation(s)
- Tobias Hepp
- Max Planck Institute for Intelligent Systems, Max Planck Ring 4, 72076 Tuebingen, Germany; Department of Diagnostic and Interventional Radiology, University Hospital Tuebingen, Hoppe-Seyler-Strasse 3, 72076 Tuebingen, Germany.
| | - Dominik Blum
- Department of Nuclear Medicine and Clinical Molecular Imaging, University Hospital Tuebingen, Otfried-Müller-Strasse 14, 72076 Tuebingen, Germany
| | - Karim Armanious
- Institute of Signal Processing and System Theory, University of Stuttgart, Pfaffenwaldring 47, 70569 Stuttgart, Germany
| | - Bernhard Schölkopf
- Max Planck Institute for Intelligent Systems, Max Planck Ring 4, 72076 Tuebingen, Germany
| | - Darko Stern
- Gottfried Schatz Research Center: Biophysics, Medical University of Graz, Neue Stiftingtalstrasse 6, 8010 Graz, Austria
| | - Bin Yang
- Institute of Signal Processing and System Theory, University of Stuttgart, Pfaffenwaldring 47, 70569 Stuttgart, Germany
| | - Sergios Gatidis
- Max Planck Institute for Intelligent Systems, Max Planck Ring 4, 72076 Tuebingen, Germany; Department of Diagnostic and Interventional Radiology, University Hospital Tuebingen, Hoppe-Seyler-Strasse 3, 72076 Tuebingen, Germany
| |
Collapse
|
45
|
Fisch L, Leenings R, Winter NR, Dannlowski U, Gaser C, Cole JH, Hahn T. Editorial: Predicting Chronological Age From Structural Neuroimaging: The Predictive Analytics Competition 2019. Front Psychiatry 2021; 12:710932. [PMID: 34421686 PMCID: PMC8374100 DOI: 10.3389/fpsyt.2021.710932] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Accepted: 07/09/2021] [Indexed: 11/13/2022] Open
Affiliation(s)
- Lukas Fisch
- Institute for Translational Psychiatry, University of Münster, Münster, Germany
| | - Ramona Leenings
- Institute for Translational Psychiatry, University of Münster, Münster, Germany
| | - Nils R. Winter
- Institute for Translational Psychiatry, University of Münster, Münster, Germany
| | - Udo Dannlowski
- Institute for Translational Psychiatry, University of Münster, Münster, Germany
| | - Christian Gaser
- Department of Psychiatry and Psychotherapy, Jena University Hospital, Jena, Germany
- Department of Neurology, Jena University Hospital, Jena, Germany
| | - James H. Cole
- Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Computational, Cognitive and Clinical Neuroimaging Laboratory, Department King's College, London, United Kingdom
| | - Tim Hahn
- Institute for Translational Psychiatry, University of Münster, Münster, Germany
| |
Collapse
|
46
|
Ball G, Kelly CE, Beare R, Seal ML. Individual variation underlying brain age estimates in typical development. Neuroimage 2021; 235:118036. [PMID: 33838267 DOI: 10.1016/j.neuroimage.2021.118036] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2020] [Revised: 03/19/2021] [Accepted: 03/26/2021] [Indexed: 12/14/2022] Open
Abstract
Typical brain development follows a protracted trajectory throughout childhood and adolescence. Deviations from typical growth trajectories have been implicated in neurodevelopmental and psychiatric disorders. Recently, the use of machine learning algorithms to model age as a function of structural or functional brain properties has been used to examine advanced or delayed brain maturation in healthy and clinical populations. Termed 'brain age', this approach often relies on complex, nonlinear models that can be difficult to interpret. In this study, we use model explanation methods to examine the cortical features that contribute to brain age modelling on an individual basis. In a large cohort of n = 768 typically-developing children (aged 3-21 years), we build models of brain development using three different machine learning approaches. We employ SHAP, a model-agnostic technique to identify sample-specific feature importance, to identify regional cortical metrics that explain errors in brain age prediction. We find that, on average, brain age prediction and the cortical features that explain model predictions are consistent across model types and reflect previously reported patterns of regions brain development. However, while several regions are found to contribute to brain age prediction error, we find little spatial correspondence between individual estimates of feature importance, even when matched for age, sex and brain age prediction error. We also find no association between brain age error and cognitive performance in this typically-developing sample. Overall, this study shows that, while brain age estimates based on cortical development are relatively robust and consistent across model types and preprocessing strategies, significant between-subject variation exists in the features that explain erroneous brain age predictions on an individual level.
Collapse
Affiliation(s)
- Gareth Ball
- Developmental Imaging, Murdoch Children's Research Institute, The Royal Children's Hospital, Melbourne, 3052 VIC, Australia; Department of Paediatrics, University of Melbourne, Australia.
| | - Claire E Kelly
- Developmental Imaging, Murdoch Children's Research Institute, The Royal Children's Hospital, Melbourne, 3052 VIC, Australia; Victorian Infant Brain Studies (VIBeS), Murdoch Children's Research Institute, Australia
| | - Richard Beare
- Developmental Imaging, Murdoch Children's Research Institute, The Royal Children's Hospital, Melbourne, 3052 VIC, Australia
| | - Marc L Seal
- Developmental Imaging, Murdoch Children's Research Institute, The Royal Children's Hospital, Melbourne, 3052 VIC, Australia; Department of Paediatrics, University of Melbourne, Australia
| |
Collapse
|
47
|
Gong W, Beckmann CF, Vedaldi A, Smith SM, Peng H. Optimising a Simple Fully Convolutional Network for Accurate Brain Age Prediction in the PAC 2019 Challenge. Front Psychiatry 2021; 12:627996. [PMID: 34040552 PMCID: PMC8141616 DOI: 10.3389/fpsyt.2021.627996] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/10/2020] [Accepted: 04/12/2021] [Indexed: 11/24/2022] Open
Abstract
Brain age prediction from brain MRI scans not only helps improve brain ageing modelling generally, but also provides benchmarks for predictive analysis methods. Brain-age delta, which is the difference between a subject's predicted age and true age, has become a meaningful biomarker for the health of the brain. Here, we report the details of our brain age prediction models and results in the Predictive Analysis Challenge 2019. The aim of the challenge was to use T1-weighted brain MRIs to predict a subject's age in multicentre datasets. We apply a lightweight deep convolutional neural network architecture, Simple Fully Convolutional Neural Network (SFCN), and combined several techniques including data augmentation, transfer learning, model ensemble, and bias correction for brain age prediction. The model achieved first place in both of the two objectives in the PAC 2019 brain age prediction challenge: Mean absolute error (MAE) = 2.90 years without bias removal (Second Place = 3.09 yrs; Third Place = 3.33 yrs), and MAE = 2.95 years with bias removal, leading by a large margin (Second Place = 3.80 yrs; Third Place = 3.92 yrs).
Collapse
Affiliation(s)
- Weikang Gong
- Wellcome Centre for Integrative Neuroimaging (WIN Centre for Functional MRI of the Brain), University of Oxford, Oxford, United Kingdom
| | - Christian F Beckmann
- Wellcome Centre for Integrative Neuroimaging (WIN Centre for Functional MRI of the Brain), University of Oxford, Oxford, United Kingdom.,Donders Institute for Brain, Cognition and Behaviour, Radboud University Nijmegen, Nijmegen, Netherlands
| | - Andrea Vedaldi
- Visual Geometry Group, University of Oxford, Oxford, United Kingdom
| | - Stephen M Smith
- Wellcome Centre for Integrative Neuroimaging (WIN Centre for Functional MRI of the Brain), University of Oxford, Oxford, United Kingdom
| | - Han Peng
- Wellcome Centre for Integrative Neuroimaging (WIN Centre for Functional MRI of the Brain), University of Oxford, Oxford, United Kingdom.,Donders Institute for Brain, Cognition and Behaviour, Radboud University Nijmegen, Nijmegen, Netherlands.,Visual Geometry Group, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
48
|
Kolbeinsson A, Filippi S, Panagakis Y, Matthews PM, Elliott P, Dehghan A, Tzoulaki I. Accelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders. Sci Rep 2020; 10:19940. [PMID: 33203906 PMCID: PMC7672070 DOI: 10.1038/s41598-020-76518-z] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2020] [Accepted: 10/19/2020] [Indexed: 02/07/2023] Open
Abstract
Brain structure in later life reflects both influences of intrinsic aging and those of lifestyle, environment and disease. We developed a deep neural network model trained on brain MRI scans of healthy people to predict "healthy" brain age. Brain regions most informative for the prediction included the cerebellum, hippocampus, amygdala and insular cortex. We then applied this model to data from an independent group of people not stratified for health. A phenome-wide association analysis of over 1,410 traits in the UK Biobank with differences between the predicted and chronological ages for the second group identified significant associations with over 40 traits including diseases (e.g., type I and type II diabetes), disease risk factors (e.g., increased diastolic blood pressure and body mass index), and poorer cognitive function. These observations highlight relationships between brain and systemic health and have implications for understanding contributions of the latter to late life dementia risk.
Collapse
Affiliation(s)
- Arinbjörn Kolbeinsson
- Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, St Mary's Campus, Norfolk Place, London, W2 1PG, UK.
- MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, W2 1PG, UK.
| | - Sarah Filippi
- Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, St Mary's Campus, Norfolk Place, London, W2 1PG, UK
- MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, W2 1PG, UK
- Department of Mathematics, Imperial College London, London, SW7 2AZ, UK
| | - Yannis Panagakis
- Department of Computing, Imperial College London, London, SW7 2AZ, UK
- Department of Informatics and Telecommunications, University of Athens, Athens, Greece
| | - Paul M Matthews
- Department of Brain Sciences, Burlington Danes Building, Imperial College London, London, W12 0NN, UK
- UK Dementia Research Institute at Imperial College, Imperial College London, London, UK
| | - Paul Elliott
- Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, St Mary's Campus, Norfolk Place, London, W2 1PG, UK
- MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, W2 1PG, UK
- UK Dementia Research Institute at Imperial College, Imperial College London, London, UK
- National Institute for Health Research, Imperial Biomedical Research Centre, Imperial College London, Exhibition Road, London, SW7 2AZ, UK
- Health Data Research UK London at Imperial College London, Exhibition Road, London, SW7 2AZ, UK
| | - Abbas Dehghan
- Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, St Mary's Campus, Norfolk Place, London, W2 1PG, UK
- MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, W2 1PG, UK
- UK Dementia Research Institute at Imperial College, Imperial College London, London, UK
| | - Ioanna Tzoulaki
- Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, St Mary's Campus, Norfolk Place, London, W2 1PG, UK
- MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, W2 1PG, UK
- UK Dementia Research Institute at Imperial College, Imperial College London, London, UK
- Department of Hygiene and Epidemiology, University of Ioannina Medical School, Ioannina, Greece
| |
Collapse
|