1
|
Aghaei A, Ebrahimi Moghaddam M. Brain age gap estimation using attention-based ResNet method for Alzheimer's disease detection. Brain Inform 2024; 11:16. [PMID: 38833039 DOI: 10.1186/s40708-024-00230-1] [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: 11/03/2023] [Accepted: 05/27/2024] [Indexed: 06/06/2024] Open
Abstract
This study investigates the correlation between brain age and chronological age in healthy individuals using brain MRI images, aiming to identify potential biomarkers for neurodegenerative diseases like Alzheimer's. To achieve this, a novel attention-based ResNet method, 3D-Attention-Resent-SVR, is proposed to accurately estimate brain age and distinguish between Cognitively Normal (CN) and Alzheimer's disease (AD) individuals by computing the brain age gap (BAG). Unlike conventional methods, which often rely on single datasets, our approach addresses potential biases by employing four datasets for training and testing. The results, based on a combined dataset from four public sources comprising 3844 data points, demonstrate the model's efficacy with a mean absolute error (MAE) of 2.05 for brain age gap estimation. Moreover, the model's generalizability is showcased by training on three datasets and testing on a separate one, yielding a remarkable MAE of 2.4. Furthermore, leveraging BAG as the sole biomarker, our method achieves an accuracy of 92% and an AUC of 0.87 in Alzheimer's disease detection on the ADNI dataset. These findings underscore the potential of our approach in assisting with early detection and disease monitoring, emphasizing the strong correlation between BAG and AD.
Collapse
Affiliation(s)
- Atefe Aghaei
- Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran
| | | |
Collapse
|
2
|
Zhang Y, Xie R, Beheshti I, Liu X, Zheng G, Wang Y, Zhang Z, Zheng W, Yao Z, Hu B. Improving brain age prediction with anatomical feature attention-enhanced 3D-CNN. Comput Biol Med 2024; 169:107873. [PMID: 38181606 DOI: 10.1016/j.compbiomed.2023.107873] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Revised: 11/17/2023] [Accepted: 12/17/2023] [Indexed: 01/07/2024]
Abstract
Currently, significant progress has been made in predicting brain age from structural Magnetic Resonance Imaging (sMRI) data using deep learning techniques. However, despite the valuable structural information they contain, the traditional engineering features known as anatomical features have been largely overlooked in this context. To address this issue, we propose an attention-based network design that integrates anatomical and deep convolutional features, leveraging an anatomical feature attention (AFA) module to effectively capture salient anatomical features. In addition, we introduce a fully convolutional network, which simplifies the extraction of deep convolutional features and overcomes the high computational memory requirements associated with deep learning. Our approach outperforms several widely-used models on eight publicly available datasets (n = 2501), with a mean absolute error (MAE) of 2.20 years in predicting brain age. Comparisons with deep learning models lacking the AFA module demonstrate that our fusion model effectively improves overall performance. These findings provide a promising approach for combining anatomical and deep convolutional features from sMRI data to predict brain age, with potential applications in clinical diagnosis and treatment, particularly for populations with age-related cognitive decline or neurological disorders.
Collapse
Affiliation(s)
- Yu Zhang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China
| | - Rui Xie
- Department of Psychiatric, Tianshui Third People's Hospital, Tianshui, 741000, China
| | - Iman Beheshti
- Department of Human Anatomy and Cell Science, University of Manitoba, Canada
| | - Xia Liu
- School of Computer Science, Qinghai Normal University, Xining, Qinghai Province, China
| | - Guowei Zheng
- School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China
| | - Yin Wang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China
| | - Zhenwen Zhang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China
| | - Weihao Zheng
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China.
| | - Zhijun Yao
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China.
| | - Bin Hu
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China; School of Medical Technology, Beijing Institute of Technology, China; CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, China; Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors, Chinese Academy of Sciences, China.
| |
Collapse
|
3
|
Soumya Kumari LK, Sundarrajan R. A review on brain age prediction models. Brain Res 2024; 1823:148668. [PMID: 37951563 DOI: 10.1016/j.brainres.2023.148668] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Revised: 10/23/2023] [Accepted: 11/06/2023] [Indexed: 11/14/2023]
Abstract
Brain age in neuroimaging has emerged over the last decade and reflects the estimated age based on the brain MRI scan from a person. As a person ages, their brain structure will change, and these changes will be exclusive to males and females and will differ for each. White matter and grey matter density have a deeper relationship with brain aging. Hence, if the white matter and grey matter concentrations vary, the rate at which the brain ages will also vary. Neurodegenerative illnesses can be detected using the biomarker known as brain age. The development of deep learning has made it possible to analyze structural neuroimaging data in new ways, notably by predicting brain ages. We introduce the techniques and possible therapeutic uses of brain age prediction in this cutting-edge review. Creating a machine learning regression model to analyze age-related changes in brain structure among healthy individuals is a typical procedure in studies focused on brain aging. Subsequently, this model is employed to forecast the aging of brains in new individuals. The concept of the "brain-age gap" refers to the difference between an individual's predicted brain age and their actual chronological age. This score may serve as a gauge of the general state of the brain's health while also reflecting neuroanatomical disorders. It may help differential diagnosis, prognosis, and therapy decisions as well as early identification of brain-based illnesses. The following is a summary of the many forecasting techniques utilized over the past 11 years to estimate brain age. The study's conundrums and potential outcomes of the brain age predicted by current models will both be covered.
Collapse
Affiliation(s)
- L K Soumya Kumari
- Computer Science Engineering, Mohandas College of Engineering and Technology, Anad, India.
| | - R Sundarrajan
- Information Technology, School of Computing, Kalasalingam Academy of Research and Education, India.
| |
Collapse
|
4
|
Dörfel RP, Arenas‐Gomez JM, Fisher PM, Ganz M, Knudsen GM, Svensson JE, Plavén‐Sigray P. Prediction of brain age using structural magnetic resonance imaging: A comparison of accuracy and test-retest reliability of publicly available software packages. Hum Brain Mapp 2023; 44:6139-6148. [PMID: 37843020 PMCID: PMC10619370 DOI: 10.1002/hbm.26502] [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: 05/04/2023] [Revised: 08/14/2023] [Accepted: 09/08/2023] [Indexed: 10/17/2023] Open
Abstract
Brain age prediction algorithms using structural magnetic resonance imaging (MRI) aim to assess the biological age of the human brain. The difference between a person's chronological age and the estimated brain age is thought to reflect deviations from a normal aging trajectory, indicating a slower or accelerated biological aging process. Several pre-trained software packages for predicting brain age are publicly available. In this study, we perform a comparison of such packages with respect to (1) predictive accuracy, (2) test-retest reliability, and (3) the ability to track age progression over time. We evaluated the six brain age prediction packages: brainageR, DeepBrainNet, brainage, ENIGMA, pyment, and mccqrnn. The accuracy and test-retest reliability were assessed on MRI data from 372 healthy people aged between 18.4 and 86.2 years (mean 38.7 ± 17.5 years). All packages showed significant correlations between predicted brain age and chronological age (r = 0.66-0.97, p < 0.001), with pyment displaying the strongest correlation. The mean absolute error was between 3.56 (pyment) and 9.54 years (ENIGMA). brainageR, pyment, and mccqrnn were superior in terms of reliability (ICC values between 0.94-0.98), as well as predicting age progression over a longer time span. Of the six packages, pyment and brainageR consistently showed the highest accuracy and test-retest reliability.
Collapse
Affiliation(s)
- Ruben P. Dörfel
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
- Centre for Psychiatry Research, Department of Clinical NeuroscienceKarolinska Institutet & Stockholm Health Care Services, Region StockholmStockholmSweden
| | - Joan M. Arenas‐Gomez
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
| | - Patrick M. Fisher
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
- Department of Drug Design and PharmacologyUniversity of CopenhagenCopenhagenDenmark
| | - Melanie Ganz
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
- Department of Computer ScienceUniversity of CopenhagenCopenhagenDenmark
| | - Gitte M. Knudsen
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
- Department of Clinical MedicineUniversity of CopenhagenCopenhagenDenmark
| | - Jonas E. Svensson
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
- Centre for Psychiatry Research, Department of Clinical NeuroscienceKarolinska Institutet & Stockholm Health Care Services, Region StockholmStockholmSweden
| | - Pontus Plavén‐Sigray
- Neurobiology Research UnitCopenhagen University Hospital, RigshospitaletCopenhagenDenmark
- Centre for Psychiatry Research, Department of Clinical NeuroscienceKarolinska Institutet & Stockholm Health Care Services, Region StockholmStockholmSweden
| |
Collapse
|
5
|
Sone D, Beheshti I. Neuroimaging-Based Brain Age Estimation: A Promising Personalized Biomarker in Neuropsychiatry. J Pers Med 2022; 12:jpm12111850. [PMID: 36579560 PMCID: PMC9695293 DOI: 10.3390/jpm12111850] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Revised: 11/01/2022] [Accepted: 11/01/2022] [Indexed: 11/10/2022] Open
Abstract
It is now possible to estimate an individual's brain age via brain scans and machine-learning models. This validated technique has opened up new avenues for addressing clinical questions in neurology, and, in this review, we summarize the many clinical applications of brain-age estimation in neuropsychiatry and general populations. We first provide an introduction to typical neuroimaging modalities, feature extraction methods, and machine-learning models that have been used to develop a brain-age estimation framework. We then focus on the significant findings of the brain-age estimation technique in the field of neuropsychiatry as well as the usefulness of the technique for addressing clinical questions in neuropsychiatry. These applications may contribute to more timely and targeted neuropsychiatric therapies. Last, we discuss the practical problems and challenges described in the literature and suggest some future research directions.
Collapse
Affiliation(s)
- Daichi Sone
- Department of Psychiatry, Jikei University School of Medicine, Tokyo 105-8461, Japan
- Correspondence: ; Tel.: +81-03-3433
| | - Iman Beheshti
- Department of Human Anatomy and Cell Science, University of Manitoba, Winnipeg, MB R3E 3P5, Canada
| |
Collapse
|
6
|
Tesli N, Bell C, Hjell G, Fischer-Vieler T, I Maximov I, Richard G, Tesli M, Melle I, Andreassen OA, Agartz I, Westlye LT, Friestad C, Haukvik UK, Rokicki J. The age of violence: Mapping brain age in psychosis and psychopathy. Neuroimage Clin 2022; 36:103181. [PMID: 36088844 PMCID: PMC9474919 DOI: 10.1016/j.nicl.2022.103181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2022] [Revised: 07/31/2022] [Accepted: 08/30/2022] [Indexed: 12/14/2022]
Abstract
Young chronological age is one of the strongest predictors for antisocial behaviour in the general population and for violent offending in individuals with psychotic disorders. An individual's age can be predicted with high accuracy using neuroimaging and machine-learning. The deviation between predicted and chronological age, i.e., brain age gap (BAG) has been suggested to reflect brain health, likely relating partly to neurodevelopmental and aging-related processes and specific disease mechanisms. Higher BAG has been demonstrated in patients with psychotic disorders. However, little is known about the brain-age in violent offenders with psychosis and the possible associations with psychopathy traits. We estimated brain-age in 782 male individuals using T1-weighted MRI scans. Three machine learning models (random forest, extreme gradient boosting with and without hyper parameter tuning) were first trained and tested on healthy controls (HC, n = 586). The obtained BAGs were compared between HC and age matched violent offenders with psychosis (PSY-V, n = 38), violent offenders without psychosis (NPV, n = 20) and non-violent psychosis patients (PSY-NV, n = 138). We ran additional comparisons between BAG of PSY-V and PSY-NV and associations with Positive and Negative Syndrome Scale (PANSS) total score as a measure of psychosis symptoms. Psychopathy traits in the violence groups were assessed with Psychopathy Checklist-revised (PCL-R) and investigated for associations with BAG. We found significantly higher BAG in PSY-V compared with HC (4.9 years, Cohen'sd = 0.87) and in PSY-NV compared with HC (2.7 years, d = 0.41). Total PCL-R scores were negatively associated with BAG in the violence groups (d = 1.17, p < 0.05). Additionally, there was a positive association between psychosis symptoms and BAG in the psychosis groups (d = 1.12, p < 0.05). While the significant BAG differences related to psychosis and not violence suggest larger BAG for psychosis, the negative associations between BAG and psychopathy suggest a complex interplay with psychopathy traits. This proof-of-concept application of brain age prediction in severe mental disorders with a history of violence and psychopathy traits should be tested and replicated in larger samples.
Collapse
Affiliation(s)
- Natalia Tesli
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway
| | - Christina Bell
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychiatry, Oslo University Hospital, Oslo, Norway
| | - Gabriela Hjell
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychiatry, Østfold Hospital Trust, Graalum, Norway
| | - Thomas Fischer-Vieler
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Division of Mental Health and Addiction, Vestre Viken Hospital Trust, Drammen, Norway
| | - Ivan I Maximov
- Department of Health and Functioning, Western Norway University of Applied Sciences, Bergen, Norway
| | - Genevieve Richard
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway
| | - Martin Tesli
- Department of Mental Disorders, Norwegian Institute of Public Health, Oslo, Norway; Centre of Research and Education in Forensic Psychiatry, Oslo University Hospital, Oslo, Norway
| | - Ingrid Melle
- Norwegian Centre for Mental Disorders Research (NORMENT), Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway; Department of Adult Psychiatry, Institute of Clinical Medicine, University of Oslo, Norway
| | - Ole A Andreassen
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway
| | - Ingrid Agartz
- Norwegian Centre for Mental Disorders Research (NORMENT), 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
| | - Lars T Westlye
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychology, University of Oslo, Oslo, Norway
| | - Christine Friestad
- Centre of Research and Education in Forensic Psychiatry, Oslo University Hospital, Oslo, Norway; University College of Norwegian Correctional Service, Oslo, Norway
| | - Unn K Haukvik
- Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway; Department of Psychiatry, Oslo University Hospital, Oslo, Norway; Centre of Research and Education in Forensic Psychiatry, Oslo University Hospital, Oslo, Norway
| | - Jaroslav Rokicki
- Norwegian Centre for Mental Disorders Research (NORMENT), Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway; Centre of Research and Education in Forensic Psychiatry, Oslo University Hospital, Oslo, Norway.
| |
Collapse
|
7
|
Besson P, Rogalski E, Gill NP, Zhang H, Martersteck A, Bandt SK. Geometric deep learning reveals a structuro-temporal understanding of healthy and pathologic brain aging. Front Aging Neurosci 2022; 14:895535. [PMID: 36081894 PMCID: PMC9445244 DOI: 10.3389/fnagi.2022.895535] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Accepted: 07/27/2022] [Indexed: 11/13/2022] Open
Abstract
Background Brain age has historically been investigated primarily at the whole brain level. The ability to deconstruct the brain into its composite parts and explore brain age at the sub-structure level offers unique advantages. These include the exploration of dynamic and interconnected relationships between different brain structures in healthy and pathologic aging. To achieve this, individual brain structures can be rendered as surface representations on which morphologic analysis is carried out. Combining the advantages of deep learning with the strengths of surface analysis, we investigate the aging process at the individual structure level with the hypothesis being that pathologic aging does not uniformly affect the aging process of individual structures. Methods MRI data, age at scan time and diagnosis of dementia were collected from seven publicly available data repositories. The data from 17,440 unique subjects were collected, representing a total of 26,276 T1-weighted MRI accounting for longitudinal acquisitions. Surfaces were extracted for the cortex and seven subcortical structures. Deep learning networks were trained to estimate a subject's age either using several structures together or a single structure. We conducted a cross-sectional analysis to assess the difference between the predicted and actual ages for all structures between healthy subjects, individuals with mild cognitive impairment (MCI) or Alzheimer's disease dementia (ADD). We then performed a longitudinal analysis to assess the difference in the aging pace for each structure between stable healthy controls and healthy controls converting to either MCI or ADD. Findings Using an independent cohort of healthy subjects, age was well estimated for all structures. Cross-sectional analysis identified significantly larger predicted age for all structures in patients with either MCI and ADD compared to healthy subjects. Longitudinal analysis revealed varying degrees of involvement of individual subcortical structures for both age difference across groups and aging pace across time. These findings were most notable in the whole brain, cortex, hippocampus and amygdala. Conclusion Although similar patterns of abnormal aging were found related to MCI and ADD, the involvement of individual subcortical structures varied greatly and was consistently more pronounced in ADD patients compared to MCI patients.
Collapse
Affiliation(s)
- Pierre Besson
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
- Advanced Neuroimaging and Surgical Epilepsy (ANISE) Lab, Northwestern University, Chicago, IL, United States
| | - Emily Rogalski
- Mesulam Center for Cognitive Neurology and Alzheimer’s Disease, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
- Department of Psychiatry and Behavioral Science, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
| | - Nathan P. Gill
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
| | - Hui Zhang
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
| | - Adam Martersteck
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
- Mesulam Center for Cognitive Neurology and Alzheimer’s Disease, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
- Helen Wills Neuroscience Institute, University of California, Berkeley, Berkeley, CA, United States
| | - S. Kathleen Bandt
- Advanced Neuroimaging and Surgical Epilepsy (ANISE) Lab, Northwestern University, Chicago, IL, United States
- Department of Neurological Surgery, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
| |
Collapse
|