1
|
Johnson R, Li MM, Noori A, Queen O, Zitnik M. Graph Artificial Intelligence in Medicine. Annu Rev Biomed Data Sci 2024; 7:345-368. [PMID: 38749465 DOI: 10.1146/annurev-biodatasci-110723-024625] [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: 06/23/2024]
Abstract
In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data-from patient records to imaging-graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters and with minimal to no retraining. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pretraining, facilitate interactive feedback loops, and foster human-AI collaboration, paving the way toward clinically meaningful predictions.
Collapse
Affiliation(s)
- Ruth Johnson
- Berkowitz Family Living Laboratory, Harvard Medical School, Boston, Massachusetts, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA;
| | - Michelle M Li
- Bioinformatics and Integrative Genomics Program, Harvard Medical School, Boston, Massachusetts, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA;
| | - Ayush Noori
- Department of Computer Science, Harvard John A. Paulson School of Engineering and Applied Sciences, Allston, Massachusetts, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA;
| | - Owen Queen
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA;
| | - Marinka Zitnik
- Harvard Data Science Initiative, Cambridge, Massachusetts, USA
- Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Allston, Massachusetts, USA
- Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA;
| |
Collapse
|
2
|
Gaser C, Kalc P, Cole JH. A perspective on brain-age estimation and its clinical promise. NATURE COMPUTATIONAL SCIENCE 2024:10.1038/s43588-024-00659-8. [PMID: 39048692 DOI: 10.1038/s43588-024-00659-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 06/12/2024] [Indexed: 07/27/2024]
Abstract
Brain-age estimation has gained increased attention in the neuroscientific community owing to its potential use as a biomarker of brain health. The difference between estimated and chronological age based on neuroimaging data enables a unique perspective on brain development and aging, with multiple open questions still remaining in the brain-age research field. This Perspective presents an overview of current advancements in the field and envisions the future evolution of the brain-age framework before its potential deployment in hospital settings.
Collapse
Affiliation(s)
- Christian Gaser
- Structural Brain Mapping Group, Department of Neurology, Jena University Hospital, Jena, Germany.
- Department of Psychiatry and Psychotherapy, Jena University Hospital, Jena, Germany.
- German Centre for Mental Health (DZPG), Jena-Halle-Magdeburg, Jena, Germany.
| | - Polona Kalc
- Structural Brain Mapping Group, Department of Neurology, Jena University Hospital, Jena, Germany
| | - James H Cole
- Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Dementia Research Centre, Queen Square Institute of Neurology, University College London, London, UK
| |
Collapse
|
3
|
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
|
4
|
Peng L, Cai S, Wu Z, Shang H, Zhu X, Li X. MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning. Med Image Anal 2024; 97:103225. [PMID: 38908306 DOI: 10.1016/j.media.2024.103225] [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: 12/16/2023] [Revised: 04/12/2024] [Accepted: 05/27/2024] [Indexed: 06/24/2024]
Abstract
Prompt learning has demonstrated impressive efficacy in the fine-tuning of multimodal large models to a wide range of downstream tasks. Nonetheless, applying existing prompt learning methods for the diagnosis of neurological disorder still suffers from two issues: (i) existing methods typically treat all patches equally, despite the fact that only a small number of patches in neuroimaging are relevant to the disease, and (ii) they ignore the structural information inherent in the brain connection network which is crucial for understanding and diagnosing neurological disorders. To tackle these issues, we introduce a novel prompt learning model by learning graph prompts during the fine-tuning process of multimodal models for diagnosing neurological disorders. Specifically, we first leverage GPT-4 to obtain relevant disease concepts and compute semantic similarity between these concepts and all patches. Secondly, we reduce the weight of irrelevant patches according to the semantic similarity between each patch and disease-related concepts. Moreover, we construct a graph among tokens based on these concepts and employ a graph convolutional network layer to extract the structural information of the graph, which is used to prompt the pre-trained multimodal models for diagnosing neurological disorders. Extensive experiments demonstrate that our method achieves superior performance for neurological disorder diagnosis compared with state-of-the-art methods and validated by clinicians.
Collapse
Affiliation(s)
- Liang Peng
- Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518000, China
| | - Songyue Cai
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
| | - Zongqian Wu
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
| | - Huifang Shang
- Department of Neurology, Laboratory of Neurodegenerative Disorders, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu 610041, China
| | - Xiaofeng Zhu
- Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518000, China.
| | - Xiaoxiao Li
- School of Electrical and Computer Engineering, University of British Columbia, Vancouver BC V6T 1Z4, Canada
| |
Collapse
|
5
|
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
|
6
|
Lv H, Zeng N, Li M, Sun J, Wu N, Xu M, Chen Q, Zhao X, Chen S, Liu W, Li X, Zhao P, Wintermark M, Hui Y, Li J, Wu S, Wang Z. Association between Body Mass Index and Brain Health in Adults: A 16-Year Population-Based Cohort and Mendelian Randomization Study. HEALTH DATA SCIENCE 2024; 4:0087. [PMID: 38500551 PMCID: PMC10944701 DOI: 10.34133/hds.0087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Accepted: 02/26/2024] [Indexed: 03/20/2024]
Abstract
Background: The cumulative effect of body mass index (BMI) on brain health remains ill-defined. The effects of overweight on brain health across different age groups need clarification. We analyzed the effect of cumulative BMI on neuroimaging features of brain health in adults of different ages. Methods: This study was based on a multicenter, community-based cohort study. We modeled the trajectories of BMI over 16 years to evaluate cumulative exposure. Multimodality neuroimaging data were collected once for volumetric measurements of the brain macrostructure, white matter hyperintensity (WMH), and brain microstructure. We used a generalized linear model to evaluate the association between cumulative BMI and neuroimaging features. Two-sample Mendelian randomization analysis was performed using summary level of BMI genetic data from 681,275 individuals and neuroimaging genetic data from 33,224 individuals to analyze the causal relationships. Results: Clinical and neuroimaging data were obtained from 1,074 adults (25 to 83 years). For adults aged under 45 years, brain volume differences in participants with a cumulative BMI of >26.2 kg/m2 corresponded to 12.0 years [95% confidence interval (CI), 3.0 to 20.0] of brain aging. Differences in WMH were statistically substantial for participants aged over 60 years, with a 6.0-ml (95% CI, 1.5 to 10.5) larger volume. Genetic analysis indicated causal relationships between high BMI and smaller gray matter and higher fractional anisotropy in projection fibers. Conclusion: High cumulative BMI is associated with smaller brain volume, larger volume of white matter lesions, and abnormal microstructural integrity. Adults younger than 45 years are suggested to maintain their BMI below 26.2 kg/m2 for better brain health. Trial Registration: This study was registered on clinicaltrials.gov (Clinical Indicators and Brain Image Data: A Cohort Study Based on Kailuan Cohort; No. NCT05453877; https://clinicaltrials.gov/ct2/show/NCT05453877).
Collapse
Affiliation(s)
- Han Lv
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Na Zeng
- Peking University School of Public Health, Beijing 100191, China
| | - Mengyi Li
- Department of General Surgery, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Jing Sun
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Ning Wu
- Department of Medical Imaging Technology,
Capital Medical University Yanjing College, Beijing 101300, China
| | - Mingze Xu
- Center for MRI Research,
Peking University Academy for Advanced Interdisciplinary Studies, Beijing 100871, China
| | - Qian Chen
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Xinyu Zhao
- Clinical Epidemiology and Evidence-based Medicine Unit, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Shuohua Chen
- Department of Cardiology, Kailuan General Hospital, Hebei, Tangshan 063000, China
| | - Wenjuan Liu
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Xiaoshuai Li
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Pengfei Zhao
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| | - Max Wintermark
- Department of Neuroradiology,
The University of Texas MD Anderson Cancer Center, Houston, TX 78701, USA
| | - Ying Hui
- Department of Radiology, Kailuan General Hospital, Hebei, Tangshan 063000, China
| | - Jing Li
- Department of Radiology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine,
Tsinghua University, Beijing, China
| | - Shouling Wu
- Department of Cardiology, Kailuan General Hospital, Hebei, Tangshan 063000, China
| | - Zhenchang Wang
- Department of Radiology, Beijing Friendship Hospital,
Capital Medical University, Beijing 100050, China
| |
Collapse
|
7
|
Lim H, Joo Y, Ha E, Song Y, Yoon S, Shin T. Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network. Bioengineering (Basel) 2024; 11:265. [PMID: 38534539 DOI: 10.3390/bioengineering11030265] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 02/28/2024] [Accepted: 03/01/2024] [Indexed: 03/28/2024] Open
Abstract
Convolutional neural networks (CNNs) have been used widely to predict biological brain age based on brain magnetic resonance (MR) images. However, CNNs focus mainly on spatially local features and their aggregates and barely on the connective information between distant regions. To overcome this issue, we propose a novel multi-hop graph attention (MGA) module that exploits both the local and global connections of image features when combined with CNNs. After insertion between convolutional layers, MGA first converts the convolution-derived feature map into graph-structured data by using patch embedding and embedding-distance-based scoring. Multi-hop connections between the graph nodes are modeled by using the Markov chain process. After performing multi-hop graph attention, MGA re-converts the graph into an updated feature map and transfers it to the next convolutional layer. We combined the MGA module with sSE (spatial squeeze and excitation)-ResNet18 for our final prediction model (MGA-sSE-ResNet18) and performed various hyperparameter evaluations to identify the optimal parameter combinations. With 2788 three-dimensional T1-weighted MR images of healthy subjects, we verified the effectiveness of MGA-sSE-ResNet18 with comparisons to four established, general-purpose CNNs and two representative brain age prediction models. The proposed model yielded an optimal performance with a mean absolute error of 2.822 years and Pearson's correlation coefficient (PCC) of 0.968, demonstrating the potential of the MGA module to improve the accuracy of brain age prediction.
Collapse
Affiliation(s)
- Heejoo Lim
- Division of Mechanical and Biomedical Engineering, Ewha W. University, Seoul 03760, Republic of Korea
- Graduate Program in Smart Factory, Ewha W. University, Seoul 03760, Republic of Korea
| | - Yoonji Joo
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
| | - Eunji Ha
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
| | - Yumi Song
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
- Department of Brain and Cognitive Sciences, Ewha W. University, Seoul 03760, Republic of Korea
| | - Sujung Yoon
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea
- Department of Brain and Cognitive Sciences, Ewha W. University, Seoul 03760, Republic of Korea
| | - Taehoon Shin
- Division of Mechanical and Biomedical Engineering, Ewha W. University, Seoul 03760, Republic of Korea
- Graduate Program in Smart Factory, Ewha W. University, Seoul 03760, Republic of Korea
| |
Collapse
|
8
|
Wu Y, Chen Y, Yang Y, Lin C, Su S, Zhao J, Wu S, Wu G, Liu H, Liu X, Yang Z, Zhang J, Huang B. Predicting brain age using partition modeling strategy and atlas-based attentional enhancement in the Chinese population. Cereb Cortex 2024; 34:bhae030. [PMID: 38342684 DOI: 10.1093/cercor/bhae030] [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: 11/13/2023] [Revised: 01/13/2024] [Accepted: 01/15/2024] [Indexed: 02/13/2024] Open
Abstract
As a biomarker of human brain health during development, brain age is estimated based on subtle differences in brain structure from those under typical developmental. Magnetic resonance imaging (MRI) is a routine diagnostic method in neuroimaging. Brain age prediction based on MRI has been widely studied. However, few studies based on Chinese population have been reported. This study aimed to construct a brain age predictive model for the Chinese population across its lifespan. We developed a partition prediction method based on transfer learning and atlas attention enhancement. The participants were separated into four age groups, and a deep learning model was trained for each group to identify the brain regions most critical for brain age prediction. The Atlas attention-enhancement method was also used to help the models focus only on critical brain regions. The proposed method was validated using 354 participants from domestic datasets. For prediction performance in the testing sets, the mean absolute error was 2.218 ± 1.801 years, and the Pearson correlation coefficient (r) was 0.969, exceeding previous results for wide-range brain age prediction. In conclusion, the proposed method could provide brain age estimation to assist in assessing the status of brain health.
Collapse
Affiliation(s)
- Yingtong Wu
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
- Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Key Laboratory for MRI, Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen 518055, Guangdong Province, China
| | - Yingqian Chen
- Department of Radiology, the First Affiliated Hospital, Sun Yat-sen University, 58 Zhongshan Second Road, Guangzhou 510080, Guangdong Province, China
| | - Yang Yang
- Department of Radiology, Suining Central Hospital, 127 Desheng West Road, Suining 629099, Sichuan Province, China
- Medical Imaging Center of Guizhou Province, Department of Radiology, The Affiliated Hospital of Zunyi Medical University, 149 Dalian Road, Zunyi 563000, Guizhou Province, China
| | - Chuxuan Lin
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
- Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
| | - Shu Su
- Department of Radiology, the First Affiliated Hospital, Sun Yat-sen University, 58 Zhongshan Second Road, Guangzhou 510080, Guangdong Province, China
| | - Jing Zhao
- Department of Radiology, the First Affiliated Hospital, Sun Yat-sen University, 58 Zhongshan Second Road, Guangzhou 510080, Guangdong Province, China
| | - Songxiong Wu
- Radiology Department, Shenzhen University General Hospital and Shenzhen University Clinical Medical Academy, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
| | - Guangyao Wu
- Radiology Department, Shenzhen University General Hospital and Shenzhen University Clinical Medical Academy, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
| | - Heng Liu
- Medical Imaging Center of Guizhou Province, Department of Radiology, The Affiliated Hospital of Zunyi Medical University, 149 Dalian Road, Zunyi 563000, Guizhou Province, China
| | - Xia Liu
- Department of Radiology, Shenzhen Mental Health Center, Shenzhen Kangning Hospital, 1080 Cuizhu Road, Shenzhen 518118, Guangdong Province, China
| | - Zhiyun Yang
- Department of Radiology, the First Affiliated Hospital, Sun Yat-sen University, 58 Zhongshan Second Road, Guangzhou 510080, Guangdong Province, China
| | - Jian Zhang
- Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, 1068 Xueyuan Avenue, Shenzhen 518055, Guangdong Province, China
- School of Pharmaceutical Sciences, Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
| | - Bingsheng Huang
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
- Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen 518060, Guangdong Province, China
| |
Collapse
|
9
|
Dular L, Špiclin Ž. BASE: Brain Age Standardized Evaluation. Neuroimage 2024; 285:120469. [PMID: 38065279 DOI: 10.1016/j.neuroimage.2023.120469] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 10/31/2023] [Accepted: 11/20/2023] [Indexed: 01/13/2024] Open
Abstract
Brain age, most commonly inferred from T1-weighted magnetic resonance images (T1w MRI), is a robust biomarker of brain health and related diseases. Superior accuracy in brain age prediction, often falling within a 2-3 year range, is achieved predominantly through deep neural networks. However, comparing study results is difficult due to differences in datasets, evaluation methodologies and metrics. Addressing this, we introduce Brain Age Standardized Evaluation (BASE), which includes (i) a standardized T1w MRI dataset including multi-site, new unseen site, test-retest and longitudinal data, and an associated (ii) evaluation protocol, including repeated model training and upon based comprehensive set of performance metrics measuring accuracy, robustness, reproducibility and consistency aspects of brain age predictions, and (iii) statistical evaluation framework based on linear mixed-effects models for rigorous performance assessment and cross-comparison. To showcase BASE, we comprehensively evaluate four deep learning based brain age models, appraising their performance in scenarios that utilize multi-site, test-retest, unseen site, and longitudinal T1w brain MRI datasets. Ensuring full reproducibility and application in future studies, we have made all associated data information and code publicly accessible at https://github.com/AralRalud/BASE.git.
Collapse
Affiliation(s)
- Lara Dular
- University of Ljubljana, Faculty of Electrical Engineering, Tržaška cesta 25, Ljubljana, 1000, Slovenia
| | - Žiga Špiclin
- University of Ljubljana, Faculty of Electrical Engineering, Tržaška cesta 25, Ljubljana, 1000, Slovenia.
| |
Collapse
|
10
|
Moon HS, Mahzarnia A, Stout J, Anderson RJ, Badea CT, Badea A. Feature attention graph neural network for estimating brain age and identifying important neural connections in mouse models of genetic risk for Alzheimer's disease. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.12.13.571574. [PMID: 38168445 PMCID: PMC10760088 DOI: 10.1101/2023.12.13.571574] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/05/2024]
Abstract
Alzheimer's disease (AD) remains one of the most extensively researched neurodegenerative disorders due to its widespread prevalence and complex risk factors. Age is a crucial risk factor for AD, which can be estimated by the disparity between physiological age and estimated brain age. To model AD risk more effectively, integrating biological, genetic, and cognitive markers is essential. Here, we utilized mouse models expressing the major APOE human alleles and human nitric oxide synthase 2 to replicate genetic risk for AD and a humanized innate immune response. We estimated brain age employing a multivariate dataset that includes brain connectomes, APOE genotype, subject traits such as age and sex, and behavioral data. Our methodology used Feature Attention Graph Neural Networks (FAGNN) for integrating different data types. Behavioral data were processed with a 2D Convolutional Neural Network (CNN), subject traits with a 1D CNN, brain connectomes through a Graph Neural Network using quadrant attention module. The model yielded a mean absolute error for age prediction of 31.85 days, with a root mean squared error of 41.84 days, outperforming other, reduced models. In addition, FAGNN identified key brain connections involved in the aging process. The highest weights were assigned to the connections between cingulum and corpus callosum, striatum, hippocampus, thalamus, hypothalamus, cerebellum, and piriform cortex. Our study demonstrates the feasibility of predicting brain age in models of aging and genetic risk for AD. To verify the validity of our findings, we compared Fractional Anisotropy (FA) along the tracts of regions with the highest connectivity, the Return-to-Origin Probability (RTOP), Return-to-Plane Probability (RTPP), and Return-to-Axis Probability (RTAP), which showed significant differences between young, middle-aged, and old age groups. Younger mice exhibited higher FA, RTOP, RTAP, and RTPP compared to older groups in the selected connections, suggesting that degradation of white matter tracts plays a critical role in aging and for FAGNN's selections. Our analysis suggests a potential neuroprotective role of APOE2, relative to APOE3 and APOE4, where APOE2 appears to mitigate age-related changes. Our findings highlighted a complex interplay of genetics and brain aging in the context of AD risk modeling.
Collapse
Affiliation(s)
- Hae Sol Moon
- Department of Biomedical Engineering, Duke University, Durham, NC, USA
- Quantitative Imaging and Analysis Laboratory, Department of Radiology, Duke University School of Medicine, Durham, NC, USA
| | - Ali Mahzarnia
- Quantitative Imaging and Analysis Laboratory, Department of Radiology, Duke University School of Medicine, Durham, NC, USA
| | - Jacques Stout
- Quantitative Imaging and Analysis Laboratory, Department of Radiology, Duke University School of Medicine, Durham, NC, USA
| | - Robert J Anderson
- Quantitative Imaging and Analysis Laboratory, Department of Radiology, Duke University School of Medicine, Durham, NC, USA
| | - Cristian T. Badea
- Department of Biomedical Engineering, Duke University, Durham, NC, USA
- Quantitative Imaging and Analysis Laboratory, Department of Radiology, Duke University School of Medicine, Durham, NC, USA
| | - Alexandra Badea
- Department of Biomedical Engineering, Duke University, Durham, NC, USA
- Quantitative Imaging and Analysis Laboratory, Department of Radiology, Duke University School of Medicine, Durham, NC, USA
- Brain Imaging and Analysis Center, Duke University School of Medicine, Durham, NC, USA
- Department of Neurology, Duke University School of Medicine, Durham, NC, USA
| |
Collapse
|
11
|
Wong SB, Tsao Y, Tsai WH, Wang TS, Wu HC, Wang SS. Application of bidirectional long short-term memory network for prediction of cognitive age. Sci Rep 2023; 13:20197. [PMID: 37980387 PMCID: PMC10657465 DOI: 10.1038/s41598-023-47606-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Accepted: 11/16/2023] [Indexed: 11/20/2023] Open
Abstract
Electroencephalography (EEG) measures changes in neuronal activity and can reveal significant changes from infancy to adulthood concomitant with brain maturation, making it a potential physiological marker of brain maturation and cognition. To investigate a promising deep learning tool for EEG classification, we applied the bidirectional long short-term memory (BLSTM) algorithm to analyze EEG data from the pediatric EEG laboratory of Taipei Tzu Chi Hospital. The trained BLSTM model was 86% accurate when identifying EEGs from young children (8 months-6 years) and adolescents (12-20 years). However, there was only a modest classification accuracy (69.3%) when categorizing EEG samples into three age groups (8 months-6 years, 6-12 years, and 12-20 years). For EEG samples from patients with intellectual disability, the prediction accuracy of the trained BLSTM model was 46.4%, which was significantly lower than its accuracy for EEGs from neurotypical patients, indicating that the individual's intelligence plays a major role in the age prediction. This study confirmed that scalp EEG can reflect brain maturation and the BLSTM algorithm is a feasible deep learning tool for the identification of cognitive age. The trained model can potentially be applied to clinical services as a supportive measurement of neurodevelopmental status.
Collapse
Affiliation(s)
- Shi-Bing Wong
- Department of Pediatrics, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan.
- School of Medicine, Tzu Chi University, Hualien, Taiwan.
| | - Yu Tsao
- Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan
| | - Wen-Hsin Tsai
- Department of Pediatrics, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan
- School of Medicine, Tzu Chi University, Hualien, Taiwan
| | - Tzong-Shi Wang
- School of Medicine, Tzu Chi University, Hualien, Taiwan
- Department of Psychiatry, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan
| | - Hsin-Chi Wu
- School of Medicine, Tzu Chi University, Hualien, Taiwan
- Department of Physical Medicine and Rehabilitation, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan
| | - Syu-Siang Wang
- Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan.
| |
Collapse
|