1
|
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] [What about the content of this article? (0)] [Affiliation(s)] [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
|
2
|
Salimi Y, Domingo-Fernández D, Hofmann-Apitius M, Birkenbihl C. Data-Driven Thresholding Statistically Biases ATN Profiling across Cohort Datasets. J Prev Alzheimers Dis 2024; 11:185-195. [PMID: 38230732 PMCID: PMC10995057 DOI: 10.14283/jpad.2023.100] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Accepted: 07/02/2023] [Indexed: 01/18/2024]
Abstract
BACKGROUND While the amyloid/tau/neurodegeneration (ATN) framework has found wide application in Alzheimer's disease research, it is unclear if thresholds obtained using distinct thresholding methods are concordant within the same dataset and interchangeable across cohorts. OBJECTIVES To investigate the robustness of data-driven thresholding methods and ATN profiling across cohort datasets. DESIGN AND SETTING We evaluated the impact of thresholding methods on ATN profiles by applying five commonly-used methodologies across cohort datasets. We assessed the generalizability of disease patterns discovered within ATN profiles by clustering individuals from different cohorts who were assigned to the same ATN profile. PARTICIPANTS AND MEASUREMENTS Participants with available CSF amyloid-β 1-42, phosphorylated tau, and total tau measurements were included from eleven AD cohort studies. RESULTS We observed high variability among obtained ATN thresholds, both across methods and datasets that impacted the resulting profile assignments of participants significantly. Clustering participants from different cohorts within the same ATN category indicated that identified disease patterns were comparable across most cohorts and biases introduced through distinct thresholding and data representations remained insignificant in most ATN profiles. CONLUSION Thresholding method selection is a decision of statistical relevance that will inevitably bias the resulting profiling and affect its sensitivity and specificity. Thresholds are likely not directly interchangeable between independent cohorts. To apply the ATN framework as an actionable and robust profiling scheme, a comprehensive understanding of the impact of used thresholding methods, their statistical implications, and a validation of results is crucial.
Collapse
Affiliation(s)
- Y. Salimi
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
- Schloß Birlinghoven, Sankt Augustin, 53757 Germany
| | - D. Domingo-Fernández
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
| | - M. Hofmann-Apitius
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
| | - C. Birkenbihl
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
- Schloß Birlinghoven, Sankt Augustin, 53757 Germany
| | - the Alzheimer’s Disease Neuroimaging Initiative
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
- Schloß Birlinghoven, Sankt Augustin, 53757 Germany
| | - the Japanese Alzheimer’s Disease Neuroimaging Initiative
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
- Schloß Birlinghoven, Sankt Augustin, 53757 Germany
| | - the Alzheimer’s Disease Repository Without Borders Investigators
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
- Schloß Birlinghoven, Sankt Augustin, 53757 Germany
| | - the European Prevention of Alzheimer’s Disease (EPAD) Consortium
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53757 Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 53115 Germany
- Schloß Birlinghoven, Sankt Augustin, 53757 Germany
| |
Collapse
|