Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer’s disease in patients with mild cognitive symptoms
(2024) In Alzheimer's Research and Therapy 16(1).- Abstract
Background: Predicting future Alzheimer’s disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. Methods: A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four... (More)
Background: Predicting future Alzheimer’s disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. Methods: A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: (1) clinical data only, including demographics, cognitive tests and APOE ε4 status, (2) clinical data plus hippocampal volume, (3) clinical data plus all regional MRI gray matter volumes (N = 68) extracted using FreeSurfer software, (4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. A double cross-validation scheme, with five test folds and for each of those ten validation folds, was used. External evaluation was performed on part of the ADNI dataset, including 108 patients. Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant. Results: In the BioFINDER cohort, 109 patients (33%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC) = 0.85 and four-year cognitive decline was R2 = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R2 = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R2 = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R2 = 0.08). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. In the external evaluation cohort from ADNI, 23 patients (21%) progressed to AD dementia. The results for predicted progression to AD dementia were similar to the results for the BioFINDER test data, while the performance for the cognitive decline was deteriorated. Conclusions: The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.
(Less)
- author
- organization
-
- Computer Vision and Machine Learning (research group)
- LU Profile Area: Natural and Artificial Cognition
- LU Profile Area: Proactive Ageing
- LTH Profile Area: AI and Digitalization
- eSSENCE: The e-Science Collaboration
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- MultiPark: Multidisciplinary research focused on Parkinson´s disease
- MR Physics (research group)
- Clinical Memory Research (research group)
- Medical Radiation Physics, Lund
- Mathematics (Faculty of Engineering)
- Faculty of Engineering, LTH
- LTH Profile Area: Engineering Health
- Mathematical Imaging Group (research group)
- LU Profile Area: Nature-based future solutions
- LU Profile Area: Light and Materials
- Stroke Imaging Research group (research group)
- WCMM-Wallenberg Centre for Molecular Medicine
- Brain Injury After Cardiac Arrest (research group)
- publishing date
- 2024-12
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Alzheimer’s disease, Cognitive decline, Deep learning
- in
- Alzheimer's Research and Therapy
- volume
- 16
- issue
- 1
- article number
- 61
- publisher
- BioMed Central (BMC)
- external identifiers
-
- scopus:85188133123
- pmid:38504336
- ISSN
- 1758-9193
- DOI
- 10.1186/s13195-024-01428-5
- language
- English
- LU publication?
- yes
- id
- 76e37f24-1d57-4977-a24e-1e3225da1d60
- date added to LUP
- 2024-04-03 10:57:57
- date last changed
- 2024-07-10 19:54:31
@article{76e37f24-1d57-4977-a24e-1e3225da1d60, abstract = {{<p>Background: Predicting future Alzheimer’s disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. Methods: A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: (1) clinical data only, including demographics, cognitive tests and APOE ε4 status, (2) clinical data plus hippocampal volume, (3) clinical data plus all regional MRI gray matter volumes (N = 68) extracted using FreeSurfer software, (4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. A double cross-validation scheme, with five test folds and for each of those ten validation folds, was used. External evaluation was performed on part of the ADNI dataset, including 108 patients. Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant. Results: In the BioFINDER cohort, 109 patients (33%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC) = 0.85 and four-year cognitive decline was R<sup>2</sup> = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R<sup>2</sup> = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R<sup>2</sup> = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R<sup>2</sup> = 0.08). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. In the external evaluation cohort from ADNI, 23 patients (21%) progressed to AD dementia. The results for predicted progression to AD dementia were similar to the results for the BioFINDER test data, while the performance for the cognitive decline was deteriorated. Conclusions: The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.</p>}}, author = {{Arvidsson, Ida and Strandberg, Olof and Palmqvist, Sebastian and Stomrud, Erik and Cullen, Nicholas and Janelidze, Shorena and Tideman, Pontus and Heyden, Anders and Åström, Karl and Hansson, Oskar and Mattsson-Carlgren, Niklas}}, issn = {{1758-9193}}, keywords = {{Alzheimer’s disease; Cognitive decline; Deep learning}}, language = {{eng}}, number = {{1}}, publisher = {{BioMed Central (BMC)}}, series = {{Alzheimer's Research and Therapy}}, title = {{Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer’s disease in patients with mild cognitive symptoms}}, url = {{http://dx.doi.org/10.1186/s13195-024-01428-5}}, doi = {{10.1186/s13195-024-01428-5}}, volume = {{16}}, year = {{2024}}, }