Voxel-Level Importance Maps for Interpretable Brain Age Estimation

Bintsi, Kyriaki-Margarita; Baltatzis, Vasileios; Hammers, Alexander; Rueckert, Daniel

doi:10.1007/978-3-030-87444-5_7

Cited by 9 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This information revealed important brain regions missed by other mapping methods. The saliency map in the previous studies highlighted the brain regions such as the hippocampus, brainstem, and amygdala [6, 7, 19]. When highlighting the important points with higher integrated gradients in our study, they were centered on the fornix and the lower part of the thalamus.…”

Section: Discussionmentioning

confidence: 60%

Investigation of Genetic Variants and Causal Biomarkers Associated with Brain Aging

Kim

Lee

2022

Preprint

View full text Add to dashboard Cite

Delta age is a biomarker of brain aging that captures differences between the actual age and the predicted age from brain MRI. This study investigates an explainable and causal basis of high delta age by analyzing UK Biobank data in three steps. 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. Genetic association analysis on both the single variants and the gene regions identified that genes related to carcinogenesis, immune response, and neuron survival are associated with high delta age. Mendelian randomization (MR) for all metabolomic biomarkers and blood-related phenotypes showed that immune-related phenotypes have a causal impact on increasing delta age. Taken together, these observations revealed regions in the brain that are susceptible to the aging process and provided evidence of the causal and genetic connection between immune responses and brain aging.

show abstract

Section: Discussionmentioning

confidence: 60%

Investigation of Genetic Variants and Causal Biomarkers Associated with Brain Aging

Kim

Lee

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In comparison, the CNN4 model exhibits BAG with greater variability than the other three models (CNN1–3). The intensity of importance, with higher importance depicted in yellow colours, proves more significant for predicting younger ages (e.g., −6 years), particularly near the ventricles ( Bintsi et al, 2021 ) and insular cortex ( Lee et al, 2022 ). Conversely, when predicting older ages, greater importance is assigned to the right side of the insular cortex ( Lee et al, 2022 ) and the frontal–occipital region.…”

Section: Resultsmentioning

confidence: 99%

“…In contrast, for predicting subjects as younger, highlighted regions are located around the ventricles and insular cortex. The salience maps also show regions symmetrical and asymmetrical, mainly on the left side of the brain ( Roe et al, 2021 ) and around the ventricles ( Bintsi et al, 2021 ), as important for age prediction. Left brain asymmetries with ageing are a typical pattern found in ageing studies of cortical thickness ( Koelkebeck et al, 2014 ; Frangou et al, 2022 ), cortical volume, and surface area ( Koelkebeck et al, 2014 ).…”

Section: Discussionmentioning

confidence: 99%

A deep learning model for brain age prediction using minimally preprocessed T1w images as input

Dartora,

Marseglia,

Mårtensson

et al. 2024

Front. Aging Neurosci.

View full text Add to dashboard Cite

IntroductionIn 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.MethodsWe 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.DiscussionWe 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.

show abstract

“…This information revealed important brain regions missed by other mapping methods. The saliency map in the previous studies highlighted the brain regions such as the hippocampus, brainstem, and amygdala 7 , 8 , 27 . When highlighting the important points with higher integrated gradients in our study, they were centered on the fornix and the lower part of the thalamus.…”

Section: Discussionmentioning

confidence: 99%

Investigation of genetic variants and causal biomarkers associated with brain aging

Kim

Lee

Nam

et al. 2023

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Voxel-Level Importance Maps for Interpretable Brain Age Estimation

Cited by 9 publications

References 26 publications

Investigation of Genetic Variants and Causal Biomarkers Associated with Brain Aging

Investigation of Genetic Variants and Causal Biomarkers Associated with Brain Aging

A deep learning model for brain age prediction using minimally preprocessed T1w images as input

Investigation of genetic variants and causal biomarkers associated with brain aging

Contact Info

Product

Resources

About