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

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.

Data-Driven Thresholding Statistically Biases ATN Profiling across Cohort Datasets

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.