Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks
This approach enables faster, more robust, and more accurate brain-age modeling for researchers and clinicians studying brain diseases and aging, though it is incremental as it builds on existing ResNet architectures.
The paper tackled the problem of predicting brain-age from MRI data by developing a 3D CNN trained on raw, non-registered T1-weighted images, which achieved a mean average deviation of 2.84 years and outperformed state-of-the-art models using preprocessed data.
Age prediction based on Magnetic Resonance Imaging (MRI) data of the brain is a biomarker to quantify the progress of brain diseases and aging. Current approaches rely on preparing the data with multiple preprocessing steps, such as registering voxels to a standardized brain atlas, which yields a significant computational overhead, hampers widespread usage and results in the predicted brain-age to be sensitive to preprocessing parameters. Here we describe a 3D Convolutional Neural Network (CNN) based on the ResNet architecture being trained on raw, non-registered T$_ 1$-weighted MRI data of N=10,691 samples from the German National Cohort and additionally applied and validated in N=2,173 samples from three independent studies using transfer learning. For comparison, state-of-the-art models using preprocessed neuroimaging data are trained and validated on the same samples. The 3D CNN using raw neuroimaging data predicts age with a mean average deviation of 2.84 years, outperforming the state-of-the-art brain-age models using preprocessed data. Since our approach is invariant to preprocessing software and parameter choices, it enables faster, more robust and more accurate brain-age modeling.