Alert button
Picture for Svenja Caspers

Svenja Caspers

Alert button

An Uncertainty-Aware, Shareable and Transparent Neural Network Architecture for Brain-Age Modeling

Jul 16, 2021
Tim Hahn, Jan Ernsting, Nils R. Winter, Vincent Holstein, Ramona Leenings, Marie Beisemann, Lukas Fisch, Kelvin Sarink, Daniel Emden, Nils Opel, Ronny Redlich, Jonathan Repple, Dominik Grotegerd, Susanne Meinert, Jochen G. Hirsch, Thoralf Niendorf, Beate Endemann, Fabian Bamberg, Thomas Kröncke, Robin Bülow, Henry Völzke, Oyunbileg von Stackelberg, Ramona Felizitas Sowade, Lale Umutlu, Börge Schmidt, Svenja Caspers, German National Cohort Study Center Consortium, Harald Kugel, Tilo Kircher, Benjamin Risse, Christian Gaser, James H. Cole, Udo Dannlowski, Klaus Berger

Figure 1 for An Uncertainty-Aware, Shareable and Transparent Neural Network Architecture for Brain-Age Modeling
Figure 2 for An Uncertainty-Aware, Shareable and Transparent Neural Network Architecture for Brain-Age Modeling
Figure 3 for An Uncertainty-Aware, Shareable and Transparent Neural Network Architecture for Brain-Age Modeling

The deviation between chronological age and age predicted from neuroimaging data has been identified as a sensitive risk-marker of cross-disorder brain changes, growing into a cornerstone of biological age-research. However, Machine Learning models underlying the field do not consider uncertainty, thereby confounding results with training data density and variability. Also, existing models are commonly based on homogeneous training sets, often not independently validated, and cannot be shared due to data protection issues. Here, we introduce an uncertainty-aware, shareable, and transparent Monte-Carlo Dropout Composite-Quantile-Regression (MCCQR) Neural Network trained on N=10,691 datasets from the German National Cohort. The MCCQR model provides robust, distribution-free uncertainty quantification in high-dimensional neuroimaging data, achieving lower error rates compared to existing models across ten recruitment centers and in three independent validation samples (N=4,004). In two examples, we demonstrate that it prevents spurious associations and increases power to detect accelerated brain-aging. We make the pre-trained model publicly available.

Viaarxiv icon

Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks

Mar 22, 2021
Lukas Fisch, Jan Ernsting, Nils R. Winter, Vincent Holstein, Ramona Leenings, Marie Beisemann, Kelvin Sarink, Daniel Emden, Nils Opel, Ronny Redlich, Jonathan Repple, Dominik Grotegerd, Susanne Meinert, Niklas Wulms, Heike Minnerup, Jochen G. Hirsch, Thoralf Niendorf, Beate Endemann, Fabian Bamberg, Thomas Kröncke, Annette Peters, Robin Bülow, Henry Völzke, Oyunbileg von Stackelberg, Ramona Felizitas Sowade, Lale Umutlu, Börge Schmidt, Svenja Caspers, German National Cohort Study Center Consortium, Harald Kugel, Bernhard T. Baune, Tilo Kircher, Benjamin Risse, Udo Dannlowski, Klaus Berger, Tim Hahn

Figure 1 for Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks
Figure 2 for Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks
Figure 3 for Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks
Figure 4 for Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks

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.

Viaarxiv icon