| Title: | Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections |
| Journal: | Brain Sciences |
| Published: | 15 Sep 2023 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/37759930/ |
| DOI: | https://doi.org/10.3390/brainsci13091329 |
| URL: | https://www.mdpi.com/2076-3425/13/9/1329/pdf?version=1694766735 |
Publication 9571
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Using 3D CNNs on high-resolution medical volumes is very computationally demanding, especially for large datasets like UK Biobank, which aims to scan 100,000 subjects. Here, we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of 3D volumes leads to reasonable test accuracy (mean absolute error of about 3.5 years) when predicting age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 20-50 s using a single GPU, which is two orders of magnitude faster than a small 3D CNN. This speedup is explained by the fact that 3D brain volumes contain a lot of redundant information, which can be efficiently compressed using 2D projections. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs.</p>
5 Authors
- Johan Jönemo
- Muhammad Usman Akbar
- Robin Kämpe
- J. Paul Hamilton
- Anders Eklund
Enabling scientific discoveries that improve human health