yuangang-pan / ukbiobank_deep_pretrain

Pretrained neural networks for UK Biobank brain MRI images. SFCN, 3D-ResNet etc.

UKBiobank_deep_pretrain

Pretrained neural networks for UK Biobank brain MRI images. SFCN, 3D-ResNet etc.

Under construction.

The models are trained, validated and benchmarked with UK Biobank brain MRI images, 14,503-subject release.

Model input shape: [batch_size, 1, 160, 192, 160]

Pretrained weights (no subject level information)

File	Model	No. training subjects	Test MAE (years)	Validation MAE (yrs)	Train MAE (yrs)	Val-Train MAE gap (yrs)
./brain_age/run_20190719_00_epoch_best_mae.p	SFCN (SGD)	12,949	2.14±0.05	2.18±0.04	1.36±0.03	0.83±0.06

(As summarized in Table 1 in the manuscript)

Examples

Checkout the file examples.ipynb

model = SFCN()
model = torch.nn.DataParallel(model)
# This is to be modified with the path of saved weights
p_ = './run_20190719_00_epoch_best_mae.p'
model.load_state_dict(torch.load(p_))

Other resources

• UK Biobank preprocessing information https://www.fmrib.ox.ac.uk/ukbiobank/fbp/

To cite

Accurate brain age prediction with lightweight deep neural networks Han Peng, Weikang Gong, Christian F. Beckmann, Andrea Vedaldi, Stephen M Smith bioRxiv 2019.12.17.879346; doi: https://doi.org/10.1101/2019.12.17.879346

Please consider star and/or watch this repository if you find it helpful, as we will keep updating this repository for pretrained models and weights.