PT  - JOURNAL ARTICLE
AU  - Han Peng
AU  - Weikang Gong
AU  - Christian F. Beckmann
AU  - Andrea Vedaldi
AU  - Stephen M. Smith
TI  - Accurate brain age prediction with lightweight deep neural networks
AID  - 10.1101/2019.12.17.879346
DP  - 2019 Jan 01
TA  - bioRxiv
PG  - 2019.12.17.879346
4099  - http://biorxiv.org/content/early/2019/12/18/2019.12.17.879346.short
4100  - http://biorxiv.org/content/early/2019/12/18/2019.12.17.879346.full
AB  - Deep learning has huge potential for accurate disease prediction with neuroimaging data, but the prediction performance is often limited by training-dataset size and compute memory requirements. To address this, we propose a deep convolutional neural network model, Simple Fully Convolutional Network (SFCN), for accurate prediction of brain age using T1-weighted structural MRI data. Compared with other popular deep network architectures, SFCN has fewer parameters, so is more compatible with small dataset size and 3D volume data. The network architecture was combined with several techniques for boosting performance, including data augmentation, pre-training, model regularization, model ensemble and prediction bias correction. We compared our overall SFCN approach with several widely-used machine learning models. It achieved state-of-the-art performance in UK Biobank data (N = 14,503), with mean absolute error (MAE) = 2.14y in brain age prediction and 99.3% in sex classification. SFCN also won (both parts of) the 2019 Predictive Analysis Challenge for brain age prediction, involving 79 competing teams (N = 2,638, MAE = 2.90y). We describe here the details of our approach, and its optimisation and validation. Our approach can easily be generalised to other tasks using different image modalities, and is released on GitHub.HighlightsA lightweight deep learning model, Simple Fully Convolutional Network (SFCN), is presented, achieving state-of-the-art brain age prediction performance in UK Biobank MRI brain imaging data.Even with limited number of training subjects (e.g., 50), SFCN performs better than widely-used regression models.A semi-multimodal ensemble strategy is proposed and achieved first place in the PAC 2019 brain age prediction challenge.Linear regression can remove brain age predication bias (even on unlabelled data) while maintaining state-of-the-art performance.