The increasing efficiency and compactness of deep learning architectures, together with hardware improvements, have enabled the complex and high-dimensional modelling of medical volumetric data at higher resolutions. Recently, Vector-Quantised Variational Autoencoders (VQ-VAE) have been proposed as an efficient generative unsupervised learning approach that can encode images to a small percentage of their initial size, while preserving their decoded fidelity. Here, we show a VQ-VAE inspired network can efficiently encode a full-resolution 3D brain volume, compressing the data to 0.825% of the original size while maintaining image fidelity, and significantly outperforming the previous state-of-the-art. We then demonstrate that VQ-VAE decoded images preserve the morphological characteristics of the original data through voxel-based morphology and segmentation experiments. Lastly, we show that such models can be pre-trained and then fine-tuned on different datasets without the introduction of bias.
@article{arxiv.2002.05692,
title = {Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE},
author = {Petru-Daniel Tudosiu and Thomas Varsavsky and Richard Shaw and Mark Graham and Parashkev Nachev and Sebastien Ourselin and Carole H. Sudre and M. Jorge Cardoso},
journal= {arXiv preprint arXiv:2002.05692},
year = {2020}
}