Back to Search Start Over

Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE

Authors :
Tudosiu, Petru-Daniel
Varsavsky, Thomas
Shaw, Richard
Graham, Mark
Nachev, Parashkev
Ourselin, Sebastien
Sudre, Carole H.
Cardoso, M. Jorge
Publication Year :
2020

Abstract

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2002.05692
Document Type :
Working Paper