English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The increasing efficiency and compactness of deep learning architectures,together with hardware improvements, have enabled the complex andhigh-dimensional modelling of medical volumetric data at higher resolutions.Recently, Vector-Quantised Variational Autoencoders (VQ-VAE) have been proposedas an efficient generative unsupervised learning approach that can encodeimages to a small percentage of their initial size, while preserving theirdecoded fidelity. Here, we show a VQ-VAE inspired network can efficientlyencode a full-resolution 3D brain volume, compressing the data to $0.825\%$ ofthe original size while maintaining image fidelity, and significantlyoutperforming the previous state-of-the-art. We then demonstrate that VQ-VAEdecoded images preserve the morphological characteristics of the original datathrough voxel-based morphology and segmentation experiments. Lastly, we showthat such models can be pre-trained and then fine-tuned on different datasetswithout the introduction of bias.

Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE