# Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE

arXiv: https://arxiv.org/abs/2002.05692 · HTML: https://mlsanity.com/paper/2002.05692/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2020.

## Built on by (most cited first, 7 of 7)

- [Unsupervised 3D out-of-distribution detection with latent diffusion models](https://mlsanity.com/paper/2307.03777/) (2023)
- [Transformer-based out-of-distribution detection for clinically safe segmentation](https://mlsanity.com/paper/2205.10650/) (2022)
- [Morphology-preserving Autoregressive 3D Generative Modelling of the Brain](https://mlsanity.com/paper/2209.03177/) (2022)
- [MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion](https://mlsanity.com/paper/2410.07659/) (2024)
- [Generative Aging of Brain Images with Diffeomorphic Registration](https://mlsanity.com/paper/2205.15607/) (2022)
- [Latent Space Analysis of VAE and Intro-VAE applied to 3-dimensional MR Brain Volumes of Multiple Sclerosis, Leukoencephalopathy, and Healthy Patients](https://mlsanity.com/paper/2101.06772/) (2021)
- [DiSC-Med: Diffusion-based Semantic Communications for Robust Medical Image Transmission](https://mlsanity.com/paper/2508.00172/) (2025)

## Abstract (arXiv)

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.