mlsanityData to 7 Oct 2026

Multiscale Metamorphic VAE for 3D Brain MRI Synthesis

arXiv 2301.03588 ↗First posted 9 Jan 2023eess.IV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Generative modeling of 3D brain MRIs presents difficulties in achieving high visual fidelity while ensuring sufficient coverage of the data distribution. In this work, we propose to address this challenge with composable, multiscale morphological transformations in a variational autoencoder (VAE) framework. These transformations are applied to a chosen reference brain image to generate MRI volumes, equipping the model with strong anatomical inductive biases. We structure the VAE latent space in a way such that the model covers the data distribution sufficiently well. We show substantial performance improvements in FID while retaining comparable, or superior, reconstruction quality compared to prior work based on VAEs and generative adversarial networks (GANs).

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 11 of its 19 references that are in the map. First posted on arXiv 9 Jan 2023.

Builds on

11 of 19 references.

References · 11

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2019An Introduction to Variational Autoencoderscited by 997
  3. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  4. 2022Brain Imaging Generation with Latent Diffusion Modelscited by 267
  5. 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
  6. 2019Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networkscited by 65
  7. 2017Visual Feature Attribution using Wasserstein GANscited by 47
  8. 2021Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative modelscited by 36
  9. 2019Degenerative Adversarial NeuroImage Nets for Brain Scan Simulations: Application in Ageing and Dementiacited by 34
  10. 20213D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Imagescited by 32
  11. 2021ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scanscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 5; 2026: 1.

8 papers.

  1. 2024Deep Generative Models for 3D Medical Image Synthesiscited by 14
  2. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRIcited by 9
  3. 2025MRI Super-Resolution with Deep Learning: A Comprehensive Surveycited by 7
  4. 2025Diffusion Bridge Models for 3D Medical Image Translationcited by 2
  5. 2026SRUG: A Fusion-Driven Generator Network for Medical Image Translationcited by 1
  6. 2025MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomographycited by 0
  7. 2025MRExtrap: Longitudinal Aging of Brain MRIs using Linear Modeling in Latent Spacecited by 0
  8. 2025From Healthy Scans to Annotated Tumors: A Tumor Fabrication Framework for 3D Brain MRI Synthesiscited by 0