# Generating Novel Brain Morphology by Deforming Learned Templates

arXiv: https://arxiv.org/abs/2503.03778 · HTML: https://mlsanity.com/paper/2503.03778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1908.02498/) (2019)
- [Learning Conditional Deformable Templates with Convolutional Networks](https://mlsanity.com/paper/1908.02738/) (2019)
- [Diffusion Deformable Model for 4D Temporal Medical Image Generation](https://mlsanity.com/paper/2206.13295/) (2022)
- [Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models](https://mlsanity.com/paper/2111.14923/) (2021)
- [Generative Adversarial Registration for Improved Conditional Deformable Templates](https://mlsanity.com/paper/2105.04349/) (2021)
- [Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend](https://mlsanity.com/paper/2311.13717/) (2023)
- [Morphology-preserving Autoregressive 3D Generative Modelling of the Brain](https://mlsanity.com/paper/2209.03177/) (2022)
- [Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs](https://mlsanity.com/paper/2310.04630/) (2023)
- [A Framework for Interpretability in Machine Learning for Medical Imaging](https://mlsanity.com/paper/2310.01685/) (2023)
- [Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases](https://mlsanity.com/paper/2403.16776/) (2024)
- [Deformation-Recovery Diffusion Model (DRDM): Instance Deformation for Image Manipulation and Synthesis](https://mlsanity.com/paper/2407.07295/) (2024)
- [DiffuseReg: Denoising Diffusion Model for Obtaining Deformation Fields in Unsupervised Deformable Image Registration](https://mlsanity.com/paper/2410.05234/) (2024)
- [Independent components of human brain morphology](https://mlsanity.com/paper/2003.10514/) (2020)

## Abstract (arXiv)

Designing generative models for 3D structural brain MRI that synthesize morphologically-plausible and attribute-specific (e.g., age, sex, disease state) samples is an active area of research. Existing approaches based on frameworks like GANs or diffusion models synthesize the image directly, which may limit their ability to capture intricate morphological details. In this work, we propose a 3D brain MRI generation method based on state-of-the-art latent diffusion models (LDMs), called MorphLDM, that generates novel images by applying synthesized deformation fields to a learned template. Instead of using a reconstruction-based autoencoder (as in a typical LDM), our encoder outputs a latent embedding derived from both an image and a learned template that is itself the output of a template decoder; this latent is passed to a deformation field decoder, whose output is applied to the learned template. A registration loss is minimized between the original image and the deformed template with respect to the encoder and both decoders. Empirically, our approach outperforms generative baselines on metrics spanning image diversity, adherence with respect to input conditions, and voxel-based morphometry. Our code is available at https://github.com/alanqrwang/morphldm.