mlsanityData to 7 Oct 2026

Synthesizing Individualized Aging Brains in Health and Disease with Generative Models and Parallel Transport

arXiv 2502.21049 ↗First posted 28 Feb 2025cs.CV cs.AI eess.IVcited by 9

Not on the map. Why?

Abstract (arXiv)

Simulating prospective magnetic resonance imaging (MRI) scans from a given individual brain image is challenging, as it requires accounting for canonical changes in aging and/or disease progression while also considering the individual brain's current status and unique characteristics. While current deep generative models can produce high-resolution anatomically accurate templates for population-wide studies, their ability to predict future aging trajectories for individuals remains limited, particularly in capturing subject-specific neuroanatomical variations over time. In this study, we introduce Individualized Brain Synthesis (InBrainSyn), a framework for synthesizing high-resolution subject-specific longitudinal MRI scans that simulate neurodegeneration in both Alzheimer's disease (AD) and normal aging. InBrainSyn uses a parallel transport algorithm to adapt the population-level aging trajectories learned by a generative deep template network, enabling individualized aging synthesis. As InBrainSyn uses diffeomorphic transformations to simulate aging, the synthesized images are topologically consistent with the original anatomy by design. We evaluated InBrainSyn both quantitatively and qualitatively on AD and healthy control cohorts from the Open Access Series of Imaging Studies - version 3 dataset. Experimentally, InBrainSyn can also model neuroanatomical transitions between normal aging and AD. An evaluation of an external set supports its generalizability. Overall, with only a single baseline scan, InBrainSyn synthesizes realistic 3D spatiotemporal T1w MRI scans, producing personalized longitudinal aging trajectories. The code for InBrainSyn is available at: https://github.com/Fjr9516/InBrainSyn.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 23 of its 84 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

23 of 84 references.

References · 23

  1. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  2. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  3. 2016Least Squares Generative Adversarial Networkscited by 1,000
  4. 2018Which Training Methods for GANs do actually Converge?cited by 672
  5. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  6. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 235
  7. 2019Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfacescited by 186
  8. 2020SynthMorph: learning contrast-invariant registration without acquired imagescited by 137
  9. 2020CycleMorph: Cycle Consistent Unsupervised Deformable Image Registrationcited by 78
  10. 2017End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Networkcited by 75
  11. 2019Learning Conditional Deformable Templates with Convolutional Networkscited by 64
  12. 2022SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generationcited by 56
11 more
  1. 2019Learning to synthesise the ageing brain without longitudinal datacited by 42
  2. 2021Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative modelscited by 36
  3. 2024Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledgecited by 35
  4. 2019Degenerative Adversarial NeuroImage Nets for Brain Scan Simulations: Application in Ageing and Dementiacited by 34
  5. 2021Generative Adversarial Registration for Improved Conditional Deformable Templatescited by 31
  6. 2019Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progressioncited by 21
  7. 2025Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusioncited by 17
  8. 2018Predictive Image Regression for Longitudinal Studies with Missing Datacited by 7
  9. 2021Distinguishing Healthy Ageing from Dementia: a Biomechanical Simulation of Brain Atrophy using Deep Networkscited by 3
  10. 2022Generative Aging of Brain Images with Diffeomorphic Registrationcited by 3
  11. 2020Anatomical Predictions using Subject-Specific Medical Datacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2026FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matchingcited by 5
  2. 2025Forecasting Future Anatomies: Longitudinal Brain Mri-to-Mri Predictioncited by 1
  3. 2026Cortex-Grounded Diffusion Models for Brain Image Generationcited by 1
  4. 20264DLoG: Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Modelcited by 1
  5. 2025Alzheimers Disease Progression Prediction Based on Manifold Mapping of Irregularly Sampled Longitudinal Datacited by 0
  6. 2026Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologiescited by 0
  7. 2026Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registrationcited by 0
  8. 2026textttDisMorph: learning to disentangle technical distortions from true biological changecited by 0
  9. 2026AnaDiffusion: Anatomically CompositionalLatent Diffusion for Controllable 3D Brain MRI Generationcited by 0