# Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation

arXiv: https://arxiv.org/abs/2512.09185 · HTML: https://mlsanity.com/paper/2512.09185/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [Flow Matching in Latent Space](https://mlsanity.com/paper/2307.08698/) (2023)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [Towards Generalizable Tumor Synthesis](https://mlsanity.com/paper/2402.19470/) (2024)
- [DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model](https://mlsanity.com/paper/2112.05149/) (2021)
- [SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation](https://mlsanity.com/paper/2212.08228/) (2022)
- [Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models](https://mlsanity.com/paper/2111.14923/) (2021)
- [Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge](https://mlsanity.com/paper/2405.03328/) (2024)
- [Degenerative Adversarial NeuroImage Nets for Brain Scan Simulations: Application in Ageing and Dementia](https://mlsanity.com/paper/1912.01526/) (2019)
- [Longitudinal Self-Supervised Learning](https://mlsanity.com/paper/2006.06930/) (2020)
- [Longitudinal Variational Autoencoder](https://mlsanity.com/paper/2006.09763/) (2020)
- [Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progression](https://mlsanity.com/paper/1907.02787/) (2019)
- [Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis](https://mlsanity.com/paper/2206.04281/) (2022)
- [Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction](https://mlsanity.com/paper/2309.05406/) (2023)
- [ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images](https://mlsanity.com/paper/2406.14794/) (2024)
- [TADM: Temporally-Aware Diffusion Model for Neurodegenerative Progression on Brain MRI](https://mlsanity.com/paper/2406.12411/) (2024)
- [Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusion](https://mlsanity.com/paper/2502.08560/) (2025)
- [PanTS: The Pancreatic Tumor Segmentation Dataset](https://mlsanity.com/paper/2507.01291/) (2025)
- [FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis](https://mlsanity.com/paper/2406.01264/) (2024)
- [Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data](https://mlsanity.com/paper/2510.14831/) (2025)
- [LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body Imaging](https://mlsanity.com/paper/2502.20985/) (2025)
- [Analyzing Tumors by Synthesis](https://mlsanity.com/paper/2409.06035/) (2024)
- [PIE: Simulating Disease Progression via Progressive Image Editing](https://mlsanity.com/paper/2309.11745/) (2023)

## Built on by (most cited first, 8 of 8)

- [Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies](https://mlsanity.com/paper/2606.16721/) (2026)
- [Uncertainty in a Single Pass: A Closed-Form Identity for One-Step Flow Matching](https://mlsanity.com/paper/2605.00941/) (2026)
- [Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching](https://mlsanity.com/paper/2601.15884/) (2026)
- [Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis](https://mlsanity.com/paper/2603.19516/) (2026)
- [NAMD: Virtual Follow-up Computed Tomography Synthesis via Nodule-Aligned Multimodal Diffusion Models for Early Lung Cancer Diagnosis](https://mlsanity.com/paper/2603.15932/) (2026)
- [Diagnostic-Guided Longitudinal Modeling for Forecasting Retinal Atrophy Progression](https://mlsanity.com/paper/2604.16955/) (2026)
- [Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory](https://mlsanity.com/paper/2606.28630/) (2026)
- [ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction](https://mlsanity.com/paper/2607.27537/) (2026)

## Abstract (arXiv)

Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment. While recent generative approaches have attempted to model progression, key mismatches remain: disease dynamics are inherently continuous and monotonic, yet latent representations are often scattered, lacking semantic structure, and diffusion-based models disrupt continuity with random denoising process. In this work, we propose to treat the disease dynamic as a velocity field and leverage Flow Matching (FM) to align the temporal evolution of patient data. Unlike prior methods, it captures the intrinsic dynamic of disease, making the progression more interpretable. However, a key challenge remains: in latent space, Auto-Encoders (AEs) do not guarantee alignment across patients or correlation with clinical-severity indicators (e.g., age and disease conditions). To address this, we propose to learn patient-specific latent alignment, which enforces patient trajectories to lie along a specific axis, with magnitude increasing monotonically with disease severity. This leads to a consistent and semantically meaningful latent space. Together, we present Delta-LFM, a framework for modeling patient-specific latent progression with flow matching. Across three longitudinal MRI benchmarks, Delta-LFM demonstrates strong empirical performance and, more importantly, offers a new framework for interpreting and visualizing disease dynamics.