Reverse Spatio-Temporal Disease Progression Modelling

Ulugbek Shernazarov; Moucheng Xu; Inomjon Ramatov

cs.CVSep 13, 2026

Reverse Spatio-Temporal Disease Progression Modelling

Authors: Ulugbek Shernazarov, Moucheng Xu, Inomjon Ramatov

Organizations: T´el´ecom SudParis, Institut Polytechnique de Paris, France · University College London, UK · Digital Technologies and Artificial Intelligence Development Research Institute (AIRI), Uzbekistan

Abstract

Deep learning-based spatio-temporal disease progression models commonly overlook the incubation period of progressive diseases, limiting the use of those models in early interventions, which are vital for not easily reversible diseases such as Alzheimer's. This is because, the existing deep learning based longitudinal disease-progression models are almost always run forward: from an observed baseline they predict future decline. In many clinical settings, however, imaging begins only after pathology is suspected or already visible, the earlier, healthier patient-specific reference was never acquired. To address this, we propose to study reverse disease progression prediction: given later diseased anatomy, reconstruct the unobserved healthier anatomy that preceded it. We use a two-stage model in which a frozen 3D vector-quantised autoencoder defines a compact discrete latent space, while a Neural Ordinary Differential Equation (ODE) learns continuous-time dynamics in that space. A recurrent encoder reads late observations in reverse temporal order, initialises the latent state, and the ODE is integrated backwards across the trajectory. On a controlled Morpho-MNIST benchmark with a sinusoidal perturbation, our model successfully recovered the unseen previous states from later observations of the non-monotonic trajectory. On longitudinal brain MRIs from Alzheimer's Disease Neuroimaging Initiative, at the task to recover the previous unseen trajectory towards healthy states of the patients from observed later diseased states, our model outperforms the baselines that uses copy-nearest and mean-observed, with positive disease-reversal scores in every diagnostic stratum. We hope that our work can provide insights and tools towards discovering the incubation periods from single-shot scans, and developing early interventions of diseases based on imaging.

Figures & tables

Figure 1: Two-stage reverse-prediction framework. A frozen 3D VQ-GAN maps late scans to a discrete latent grid. A reverse-order recurrent encoder initializes the latent state, a Neural ODE integrates backward over the visit grid, and a residual latent decoder plus frozen image decoder reconstruct earlier frames.

Figure 2: Single-scan inference. From one observed late scan, the frozen encoder produces a latent anchor; an inclination-conditioned temporal model integrates backward over the requested interval and horizon; the frozen decoder reconstructs earlier scans.

Figure 3: Visual results on Morpho-MNIST periodic reverse prediction. Given only diseased late frames ( $t=4$ – $9$ , green), the model reconstructs healthier earlier frames ( $t=0$ – $3$ , red). Rows show the masked input, ground truth, and prediction.

Method	MSE $\downarrow$	SSIM $\uparrow$
Neural ODE	$0.00238$	$\mathbf{0.574}$
VQ copy-nearest	$0.00168$	$0.454$
VQ mean-observed	$0.00157$	$0.470$
Pixel copy-nearest	$0.00088$	$0.957$
Pixel mean-observed	$0.00071$	$0.963$

Table 1: Registered

1\,

mm ADNI diagnostics on predicted frames for 25 test subjects. Pixel baselines are shown for context but skip the autoencoder. Best fair SSIM is bold. Dyn. denotes dynamics ratio; Rev. denotes disease-reversal score.

Figure 4: Visual results on registered $1\,$ mm ADNI. The frozen autoencoder already smooths the ground truth, and the Neural ODE prediction inherits this limitation. Green borders denote observed frames; red borders denote predicted frames.

Disease Progression Modeling

See all 24 papers

Jul 9, 2026

Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challenging because true progression signals are subtle in longitudinal MRI. In this low-signal regime, transferring modern generative sequence models directly is unreliable: training is dominated by stable baseline anatomy and confounded by dense, sample-specific nuisance variation. We first provide a theoretical analysis that explains these failures through two modes. Identity collapse occurs when optimization is driven toward reproducing the current anatomy, which prevents the model from learning faint temporal change. The continuous interpolation trap arises when standard smooth networks cannot separate localized biological drift from pervasive noise, which leads to spurious changes that diffuse across the volume. To address both issues, we propose Latent Drift, a progressive generative framework that learns change in a compressed semantic representation rather than synthesizing full-resolution anatomy. This design removes pixel-level identity from the prediction target and concentrates model capacity on progression-relevant dynamics. We further apply Finite Scalar Quantization to the learned change representation, which suppresses small, high-frequency nuisance fluctuations while preserving consistent structural drift. Experiments on longitudinal 3D brain MRI show that Latent Drift improves patient-specific neuro-forecasting over diffusion and autoregressive transformer baselines across generative fidelity and clinically relevant evaluation metrics. Project page: https://cutepkq.github.io/latent-drift.

Yuxiang Feng, Juncheng Wang, Chao Xu +7

Zhejiang University, Hangzhou, China · IROOTECH TECHNOLOGY, China · The Hong Kong Polytechnic University, Hong Kong, China +1

Finite Scalar Quantization Latent Dynamics Modeling Longitudinal Medical Image Analysis Clinical Outcome Prediction Medical Image Representation Learning Disease Progression Modeling

Ask PDF

Jun 23, 2026

Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning

Longitudinal modelling of Alzheimer's disease progression is clinically useful only if it can describe not just the most likely next diagnosis, but how a patient may evolve over time and how reliable that forecast is. Most deep learning approaches reduce this problem to single-step classification, treating cognitively normal, mild cognitive impairment, and dementia as flat categories while providing limited insight into how uncertainty accumulates across future visits. We propose a probabilistic framework that combines ordinal diagnosis prediction, multi-horizon trajectory generation, and decomposed uncertainty estimation. A Temporal Fusion Transformer encoder is adapted with a CORAL ordinal output layer, asymmetric loss weighting, and converter oversampling to respect disease-stage ordering and improve sensitivity to MCI-to-dementia transitions. Conditioned on the learned patient-context representation, an autoregressive Mixture Density Network generates five-year probabilistic trajectories for diagnosis state, CDR Sum of Boxes, MMSE orientation, and hippocampal volume. On ADNI, the model outperforms linear, recurrent, and transformer baselines for next-visit diagnosis prediction, with the strongest gains on MCI-versus-dementia discrimination. Generated trajectories achieve near-nominal 90% credible interval coverage, widening uncertainty across the forecast horizon, and biomarker dynamics consistent with expected Alzheimer's disease progression. We further separate aleatoric from epistemic uncertainty using analytic mixture variance and a five-member bootstrap ensemble, which provides the strongest encoder diversity and output-level epistemic signal. Epistemic uncertainty is higher for rare progression archetypes, MCI and dementia patients, and under external evaluation on OASIS-3, where it increases alongside prediction error.

Arya Hariharan, Shreyank N Gowda, Anala M R

Department of Computer Science and Engineering, R.V. College of Engineering, Bengaluru, Karnataka, India · School of Computer Science, University of Nottingham, Nottingham, United Kingdom

Clinical Outcome Prediction Alzheimer's Disease Classification Alzheimer's Disease Progression Prediction Probabilistic Time Series Forecasting Disease Progression Modeling

Ask PDF

Nov 8, 2025

AD-DAE: Alzheimer's Disease Progression Modeling with Unpaired Longitudinal MRI using Diffusion Auto-Encoders

Generative modeling frameworks have emerged as an effective approach to capture high-dimensional image distributions from large datasets without requiring domain-specific knowledge, a capability essential for disease progression modeling. Recent generative approaches have attempted to capture progression by mapping images to a latent space and guiding representations to generate follow-up images from previous time points. However, these methods impose constraints on distribution learning, resulting in latent spaces with limited controllability for generating follow-up images without paired subject-specific longitudinal guidance. In order to enable controlled movements in the latent representational space and generate progression images from a previous time-point image without subject-specific guidance, we introduce a conditionable Diffusion Auto-encoder framework that forms a compact latent space capturing high-level semantics and providing means to control generation. Our approach leverages this latent space to condition and apply controlled shifts to the representations of previous time-point images by isolating progression and subject identity information for generating follow-up images. The shifts are implicitly guided by correlating with progression attributes and constraining to Alzheimer's disease specific regions, without paired longitudinal guidance. We validate the generations through image quality metrics, volumetric progression analysis, and downstream tasks in Alzheimer's disease datasets from different sources. This demonstrates the effectiveness of our approach for Alzheimer's progression modeling and longitudinal image generation.

Ayantika Das, Arunima Sarkar, Keerthi Ram +1

Department of Electrical Engineering, Indian Institute of Technology Madras (IITM), Chennai 600036, India · Sudha Gopalakrishnan Brain Centre (SGBC), IITM, Chennai 600036, India

Medical Image Synthesis Alzheimer's Disease Progression Prediction Diffusion Autoencoder Conditional Generative Modeling Diffusion Models

Ask PDF

Abstract

Disease Progression Modeling

Explore similar work

Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning

AD-DAE: Alzheimer's Disease Progression Modeling with Unpaired Longitudinal MRI using Diffusion Auto-Encoders