Long-Term Alzheimers Disease Prediction: A Novel Image Generation Method Using Temporal Parameter Estimation with Normal Inverse Gamma Distribution on Uneven Time Series

2025-11-25

AI Summary

Irregular temporal sampling in longitudinal neuroimaging hinders continuous, pathologically faithful generation of brain MRI volumes for long-term Alzheimer’s disease (AD) progression prediction. Method: We propose T-NIG, a novel generative model that introduces time-parameterized Normal-Inverse-Gamma (NIG) distributions to explicitly encode temporal uncertainty in disease evolution. T-NIG jointly estimates cognitive (systematic) and aleatoric (stochastic) uncertainties via coordinate neighborhood feature encoding, enabling robust modeling of sparse, irregularly sampled longitudinal scans. Contribution/Results: Evaluated on real-world datasets including ADNI, T-NIG achieves state-of-the-art performance in both short- and long-term synthetic MRI generation and clinical progression forecasting. It significantly improves pathological feature fidelity and temporal dynamic consistency—demonstrating superior preservation of disease-relevant spatiotemporal patterns. T-NIG establishes a new paradigm for modeling neurodegenerative disorders under irregular sampling protocols.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems

Abstract

Image generation can provide physicians with an imaging diagnosis basis in the prediction of Alzheimer's Disease (AD). Recent research has shown that long-term AD predictions by image generation often face difficulties maintaining disease-related characteristics when dealing with irregular time intervals in sequential data. Considering that the time-related aspects of the distribution can reflect changes in disease-related characteristics when images are distributed unevenly, this research proposes a model to estimate the temporal parameter within the Normal Inverse Gamma Distribution (T-NIG) to assist in generating images over the long term. The T-NIG model employs brain images from two different time points to create intermediate brain images, forecast future images, and predict the disease. T-NIG is designed by identifying features using coordinate neighborhoods. It incorporates a time parameter into the normal inverse gamma distribution to understand how features change in brain imaging sequences that have varying time intervals. Additionally, T-NIG utilizes uncertainty estimation to reduce both epistemic and aleatoric uncertainties in the model, which arise from insufficient temporal data. In particular, the T-NIG model demonstrates state-of-the-art performance in both short-term and long-term prediction tasks within the dataset. Experimental results indicate that T-NIG is proficient in forecasting disease progression while maintaining disease-related characteristics, even when faced with an irregular temporal data distribution.

Problem

• Predicting Alzheimer's progression using irregular time-series brain imaging data
• Generating future brain images while preserving disease-related characteristics
• Estimating temporal parameters with Normal Inverse Gamma distribution for uncertainty reduction

Innovation

• T-NIG model estimates temporal parameters for image generation
• Incorporates time parameter into Normal Inverse Gamma distribution
• Uses uncertainty estimation to handle irregular time intervals