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

TL;DR

This paper introduces T-NIG, a novel image generation model that estimates temporal parameters using the Normal Inverse Gamma distribution to improve long-term Alzheimer's disease prediction from uneven time series data.

Contribution

The paper presents T-NIG, a new model that incorporates temporal parameter estimation and uncertainty modeling to enhance long-term disease prediction from irregular brain imaging sequences.

Findings

Achieves state-of-the-art performance in long-term AD prediction.

Effectively maintains disease-related features in generated images.

Reduces epistemic and aleatoric uncertainties in predictions.

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.