4D VQ-GAN: Synthesising Medical Scans at Any Time Point for Personalised Disease Progression Modelling of Idiopathic Pulmonary Fibrosis

TL;DR

This paper introduces 4D-VQ-GAN, a novel model that synthesizes realistic longitudinal CT scans of IPF patients at any time point, aiding disease progression modeling and survival prediction.

Contribution

The paper presents a two-stage 4D VQ-GAN framework combining generative and temporal modeling for realistic disease progression simulation in medical imaging.

Findings

Generated CT scans closely match real data both qualitatively and quantitatively.

Survival analysis using generated scans achieves comparable C-index to real scans.

The model demonstrates potential for clinical utility in disease prognosis.

Abstract

Understanding the progression trajectories of diseases is crucial for early diagnosis and effective treatment planning. This is especially vital for life-threatening conditions such as Idiopathic Pulmonary Fibrosis (IPF), a chronic, progressive lung disease with a prognosis comparable to many cancers. Computed tomography (CT) imaging has been established as a reliable diagnostic tool for IPF. Accurately predicting future CT scans of early-stage IPF patients can aid in developing better treatment strategies, thereby improving survival outcomes. In this paper, we propose 4D Vector Quantised Generative Adversarial Networks (4D-VQ-GAN), a model capable of generating realistic CT volumes of IPF patients at any time point. The model is trained using a two-stage approach. In the first stage, a 3D-VQ-GAN is trained to reconstruct CT volumes. In the second stage, a Neural Ordinary Differential Equation (ODE) based temporal model is trained to capture the temporal dynamics of the quantised embeddings generated by the encoder in the first stage. We evaluate different configurations of our model for generating longitudinal CT scans and compare the results against ground truth data, both quantitatively and qualitatively. For validation, we conduct survival analysis using imaging biomarkers derived from generated CT scans and achieve a C-index comparable to that of biomarkers derived from the real CT scans. The survival analysis results demonstrate the potential clinical utility inherent to generated longitudinal CT scans, showing that they can reliably predict survival outcomes.