Early Lung Cancer Diagnosis from Virtual Follow-up LDCT Generation via Correlational Autoencoder and Latent Flow Matching

TL;DR

This paper introduces CorrFlowNet, a generative AI model that creates virtual follow-up CT scans from baseline images, enabling earlier lung cancer detection and improving diagnostic accuracy without waiting for actual follow-ups.

Contribution

The paper presents a novel correlational autoencoder and flow matching approach to generate realistic follow-up CT images, enhancing early lung cancer diagnosis from initial scans.

Findings

Significantly improves lung nodule risk assessment accuracy.

Generates virtual follow-up scans comparable to real clinical follow-ups.

Enhances early detection of malignant nodules.

Abstract

Lung cancer is one of the most commonly diagnosed cancers, and early diagnosis is critical because the survival rate declines sharply once the disease progresses to advanced stages. However, achieving an early diagnosis remains challenging, particularly in distinguishing subtle early signals of malignancy from those of benign conditions. In clinical practice, a patient with a high risk may need to undergo an initial baseline and several annual follow-up examinations (e.g., CT scans) before receiving a definitive diagnosis, which can result in missing the optimal treatment. Recently, Artificial Intelligence (AI) methods have been increasingly used for early diagnosis of lung cancer, but most existing algorithms focus on radiomic features extraction from single early-stage CT scans. Inspired by recent advances in diffusion models for image generation, this paper proposes a generative method, named CorrFlowNet, which creates a virtual, one-year follow-up CT scan after the initial baseline scan. This virtual follow-up would allow for an early detection of malignant/benign nodules, reducing the need to wait for clinical follow-ups. During training, our approach employs a correlational autoencoder to encode both early baseline and follow-up CT images into a latent space that captures the dynamics of nodule progression as well as the correlations between them, followed by a flow matching algorithm on the latent space with a neural ordinary differential equation. An auxiliary classifier is used to further enhance the diagnostic accuracy. Evaluations on a real clinical dataset show our method can significantly improve downstream lung nodule risk assessment compared with existing baseline models. Moreover, its diagnostic accuracy is comparable with real clinical CT follow-ups, highlighting its potential to improve cancer diagnosis.