From Static CT to Dynamic Insights: Pseudotime-Based Modeling of Lung Nodule Progression

Luoting Zhuang, Linh M. Tran, Ashley E. Prosper, William Hsu

Keywords: Pseudotime inference, disease trajectory, lung nodules, diffusion maps, unsupervised learning

TL;DR: This paper is the first to explore and demonstrate the potential of using pseudotime inference to reconstruct pulmonary nodule progression from cross-sectional CT scans.

Abstract: Early detection of lung cancer relies on a comprehensive understanding of the progression of pulmonary nodules. Existing longitudinal modeling approaches are constrained due to the limited availability of longitudinal datasets and the failure to capture the inter-nodular relationship. In this study, we present the first application of pseudotime inference, adapted from single-cell RNA sequencing studies, to reconstruct progression trajectories of nodules from cross-sectional CT images. We collected 13,626 nodule snapshots from two screening cohorts and reserved a longitudinal test set for evaluation. We compared a graph-based pseudotime method, diffusion pseudotime, and an unsupervised deep learning framework combining a variational autoencoder and a neural ordinary differential equation. Both approaches demonstrate longitudinal consistency, with malignant nodules showing a higher correlation between pseudotime and actual time. Pseudotime aligns with clinically relevant features such as irregular margins and solid consistency. Logistic regression analysis shows that delta pseudotime remains a significant predictor of malignancy even after adjusting for semantic features, suggesting its potential as an independent biomarker. Our findings highlight pseudotime inference as a promising tool for dynamic modeling of lesion progression using static imaging data.

Primary Subject Area: Unsupervised Learning and Representation Learning

Secondary Subject Area: Application: Radiology

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 258