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

Luoting Zhuang, Linh M. Tran, Yunzheng Zhu, Ashley E. Prosper, William Hsu
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2941-2957, 2026.

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 one of the first applications 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. Furthermore, pseudotime and delta-pseudotime effectively stratify nodules into distinct malignancy risk groups and remain significant independent predictors of malignancy after adjusting for established semantic biomarkers. Our study highlights pseudotime inference as a promising tool for dynamic modeling of lesion progression using static imaging data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-zhuang26a, title = {From Cross-Sectional CT to Dynamic Insights: Pseudotime-Based Modeling of Lung Nodule Progression}, author = {Zhuang, Luoting and Tran, Linh M. and Zhu, Yunzheng and Prosper, Ashley E. and Hsu, William}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2941--2957}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/zhuang26a/zhuang26a.pdf}, url = {https://proceedings.mlr.press/v315/zhuang26a.html}, 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 one of the first applications 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. Furthermore, pseudotime and delta-pseudotime effectively stratify nodules into distinct malignancy risk groups and remain significant independent predictors of malignancy after adjusting for established semantic biomarkers. Our study highlights pseudotime inference as a promising tool for dynamic modeling of lesion progression using static imaging data.} }
Endnote
%0 Conference Paper %T From Cross-Sectional CT to Dynamic Insights: Pseudotime-Based Modeling of Lung Nodule Progression %A Luoting Zhuang %A Linh M. Tran %A Yunzheng Zhu %A Ashley E. Prosper %A William Hsu %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-zhuang26a %I PMLR %P 2941--2957 %U https://proceedings.mlr.press/v315/zhuang26a.html %V 315 %X 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 one of the first applications 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. Furthermore, pseudotime and delta-pseudotime effectively stratify nodules into distinct malignancy risk groups and remain significant independent predictors of malignancy after adjusting for established semantic biomarkers. Our study highlights pseudotime inference as a promising tool for dynamic modeling of lesion progression using static imaging data.
APA
Zhuang, L., Tran, L.M., Zhu, Y., Prosper, A.E. & Hsu, W.. (2026). From Cross-Sectional CT to Dynamic Insights: Pseudotime-Based Modeling of Lung Nodule Progression. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2941-2957 Available from https://proceedings.mlr.press/v315/zhuang26a.html.

Related Material