Image-Based Inference of Tumor Cell Trajectories Enables Large-Scale Cancer Progression Analysis

Authors

Yang Liu
Ling Cai
Ruichen Rong
Shidan Wang
Liwei Jia
Peiran Quan
Qin Zhou
Guanghua Xiao
Yang Xie

Language

English

Publication Date

7-18-2025

Journal

Science Advances

DOI

10.1126/sciadv.adv9466

PMID

40680117

PMCID

PMC12273761

PubMedCentral® Posted Date

7-18-2025

PubMedCentral® Full Text Version

Post-print

Abstract

Current approaches to estimating cell trajectories, tumor progression dynamics, and cell population diversity of tumor microenvironment often depend on single-cell RNA sequencing, which is costly and resource intensive. To address this limitation, we developed an artificial intelligence (AI) model that leverages cell morphology features and histological spatial organization to classify tumor cell differentiation status, infer cell dynamic trajectories, and quantify tumor progression from hematoxylin and eosin (H&E)-stained whole-slide images. In three independent lung adenocarcinoma cohorts, our AI-based model accurately predicted cell differential status and provided quantifiable measures of tumor progression that were prognostic of patient survival. Spatial transcriptomic integrative analyses revealed cell components and gene signatures enriched in different cell differentiation statuses. Bulk transcriptomic analyses revealed that fast-progressing tumors exhibit up-regulated cell cycle pathways, while slow-progressing tumors retain characteristics of normal lung epithelium. This cost-effective method enables large-scale analysis of tumor progression dynamics using routinely collected pathology slides and provides insights into intratumor heterogeneity.

Keywords

Humans, Disease Progression, Lung Neoplasms, Tumor Microenvironment, Adenocarcinoma of Lung, Gene Expression Profiling, Artificial Intelligence, Transcriptome, Prognosis, Neoplasms, Image Processing, Computer-Assisted

Published Open-Access

yes

Recommended Citation

Liu, Yang; Cai, Ling; Rong, Ruichen; et al., "Image-Based Inference of Tumor Cell Trajectories Enables Large-Scale Cancer Progression Analysis" (2025). Faculty, Staff and Student Publications. 6199.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/6199