The tumor microenvironment (TME) plays a central role in cancer progression, treatment response, and patient outcomes, yet large-scale, consistent, and quantitative TME characterization from routine hematoxylin and eosin (H&E)-stained histopathology remains scarce. We introduce OpenTME, an open-access dataset of pre-computed TME profiles derived from 3,634 H&E-stained whole-slide images across five cancer types (bladder, breast, colorectal, liver, and lung cancer) from The Cancer Genome Atlas (TCGA). All outputs were generated using Atlas H&E-TME, an AI-powered application built on the Atlas family of pathology foundation models, which performs tissue quality control, tissue segmentation, cell detection and classification, and spatial neighborhood analysis, yielding over 4,500 quantitative readouts per slide at cell-level resolution. OpenTME is available for non-commercial academic research on Hugging Face. We will continue to expand OpenTME over time and anticipate it will serve as a resource for biomarker discovery, spatial biology research, and the development of computational methods for TME analysis.
@article{arxiv.2604.12075,
title = {OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA},
author = {Maaike Galama and Nina Kozar-Gillan and Christina Embacher and Todd Dembo and Cornelius Böhm and Evelyn Ramberger and Julika Ribbat-Idel and Rosemarie Krupar and Verena Aumiller and Miriam Hägele and Kai Standvoss and Gerrit Erdmann and Blanca Pablos and Ari Angelo and Simon Schallenberg and Andrew Norgan and Viktor Matyas and Klaus-Robert Müller and Maximilian Alber and Lukas Ruff and Frederick Klauschen},
journal= {arXiv preprint arXiv:2604.12075},
year = {2026}
}