OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA

TL;DR

OpenTME is a comprehensive, publicly available dataset of AI-derived tumor microenvironment profiles from thousands of H&E-stained images across multiple cancer types, supporting research and biomarker discovery.

Contribution

The paper introduces OpenTME, a large-scale, open-access dataset of TME profiles generated by AI from TCGA H&E images, enabling advanced spatial biology studies.

Findings

Over 4,500 quantitative TME readouts per slide

Dataset covers five major cancer types

Built using AI-powered Atlas H&E-TME application

Abstract

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.