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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Galama, Maaike, Kozar-Gillan, Nina, Embacher, Christina, Dembo, Todd, Böhm, Cornelius, Ramberger, Evelyn, Ribbat-Idel, Julika, Krupar, Rosemarie, Aumiller, Verena, Hägele, Miriam, Standvoss, Kai, Erdmann, Gerrit, Pablos, Blanca, Angelo, Ari, Schallenberg, Simon, Norgan, Andrew, Matyas, Viktor, Müller, Klaus-Robert, Alber, Maximilian, Ruff, Lukas, Klauschen, Frederick
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911591388151808
author Galama, Maaike
Kozar-Gillan, Nina
Embacher, Christina
Dembo, Todd
Böhm, Cornelius
Ramberger, Evelyn
Ribbat-Idel, Julika
Krupar, Rosemarie
Aumiller, Verena
Hägele, Miriam
Standvoss, Kai
Erdmann, Gerrit
Pablos, Blanca
Angelo, Ari
Schallenberg, Simon
Norgan, Andrew
Matyas, Viktor
Müller, Klaus-Robert
Alber, Maximilian
Ruff, Lukas
Klauschen, Frederick
author_facet Galama, Maaike
Kozar-Gillan, Nina
Embacher, Christina
Dembo, Todd
Böhm, Cornelius
Ramberger, Evelyn
Ribbat-Idel, Julika
Krupar, Rosemarie
Aumiller, Verena
Hägele, Miriam
Standvoss, Kai
Erdmann, Gerrit
Pablos, Blanca
Angelo, Ari
Schallenberg, Simon
Norgan, Andrew
Matyas, Viktor
Müller, Klaus-Robert
Alber, Maximilian
Ruff, Lukas
Klauschen, Frederick
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12075
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA
Galama, Maaike
Kozar-Gillan, Nina
Embacher, Christina
Dembo, Todd
Böhm, Cornelius
Ramberger, Evelyn
Ribbat-Idel, Julika
Krupar, Rosemarie
Aumiller, Verena
Hägele, Miriam
Standvoss, Kai
Erdmann, Gerrit
Pablos, Blanca
Angelo, Ari
Schallenberg, Simon
Norgan, Andrew
Matyas, Viktor
Müller, Klaus-Robert
Alber, Maximilian
Ruff, Lukas
Klauschen, Frederick
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Quantitative Methods
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.
title OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2604.12075