%0 Journal Article
%A Schallenberg, Simon
%A Dernbach, Gabriel
%A Ruane, Sharon
%A Jurmeister, Philipp
%A Böhm, Cornelius
%A Standvoss, Kai
%A Ghosh, Sandip
%A Frentsch, Marco
%A Dragomir, Mihnea-Paul
%A Keyl, Philipp G
%A Friedrich, Corinna
%A Na, Il-Kang
%A Merkelbach-Bruse, Sabine
%A Quaas, Alexander
%A Frost, Nikolaj
%A Boschung, Kyrill
%A Randerath, Winfried
%A Schlachtenberger, Georg
%A Heldwein, Matthias
%A Keilholz, Ulrich
%A Hekmat, Khosro
%A Rückert, Jens-Carsten
%A Büttner, Reinhard
%A Vasaturo, Angela
%A Horst, David
%A Ruff, Lukas
%A Alber, Maximilian
%A Müller, Klaus-Robert
%A Klauschen, Frederick
%T AI-powered spatial cell phenomics enhances risk stratification in non-small cell lung cancer.
%J Nature Communications
%V 16
%N 1
%@ 2041-1723
%C [London]
%I Springer Nature
%M DKFZ-2025-02269
%P 9701
%D 2025
%X Risk stratification remains a critical challenge in non-small cell lung cancer patients for optimal therapy selection. In this study, we develop an artificial intelligence-powered spatial cellomics approach that combines histology, multiplex immunofluorescence imaging and multimodal machine learning to characterize the complex cellular relationships of 43 cell phenotypes in the tumor microenvironment in a real-world retrospective cohort of 1168 non-small cell lung cancer patients from two large German cancer centers. The model identifies cell niches associated with survival and achieves a 14
%K Humans
%K Carcinoma, Non-Small-Cell Lung: pathology
%K Carcinoma, Non-Small-Cell Lung: mortality
%K Carcinoma, Non-Small-Cell Lung: diagnostic imaging
%K Lung Neoplasms: pathology
%K Lung Neoplasms: mortality
%K Tumor Microenvironment
%K Female
%K Male
%K Artificial Intelligence
%K Retrospective Studies
%K Phenomics: methods
%K Middle Aged
%K Aged
%K Risk Assessment: methods
%K Machine Learning
%K Carcinoma, Squamous Cell: pathology
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:41184299
%R 10.1038/s41467-025-65783-z
%U https://inrepo02.dkfz.de/record/305621