Peer-Reviewed Publication
Nat Commun2025;16(1):9701.November 3, 2025Journal Article
AI-powered spatial cell phenomics enhances risk stratification in non-small cell lung cancer.
Simon Schallenberg1, Gabriel Dernbach1,2, Sharon Ruane2, Philipp Jurmeister3, Cornelius Böhm2, Kai Standvoss2, Sandip Ghosh2, Marco Frentsch4,5, Mihnea P Dragomir1,6,7, Philipp G Keyl8, Corinna Friedrich1,9, Il-Kang Na4,5,6,10, Sabine Merkelbach-Bruse11, Alexander Quaas11, Nikolaj Frost12, Kyrill Boschung13, Winfried Randerath13, Georg Schlachtenberger14, Matthias Heldwein14, Ulrich Keilholz7,15, Khosro Hekmat14, Jens-Carsten Rückert16, Reinhard Büttner11, Angela Vasaturo17, David Horst1, Lukas Ruff2, Maximilian Alber1,2, Klaus-Robert Müller18,19,20,21, Frederick Klauschen22,23,24,25,26
1Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.
2Aignostics, Berlin, Germany.
3Institute of Pathology, Ludwig-Maximilians-Universität München, Munich, Germany.
4Department of Hematology, Oncology, and Tumor Immunology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
5BIH Center for Regenerative Therapies (BCRT), Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany.
6German Cancer Consortium (DKTK), partner site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany.
7Berlin Institute of Health (BIH), Berlin, Germany.
8BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany.
9Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Proteomics Platform, Berlin, Germany.
10ECRC Experimental and Clinical Research Center, Charite - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
11Institute of Pathology, University Hospital Cologne, Köln, Germany.
12Department of Infectious Diseases and Respiratory Medicine, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.
13Bethanien Hospital, Clinic of Pneumology and Allergology, Center for Sleep Medicine and Respiratory Care, Institute of Pneumology at the University of Cologne, Solingen, Germany.
14Department of Cardiothoracic Surgery, University Hospital Cologne, Solingen, Germany.
15Charité Comprehensive Cancer Center, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.
16Department of General, Visceral, Vascular and Thoracic Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany.
17Ultivue, Berlin, Germany.
18BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany. klaus-robert.mueller@tu-berlin.de.
19Machine Learning Group, Technische Universität Berlin, Berlin, Germany. klaus-robert.mueller@tu-berlin.de.
20Max-Planck-Institute for Informatics, Saarbrücken, Germany. klaus-robert.mueller@tu-berlin.de.
21Department of Artificial Intelligence, Korea University, Seoul, South Korea. klaus-robert.mueller@tu-berlin.de.
22Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany. frederick.klauschen@med.uni-muenchen.de.
23Institute of Pathology, Ludwig-Maximilians-Universität München, Munich, Germany. frederick.klauschen@med.uni-muenchen.de.
24BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany. frederick.klauschen@med.uni-muenchen.de.
25German Cancer Consortium (DKTK), partner site Munich, and German Cancer Research Center (DKFZ), Heidelberg, Germany. frederick.klauschen@med.uni-muenchen.de.
26Bavarian Cancer Research Center (BZKF), Munich, Germany. frederick.klauschen@med.uni-muenchen.de.
Abstract
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 microenvironm…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans