AI-powered spatial cell phenomics enhances risk stratification in non-small cell lung cancer
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% and 47% improvement in risk stratification in the two main non-small cell lung cancer subtypes, lung adenocarcinoma and squamous cell carcinoma, respectively, combining niche patterns with conventional cancer staging. Our results show that complex immune cell niche patterns identify potentially undertreated high-risk patients qualifying for adjuvant therapy. Our approach highlights the potential of artificial intelligence powered multiplex imaging analyses to better understand the contribution of the tumor microenvironment to cancer progression and to improve risk stratification and treatment selection in non-small cell lung cancer.
Authors
- Reinhard Büttner (ORCID: https://orcid.org/0000-0001-8806-4786)
- Lukas Ruff (ORCID: https://orcid.org/0000-0002-9707-297X)
- Kai Standvoss (ORCID: https://orcid.org/0000-0002-5739-6726)
- Il‐Kang Na (ORCID: https://orcid.org/0000-0001-9902-5424)
- Philipp Jurmeister (ORCID: https://orcid.org/0000-0001-7745-3794)
- Sharon Ruane
- Marco Frentsch (ORCID: https://orcid.org/0000-0003-3200-210X)
- Winfried Johannes Randerath (ORCID: https://orcid.org/0000-0002-5010-8461)
- Nikolaj Frost (ORCID: https://orcid.org/0000-0001-7452-7129)
- Matthias Heldwein (ORCID: https://orcid.org/0000-0002-2084-795X)
- Khosro Hekmat (ORCID: https://orcid.org/0000-0002-6479-8774)
- Alexander Quaas (ORCID: https://orcid.org/0000-0002-3537-6011)
- Georg Schlachtenberger (ORCID: https://orcid.org/0000-0001-7118-8432)
- Kyrill Boschung
- Cornelius Böhm (ORCID: https://orcid.org/0009-0007-3754-4182)
- Simon Schallenberg (ORCID: https://orcid.org/0000-0002-7897-7116)
- Frederick Klauschen (ORCID: https://orcid.org/0000-0002-9131-2389)
- Mihnea P. Dragomir (ORCID: https://orcid.org/0000-0002-5550-3516)
- Ulrich Keilholz (ORCID: https://orcid.org/0000-0001-6773-9406)
- David Horst (ORCID: https://orcid.org/0000-0003-4755-5743)
- Klaus-Robert Müller (ORCID: https://orcid.org/0000-0002-3861-7685)
- Maximilian Alber
- Gabriel Dernbach
- Sabine Merkelbach‐Bruse (ORCID: https://orcid.org/0000-0002-0312-5760)
- Philipp Keyl (ORCID: https://orcid.org/0000-0002-5472-4683)
- Angela Vasaturo (ORCID: https://orcid.org/0000-0001-7985-3820)
- Sandip Ghosh (ORCID: https://orcid.org/0009-0008-7342-1064)
- Corinna Friedrich (ORCID: https://orcid.org/0000-0002-5586-1989)
- Jens‐Carsten Rückert
Institutions
- German Cancer Research Center (DE)
- University of Cologne (DE)
- Oral Roberts University (US)
- Max Delbrück Center (DE)
- Heidelberg University (DE)
- Robert Koch Institute (DE)
- Humboldt-Universität zu Berlin (DE)
- Max Planck Institute for Informatics (DE)
- Cancer Research Center (US)
- Krankenhaus Bethanien (DE)
- Berlin Institute of Health at Charité - Universitätsmedizin Berlin (DE)
- Berliner Verkehrsbetriebe (Germany) (DE)
- University Hospital Cologne (DE)
- Berlin Institute for the Foundations of Learning and Data (DE)
- Technische Universität Berlin (DE)
- Freie Universität Berlin (DE)
- Charité - Universitätsmedizin Berlin (DE)
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1038/s41467-025-65783-z
- Citations
- 4
- Primary Topic
- Single-cell and spatial transcriptomics
- Type
- article
- Field-Weighted Citation Impact
- 3.22
Funders
- Bundesministerium für Bildung und Forschung
- Korea University
- Deutschen Konsortium für Translationale Krebsforschung
- Ministry of Science and ICT, South Korea
- Berlin Institute of Health
- Banting and Best Diabetes Centre, University of Toronto
- Institute for Information and Communications Technology Promotion
- Berlin Center for Machine Learning