Tumor morphology on CT radiomics is largely driven by the local anatomical environment, not the primary tumor type
In a large, multicenter cohort, tumors exhibited distinct morphological clustering. These clusters did not align with primary tumor sites (ARI = 0.04). Stronger associations emerged between morphological clusters and the local anatomical environment (ARI = 0.37). Stratification by lesion type revealed even stronger associations between local anatomical context and solid organ metastases (ARI = 0.60).
Authors
- S. Benson (ORCID: https://orcid.org/0000-0003-4819-779X)
- Kalina Chupetlovska (ORCID: https://orcid.org/0000-0002-1183-7426)
- Warissara Jutidamrongphan (ORCID: https://orcid.org/0000-0002-4350-9988)
- Federica Landolfi (ORCID: https://orcid.org/0000-0002-2208-2559)
- Andrea Delli Pizzi (ORCID: https://orcid.org/0000-0002-2011-3753)
- Mohamed A. Abdelatty (ORCID: https://orcid.org/0000-0003-2740-4657)
- Peter Matkulčík (ORCID: https://orcid.org/0000-0001-7428-1202)
- Sajjad Rostami
- Zuhir Bodalal (ORCID: https://orcid.org/0000-0002-2617-8128)
- Francesca Castagnoli (ORCID: https://orcid.org/0000-0003-2407-7451)
- Geerard L. Beets (ORCID: https://orcid.org/0000-0002-1671-9912)
- George Agrotis
- Hannah W. Stutterheim
- Olga Maxouri (ORCID: https://orcid.org/0000-0002-4709-1929)
- Corentin Guérendel (ORCID: https://orcid.org/0009-0001-2343-0922)
- Liliana Petrychenko
- Diana Ivonne Rodríguez Sánchez
- Francesco Marcello Aricò
- Nino Boveradze
- Nicolo Gennaro
- Petur Snaebjornsson
- Alba Salgado-Parente
- Marleen Soliman
- Stephan Ursprung
- Eun Kyoung Hong
Institutions
- Northwestern University (US)
- University of Bern (CH)
- Institute of Cancer Research (GB)
- Cairo University (EG)
- University of Iceland (IS)
- Palo Alto University (US)
- University of Southern Denmark (DK)
- Instituto Cajal (ES)
- Swedish American Hospital (US)
- Maastricht University Medical Centre (NL)
- University Hospital of Bern (CH)
- The Netherlands Cancer Institute (NL)
- Maastricht University (NL)
- University of Chieti-Pescara (IT)
- Ente Ospedaliero Cantonale (CH)
- University Hospital Brno (CZ)
- Oncode Institute (NL)
- Royal Marsden Hospital (GB)
- University Children's Hospital Tübingen (DE)
- Azienda Ospedaliera Universitaria Policlinico "G. Martino" (IT)
- Maastro Clinic (NL)
- University of Tübingen (DE)
- Sapienza University of Rome (IT)
- University of Amsterdam (NL)
- Stanford University (US)
Publication Details
- Journal
- European Radiology Experimental
- Published
- 2026-03-12
- DOI
- https://doi.org/10.1186/s41747-026-00691-5
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00