From Anatomy to Outcome: Linking Glioma Location Patterns to Survival Using Non-Negative Matrix Factorization
Continuous spatial phenotyping of IDH-wildtype gliomas using NMF captures prognostically relevant information not reflected by conventional markers. Integration of spatial patterns into prognostic models enhances risk stratification and supports the incorporation of detailed spatial analyses into radiologic workflows.
Authors
- Jessica Jesser (ORCID: https://orcid.org/0000-0002-1236-8828)
- Tim Hilgenfeld (ORCID: https://orcid.org/0000-0002-3458-8899)
- Julius M. Kernbach (ORCID: https://orcid.org/0000-0002-0256-1923)
- Irada Pflüger
- Haidar Alzaid (ORCID: https://orcid.org/0000-0002-1918-9187)
- Marianne Schell (ORCID: https://orcid.org/0000-0002-9754-1350)
- Sandro M. Krieg
- Martha Folty-Dumitru
- Wolfgang Wick
- Joel Kohler
- Felix Sahm
- Katharina Schregel
- Martin Bendszus
Institutions
- German Cancer Research Center (DE)
- Heidelberg University (DE)
- University Hospital Bonn (DE)
- University Hospital Heidelberg (DE)
Publication Details
- Journal
- Clinical Neuroradiology
- Published
- 2026-03-27
- DOI
- https://doi.org/10.1007/s00062-026-01642-8
- Primary Topic
- Glioma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00