Optimizing MRI sequence selection for glioma classification: a radiomics-based analysis of WHO CNS grade, final pathological diagnosis, and IDH status
La radiologia medica · 2026
DOI: 10.1007/s11547-026-02218-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift La radiologia medica, 2026. Verfasst von Kimberly Amador und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Clinical Neurosciences, University of Calgary, Calgary, Canada. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain Neoplasms, Glioma. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Universitätsklinikum Hamburg-Eppendorf (UKE).
Abstract (Originalsprache)
Background
Multi-sequence MRI protocols for glioma classification are resource-intensive, prompting the need to identify optimal, potentially reduced imaging protocols.
Purpose
To evaluate the diagnostic utility of individual MRI sequences (ASL, DWI, FLAIR, SWI, T1w, T2w) for classifying WHO CNS grade (II, III, IV), final pathological diagnosis (glioblastoma vs. astrocytoma), and IDH status (mutated, wildtype, IDH1) using radiomic features and machine learning. Materials and methods We analyzed data from 501 patients with diagnosed brain cancer from the UCSF-PDGM dataset, by extracting radiomics features from all available imaging sequences and training uni- and multi-sequence machine learning models (ASL, DWI, FLAIR, SWI, T1w, T2w) for the three outcome tasks of interest. Performance metrics (accuracy, sensitivity, F1-score) were derived for each task, alongside feature selection frequencies.
Results
The uni-sequence machine learning models using FLAIR imaging features excelled for WHO CNS grade classification (57.4% accuracy), ASL for final pathological diagnosis (81.5% accuracy), and T1w for IDH status classification (66.7% accuracy). Interestingly, the combination of all sequences did not lead to significant improvements compared to the best performing uni-sequence machine learning models for the three tasks. Regardless of the input sequence, the models consistently relied on similar features, such as shape and demographic variables ( e.g., patient age and tumor sphericity).
Conclusion
Single sequences, such as FLAIR, ASL, and T1w, achieved the highest individual accuracies in the radiomics models for classification of tumor grade, final diagnosis, and IDH status, and may inform the design of more streamlined imaging protocols.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Radiology and Clinical Neurosciences, University of Calgary, Calgary, Canada.
- Department of Diagnostic and Interventional Neuroradiology, University Hospital Hamburg-Eppendorf, Martinistr. 52, 20251, Hamburg, Germany.
- Department of Diagnostic and Interventional Neuroradiology, University Hospital Hamburg-Eppendorf, Martinistr. 52, 20251, Hamburg, Germany. t.lindner@uke.de.
Förderung
- Deutsche Forschungsgemeinschaft
- Universitätsklinikum Hamburg-Eppendorf (UKE)
Zitieren
APA
Amador, K., Kniep, H., Fiehler, J., Forkert, N. D., & Lindner, T. (2026). Optimizing MRI sequence selection for glioma classification: a radiomics-based analysis of WHO CNS grade, final pathological diagnosis, and IDH status. La radiologia medica. https://doi.org/10.1007/s11547-026-02218-9
Vancouver
Amador K, Kniep H, Fiehler J, Forkert ND, Lindner T. Optimizing MRI sequence selection for glioma classification: a radiomics-based analysis of WHO CNS grade, final pathological diagnosis, and IDH status. La radiologia medica. 2026. doi:10.1007/s11547-026-02218-9
BibTeX
@article{Amador2026,
author = {Amador, Kimberly and Kniep, Helge and Fiehler, Jens and Forkert, Nils Daniel and Lindner, Thomas},
title = {Optimizing MRI sequence selection for glioma classification: a radiomics-based analysis of WHO CNS grade, final pathological diagnosis, and IDH status},
journal = {La radiologia medica},
year = {2026},
doi = {10.1007/s11547-026-02218-9}
}
EUVIMED