Radiogenomics and radiomics of skull base chordoma: Classification of novel radiomic subgroups and prediction of genetic signatures and clinical outcomes
Neuro-Oncology · 14.10.2025 · 27 (9) · 2472-2483
DOI: 10.1093/neuonc/noaf131 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neuro-Oncology, online erschienen am 02.06.2025. Verfasst von Zachary C Gersey und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurological Surgery, University of Miami, Miami, FL, USA. Hauptthemen laut MEDLINE: Chordoma, Skull Base Neoplasms, Magnetic Resonance Imaging, Genomics. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Chordomas are rare, aggressive tumors of notochordal origin, commonly affecting the spine and skull base. Skull base chordomas (SBCs) comprise approximately 39% of cases, with an incidence of less than 1 per million annually in the United States. Prognosis remains poor due to resistance to chemotherapy, often requiring extensive surgical resection and adjuvant radiotherapy. Current classification methods based on chromosomal deletions are invasive and costly, presenting a need for alternative diagnostic tools. Radiomics allows for noninvasive SBC diagnosis and treatment planning.
Methods
We developed and validated radiomic-based models using MRI data to predict overall survival (OS) and progression-free survival following surgery (PFSS) in SBC patients. Machine-learning classifiers, including eXtreme Gradient Boosting (XGBoost), were employed along with feature selection techniques. Unsupervised clustering identified radiomic-based subgroups, which were correlated with chromosomal deletions and clinical outcomes.
Results
Our XGBoost model demonstrated superior predictive performance, achieving an area under the curve (AUC) of 83.33% for OS and 80.36% for PFSS, outperforming other classifiers. Radiomic clustering revealed two SBC groups with differing survival and molecular characteristics, strongly correlating with chromosomal deletion profiles. These findings indicate that radiomics can noninvasively characterize SBC phenotypes and stratify patients by prognosis.
Conclusions
Radiomics shows promise as a reliable, noninvasive tool for the prognostication and classification of SBCs, minimizing the need for invasive genetic testing and supporting personalized treatment strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurological Surgery, University of Miami, Miami, FL, USA.
- Department of Neurological Surgery, UPMC, Pittsburgh, PA, USA.
- Hillman Cancer Center, University of Pittsburgh Medical Center, Pittsburgh, PA, USA.
- Department of Radiology, University of Pittsburgh, Pittsburgh, PA, USA.
- University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
- Department of Otolaryngology, University of Pittsburgh, Pittsburgh, PA, USA.
ORCID-Profile: Zachary C Gersey
Zitieren
APA
Gersey, Z. C., Zenkin, S., Mamindla, P., Amjadzadeh, M., Ak, M., Plute, T., Peddagangireddy, V., Abdallah, H., Muthiah, N., Wang, E. W., Snyderman, C., Gardner, P. A., Colen, R. R., & Zenonos, G. A. (2025). Radiogenomics and radiomics of skull base chordoma: Classification of novel radiomic subgroups and prediction of genetic signatures and clinical outcomes. Neuro-Oncology, 27(9), 2472-2483. https://doi.org/10.1093/neuonc/noaf131
Vancouver
Gersey ZC, Zenkin S, Mamindla P, Amjadzadeh M, Ak M, Plute T, et al. Radiogenomics and radiomics of skull base chordoma: Classification of novel radiomic subgroups and prediction of genetic signatures and clinical outcomes. Neuro-Oncology. 2025;27(9):2472-2483. doi:10.1093/neuonc/noaf131
BibTeX
@article{Gersey2025,
author = {Gersey, Zachary C and Zenkin, Serafettin and Mamindla, Priyadarshini and Amjadzadeh, Mohammadreza and Ak, Murat and Plute, Tritan and Peddagangireddy, Vishal and Abdallah, Hussein and Muthiah, Nallammai and Wang, Eric W and Snyderman, Carl and Gardner, Paul A and Colen, Rivka R and Zenonos, Georgios A},
title = {Radiogenomics and radiomics of skull base chordoma: Classification of novel radiomic subgroups and prediction of genetic signatures and clinical outcomes},
journal = {Neuro-Oncology},
year = {2025},
volume = {27},
number = {9},
pages = {2472--2483},
doi = {10.1093/neuonc/noaf131}
}
EUVIMED