Integrated models incorporating radiologic and radiomic features predict meningioma grade, local failure, and overall survival
-
- Olivier Morin
- Department of Radiation Oncology, University of California San Francisco, California
-
- William C Chen
- Department of Radiation Oncology, University of California San Francisco, California
-
- Farshad Nassiri
- Department of Surgery, University of Toronto, Toronto, Ontario, Canada
-
- Matthew Susko
- Department of Radiation Oncology, University of California San Francisco, California
-
- Stephen T Magill
- Department of Neurological Surgery, University of California San Francisco, California
-
- Harish N Vasudevan
- Department of Radiation Oncology, University of California San Francisco, California
-
- Ashley Wu
- Department of Radiation Oncology, University of California San Francisco, California
-
- Martin Vallières
- Department of Radiation Oncology, University of California San Francisco, California
-
- Efstathios D Gennatas
- Department of Radiation Oncology, University of California San Francisco, California
-
- Gilmer Valdes
- Department of Radiation Oncology, University of California San Francisco, California
-
- Melike Pekmezci
- Department of Pathology, University of California San Francisco, California
-
- Paula Alcaide-Leon
- Department of Radiology and Biomedical Imaging, University of California San Francisco, California
-
- Abrar Choudhury
- Department of Radiation Oncology, University of California San Francisco, California
-
- Yannet Interian
- Department of Radiation Oncology, University of California San Francisco, California
-
- Siavash Mortezavi
- Department of Radiation Oncology, University of California San Francisco, California
-
- Kerem Turgutlu
- Department of Radiation Oncology, University of California San Francisco, California
-
- Nancy Ann Oberheim Bush
- Department of Neurological Surgery, University of California San Francisco, California
-
- Timothy D Solberg
- Department of Radiation Oncology, University of California San Francisco, California
-
- Steve E Braunstein
- Department of Radiation Oncology, University of California San Francisco, California
-
- Penny K Sneed
- Department of Radiation Oncology, University of California San Francisco, California
-
- Arie Perry
- Department of Pathology, University of California San Francisco, California
-
- Gelareh Zadeh
- Department of Radiation Oncology, University of California San Francisco, California
-
- Michael W McDermott
- Department of Neurological Surgery, University of California San Francisco, California
-
- Javier E Villanueva-Meyer
- Department of Radiology and Biomedical Imaging, University of California San Francisco, California
-
- David R Raleigh
- Department of Radiation Oncology, University of California San Francisco, California
説明
<jats:title>Abstract</jats:title><jats:sec><jats:title>Background</jats:title><jats:p>We investigated prognostic models based on clinical, radiologic, and radiomic feature to preoperatively identify meningiomas at risk for poor outcomes.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>Retrospective review was performed for 303 patients who underwent resection of 314 meningiomas (57% World Health Organization grade I, 35% grade II, and 8% grade III) at two independent institutions, which comprised primary and external datasets. For each patient in the primary dataset, 16 radiologic and 172 radiomic features were extracted from preoperative magnetic resonance images, and prognostic features for grade, local failure (LF) or overall survival (OS) were identified using the Kaplan–Meier method, log-rank tests and recursive partitioning analysis. Regressions and random forests were used to generate and test prognostic models, which were validated using the external dataset.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Multivariate analysis revealed that apparent diffusion coefficient hypointensity (HR 5.56, 95% CI 2.01–16.7, P = .002) was associated with high grade meningioma, and low sphericity was associated both with increased LF (HR 2.0, 95% CI 1.1–3.5, P = .02) and worse OS (HR 2.94, 95% CI 1.47–5.56, P = .002). Both radiologic and radiomic predictors of adverse meningioma outcomes were significantly associated with molecular markers of aggressive meningioma biology, such as somatic mutation burden, DNA methylation status, and FOXM1 expression. Integrated prognostic models combining clinical, radiologic, and radiomic features demonstrated improved accuracy for meningioma grade, LF, and OS (area under the curve 0.78, 0.75, and 0.78, respectively) compared to models based on clinical features alone.</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>Preoperative radiologic and radiomic features such as apparent diffusion coefficient and sphericity can predict tumor grade, LF, and OS in patients with meningioma.</jats:p></jats:sec>
収録刊行物
-
- Neuro-Oncology Advances
-
Neuro-Oncology Advances 1 (1), 2019-05-01
Oxford University Press (OUP)
