MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery
Journal
Journal of Neuro-Oncology
Date Issued
2022-09
Author(s)
Speckter, Herwin
Radulovic,Marko
Vranes, Velicko
Joaquin, Johanna
Hernandez, Wenceslao
Mota, Angel
Bido, Jose
Hernandez, Giancarlo
Rivera, Diones
Suazo, Luis
Valenzuela, Santiago
Stoeter, Peter
Abstract
Purpose This report presents the frst investigation of the radiomics value in predicting the meningioma volumetric response
to gamma knife radiosurgery (GKRS).
Methods The retrospective study included 93 meningioma patients imaged by three Tesla MRI. Tumor morphology was
quantifed by calculating 337 shape, frst- and second-order radiomic features from MRI obtained before GKRS. Analysis
was performed on original 3D MR images and after their laplacian of gaussian (LoG), logarithm and exponential fltering.
The prediction performance was evaluated by Pearson correlation, linear regression and ROC analysis, with meningioma
volume change per month as the outcome.
Results Sixty calculated features signifcantly correlated with the outcome. The feature selection based on LASSO and
multivariate regression started from all available 337 radiomic and 12 non-radiomic features. It selected LoG-sigma-1-0-
mm-3D_frstorder_InterquartileRange and logarithm_ngtdm_Busyness as the predictively most robust and non-redundant
features. The radiomic score based on these two features produced an AUC=0.81. Adding the non-radiomic karnofsky performance status (KPS) to the score has increased the AUC to 0.88. Low values of the radiomic score defned a homogeneous
subgroup of 50 patients with consistent absence (0%) of tumor progression.
Conclusion This is the frst report of a strong association between MRI radiomic features and volumetric meningioma
response to radiosurgery. The clinical importance of the early and reliable prediction of meningioma responsiveness to
radiosurgery is based on its potential to aid individualized therapy decision making.
to gamma knife radiosurgery (GKRS).
Methods The retrospective study included 93 meningioma patients imaged by three Tesla MRI. Tumor morphology was
quantifed by calculating 337 shape, frst- and second-order radiomic features from MRI obtained before GKRS. Analysis
was performed on original 3D MR images and after their laplacian of gaussian (LoG), logarithm and exponential fltering.
The prediction performance was evaluated by Pearson correlation, linear regression and ROC analysis, with meningioma
volume change per month as the outcome.
Results Sixty calculated features signifcantly correlated with the outcome. The feature selection based on LASSO and
multivariate regression started from all available 337 radiomic and 12 non-radiomic features. It selected LoG-sigma-1-0-
mm-3D_frstorder_InterquartileRange and logarithm_ngtdm_Busyness as the predictively most robust and non-redundant
features. The radiomic score based on these two features produced an AUC=0.81. Adding the non-radiomic karnofsky performance status (KPS) to the score has increased the AUC to 0.88. Low values of the radiomic score defned a homogeneous
subgroup of 50 patients with consistent absence (0%) of tumor progression.
Conclusion This is the frst report of a strong association between MRI radiomic features and volumetric meningioma
response to radiosurgery. The clinical importance of the early and reliable prediction of meningioma responsiveness to
radiosurgery is based on its potential to aid individualized therapy decision making.
Subjects
File(s)![Thumbnail Image]()
Loading...
Name
Journal-of-Neuro-Oncology-2022-MRI-radiomics-for-volumetric-response-in-meningiomas-paid2.pdf
Size
933.67 KB
Format
Adobe PDF
Checksum
(MD5):d20d7ea848918a0be2e8a43c7948e165