TY  - JOUR
AU  - Yun, Yeong Chul
AU  - Jende, Johann M E
AU  - Holz, Katharina
AU  - Wolf, Sabine
AU  - Garhöfer, Freya
AU  - Hohmann, Anja
AU  - Vollmuth, Philipp
AU  - Bendszus, Martin
AU  - Schlemmer, Heinz-Peter
AU  - Sahm, Felix
AU  - Heiland, Sabine
AU  - Wick, Wolfgang
AU  - Venkataramani, Varun
AU  - Kurz, Felix Tobias
TI  - Radiomics features from the peritumoral region can be associated with the epilepsy status of glioblastoma patients.
JO  - Frontiers in oncology
VL  - 15
SN  - 2234-943X
CY  - Lausanne
PB  - Frontiers Media
M1  - DKFZ-2025-01889
SP  - 1587745
PY  - 2025
N1  - #EA:E010#LA:E010#
AB  - Identifying radiomics features that help predict whether glioblastoma patients are prone to developing epilepsy may contribute to an improvement of preventive treatment and a better understanding of the underlying pathophysiology.In this retrospective study, 3-T MRI data of 451 pretreatment glioblastoma patients (mean age: 61.2 ± 11.8 years; 268 men, 183 women) were analyzed. Three hundred thirty-six patients reported no epilepsy, while 115 patients were diagnosed with symptomatic epilepsy. A total of 1,546 radiomics features were extracted from contrast-enhancing tumor, peritumoral regions, and normal-appearing white matter as regions of interest using PyRadiomics. The dataset was initially split into a training (70
KW  - MRI (Other)
KW  - epilepsy (Other)
KW  - glioblastoma (Other)
KW  - machine learning (Other)
KW  - radiomics (Other)
KW  - radiomics features from peritumoral (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:40927524
C2  - pmc:PMC12416087
DO  - DOI:10.3389/fonc.2025.1587745
UR  - https://inrepo02.dkfz.de/record/304500
ER  -