OBJECTIVES: The aim of this study was to investigate whether radiomic analysis with random survival forests (RSFs) can predict overall survival from T1-weighted contrast-enhanced baseline magnetic resonance imaging (MRI) scans in a cohort of glioblastoma multiforme (GBM) patients with uniform treatment. MATERIALS AND METHODS: This retrospective study was approved by the institutional review board and informed consent was waived. The MRI scans from 66 patients with newly diagnosed GBM from a previous prospective study were analyzed. Tumors were segmented manually on contrast-enhanced 3-dimensional T1-weighted images. Using these segmentations, P = 208 quantitative image features characterizing tumor shape, signal intensity, and texture were calculated in an automated fashion. On this data set, an RSF was trained using 10-fold cross validation to establish a link between image features and overall survival, and the individual risk for each patient was predicted. The mean concordance index was assessed as a measure of prediction accuracy. Association of individual risk with overall survival was assessed using Kaplan-Meier analysis and a univariate proportional hazards model. RESULTS: Mean overall survival was 14 months (range, 0.8-85 months). Mean concordance index of the 10-fold cross-validated RSF was 0.67. Kaplan-Meier analysis clearly distinguished 2 patient groups with high and low predicted individual risk (P = 5.5 × 10). Low predicted individual mortality was found to be a favorable prognostic factor for overall survival in a univariate Cox proportional hazards model (hazards ratio, 1.038; 95% confidence interval, 1.015-1.062; P = 0.0059). CONCLUSIONS: This study demonstrates that baseline MRI in GBM patients contains prognostic information, which can be accessed by radiomic analysis using RSFs.
OBJECTIVES: The aim of this study was to investigate whether radiomic analysis with random survival forests (RSFs) can predict overall survival from T1-weighted contrast-enhanced baseline magnetic resonance imaging (MRI) scans in a cohort of glioblastoma multiforme (GBM) patients with uniform treatment. MATERIALS AND METHODS: This retrospective study was approved by the institutional review board and informed consent was waived. The MRI scans from 66 patients with newly diagnosed GBM from a previous prospective study were analyzed. Tumors were segmented manually on contrast-enhanced 3-dimensional T1-weighted images. Using these segmentations, P = 208 quantitative image features characterizing tumor shape, signal intensity, and texture were calculated in an automated fashion. On this data set, an RSF was trained using 10-fold cross validation to establish a link between image features and overall survival, and the individual risk for each patient was predicted. The mean concordance index was assessed as a measure of prediction accuracy. Association of individual risk with overall survival was assessed using Kaplan-Meier analysis and a univariate proportional hazards model. RESULTS: Mean overall survival was 14 months (range, 0.8-85 months). Mean concordance index of the 10-fold cross-validated RSF was 0.67. Kaplan-Meier analysis clearly distinguished 2 patient groups with high and low predicted individual risk (P = 5.5 × 10). Low predicted individual mortality was found to be a favorable prognostic factor for overall survival in a univariate Cox proportional hazards model (hazards ratio, 1.038; 95% confidence interval, 1.015-1.062; P = 0.0059). CONCLUSIONS: This study demonstrates that baseline MRI in GBM patients contains prognostic information, which can be accessed by radiomic analysis using RSFs.
Authors: Juan Jiménez-Sánchez; Álvaro Martínez-Rubio; Anton Popov; Julián Pérez-Beteta; Youness Azimzade; David Molina-García; Juan Belmonte-Beitia; Gabriel F Calvo; Víctor M Pérez-García Journal: PLoS Comput Biol Date: 2021-02-10 Impact factor: 4.475
Authors: J Pérez-Beteta; D Molina-García; M Villena; M J Rodríguez; C Velásquez; J Martino; B Meléndez-Asensio; Á Rodríguez de Lope; R Morcillo; J M Sepúlveda; A Hernández-Laín; A Ramos; J A Barcia; P C Lara; D Albillo; A Revert; E Arana; V M Pérez-García Journal: AJNR Am J Neuroradiol Date: 2019-03-28 Impact factor: 3.825
Authors: Manoj Mannil; Jakob M Burgstaller; Arjun Thanabalasingam; Sebastian Winklhofer; Michael Betz; Ulrike Held; Roman Guggenberger Journal: Skeletal Radiol Date: 2018-03-01 Impact factor: 2.199