BACKGROUND: Local response prediction for brain metastases (BM) after stereotactic radiosurgery (SRS) is challenging, particularly for smaller BM, as existing criteria are based solely on unidimensional measurements. This investigation sought to determine whether radiomic features provide additional value to routinely available clinical and dosimetric variables to predict local recurrence following SRS. METHODS: Analyzed were 408 BM in 87 patients treated with SRS. A total of 440 radiomic features were extracted from the tumor core and the peritumoral regions, using the baseline pretreatment volumetric post-contrast T1 (T1c) and volumetric T2 fluid-attenuated inversion recovery (FLAIR) MRI sequences. Local tumor progression was determined based on Response Assessment in Neuro-Oncology‒BM criteria, with a maximum axial diameter growth of >20% on the follow-up T1c indicating local failure. The top radiomic features were determined based on resampled random forest (RF) feature importance. An RF classifier was trained using each set of features and evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: The addition of any one of the top 10 radiomic features to the set of clinical features resulted in a statistically significant (P < 0.001) increase in the AUC. An optimized combination of radiomic and clinical features resulted in a 19% higher resampled AUC (mean = 0.793; 95% CI = 0.792-0.795) than clinical features alone (0.669, 0.668-0.671). CONCLUSIONS: The increase in AUC of the RF classifier, after incorporating radiomic features, suggests that quantitative characterization of tumor appearance on pretreatment T1c and FLAIR adds value to known clinical and dosimetric variables for predicting local failure.
BACKGROUND: Local response prediction for brain metastases (BM) after stereotactic radiosurgery (SRS) is challenging, particularly for smaller BM, as existing criteria are based solely on unidimensional measurements. This investigation sought to determine whether radiomic features provide additional value to routinely available clinical and dosimetric variables to predict local recurrence following SRS. METHODS: Analyzed were 408 BM in 87 patients treated with SRS. A total of 440 radiomic features were extracted from the tumor core and the peritumoral regions, using the baseline pretreatment volumetric post-contrast T1 (T1c) and volumetric T2 fluid-attenuated inversion recovery (FLAIR) MRI sequences. Local tumor progression was determined based on Response Assessment in Neuro-Oncology‒BM criteria, with a maximum axial diameter growth of >20% on the follow-up T1c indicating local failure. The top radiomic features were determined based on resampled random forest (RF) feature importance. An RF classifier was trained using each set of features and evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: The addition of any one of the top 10 radiomic features to the set of clinical features resulted in a statistically significant (P < 0.001) increase in the AUC. An optimized combination of radiomic and clinical features resulted in a 19% higher resampled AUC (mean = 0.793; 95% CI = 0.792-0.795) than clinical features alone (0.669, 0.668-0.671). CONCLUSIONS: The increase in AUC of the RF classifier, after incorporating radiomic features, suggests that quantitative characterization of tumor appearance on pretreatment T1c and FLAIR adds value to known clinical and dosimetric variables for predicting local failure.
Authors: Nicholas J Tustison; Brian B Avants; Philip A Cook; Yuanjie Zheng; Alexander Egan; Paul A Yushkevich; James C Gee Journal: IEEE Trans Med Imaging Date: 2010-04-08 Impact factor: 10.048
Authors: Priscilla K Brastianos; Scott L Carter; Gad Getz; William C Hahn; Sandro Santagata; Daniel P Cahill; Amaro Taylor-Weiner; Robert T Jones; Eliezer M Van Allen; Michael S Lawrence; Peleg M Horowitz; Kristian Cibulskis; Keith L Ligon; Josep Tabernero; Joan Seoane; Elena Martinez-Saez; William T Curry; Ian F Dunn; Sun Ha Paek; Sung-Hye Park; Aaron McKenna; Aaron Chevalier; Mara Rosenberg; Frederick G Barker; Corey M Gill; Paul Van Hummelen; Aaron R Thorner; Bruce E Johnson; Mai P Hoang; Toni K Choueiri; Sabina Signoretti; Carrie Sougnez; Michael S Rabin; Nancy U Lin; Eric P Winer; Anat Stemmer-Rachamimov; Matthew Meyerson; Levi Garraway; Stacey Gabriel; Eric S Lander; Rameen Beroukhim; Tracy T Batchelor; Jose Baselga; David N Louis Journal: Cancer Discov Date: 2015-09-26 Impact factor: 39.397
Authors: Jay S Detsky; Julia Keith; John Conklin; Sean Symons; Sten Myrehaug; Arjun Sahgal; Chinthaka C Heyn; Hany Soliman Journal: J Neurooncol Date: 2017-07-03 Impact factor: 4.130
Authors: Anna-Katharina Meißner; Robin Gutsche; Norbert Galldiks; Martin Kocher; Stephanie T Jünger; Marie-Lisa Eich; Manuel Montesinos-Rongen; Anna Brunn; Martina Deckert; Christina Wendl; Wolfgang Dietmaier; Roland Goldbrunner; Maximilian I Ruge; Cornelia Mauch; Nils-Ole Schmidt; Martin Proescholdt; Stefan Grau; Philipp Lohmann Journal: Neuro Oncol Date: 2022-08-01 Impact factor: 13.029
Authors: Zhigang Yuan; Marissa Frazer; Anupam Rishi; Kujtim Latifi; Michal R Tomaszewski; Eduardo G Moros; Vladimir Feygelman; Seth Felder; Julian Sanchez; Sophie Dessureault; Iman Imanirad; Richard D Kim; Louis B Harrison; Sarah E Hoffe; Geoffrey G Zhang; Jessica M Frakes Journal: Rep Pract Oncol Radiother Date: 2021-02-25
Authors: Hae Young Kim; Se Jin Cho; Leonard Sunwoo; Sung Hyun Baik; Yun Jung Bae; Byung Se Choi; Cheolkyu Jung; Jae Hyoung Kim Journal: Neurooncol Adv Date: 2021-07-01