Abstract 3449
Background
Early intracranial progression (ICP) reduce the efficacy of first line radiosurgery (SRS) for brain metastases. We aim to develop and validate a MR imaging-derived radiomic signature (RS) via deep learning approach for the prediction of 1-year disseminated ICP (DICP; more than or equal to 3 lesions and leptomeningeal carcinomatosis) in brain metastases patients treated with SRS.
Methods
A total of 1304 MRI-based radiomic features of pretreatment tumors were obtained from 208 patients with 451 lesions, who received first line SRS during August 2008 to January 2018. Variational autoencoder (VAE), trained with symmetric two encoded and decoded layers of neural network and 1,649,560 trainable parameters, was applied to reduce the dimensionality of radiomc features to 128 VAE-radiomic features. Penalized regression with 10-fold cross validation using least absolute shrinkage and selection operator performs features selection and construct RS to predict 1-year DICP events in train set of 150 patients, which was validated in test set of 58 patients. Harrell’s C-index was used to evaluate the discriminative ability of RS in both sets. The correlation of VAE-radiomic features and molecular features was analyzed by student t-test. Survival analysis was calculated using the Kaplan-Meier method.
Results
The RS yielded 1000 times bootstrapping corrected C-index of 0.746 and 0.747 for discrimination of 1-year DICP in the train and test cohorts, respectively. As for the subgroup of patients with lung (n = 175) and breast (n = 23) origin, the RS also showed good predictive performance with C-indices of 0.735 and 0.755, respectively. EGFR-mutation (n = 113) and ER (n = 22) status were associated with selected VAE-radiomic features No. 98 (p = 0.035) and No.127 (p = 0.44), respectively. Dichotomized risk category using RS of -0.769 (Youden index) as cut-off point yielded median overall survival of 57.7 months in low risk compared to 20.5 months in high risk group (p < 0.01).
Conclusions
The RS model provides a novel approach to predict 1-year DICP and survival in brain metastases receiving SRS, and is warranted to be integrated into GPA for optimal selection of patients treated with first line SRS.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
3088 - Spanish Survey of treatment recommendations for elderley patients with glioblastoma
Presenter: María Ángeles Vaz Salgado
Session: Poster Display session 1
Resources:
Abstract
3484 - Updated analysis of the National Registry of Nervous System Tumors in Spain (RETSINE). RETSINE: National Registry of Nervous System Tumors of the Spanish Research Group in Neuro-oncology (GEINO) and Spanish Infrequent and Orphan Tumors Group (GETHI)
Presenter: Isaac Ceballos Lenza
Session: Poster Display session 1
Resources:
Abstract
4737 - Development and validation of novel nomograms predicting survival of malignant ependymoma patients: A population-based study
Presenter: Alzhraa Abbas
Session: Poster Display session 1
Resources:
Abstract
4740 - Characteristics, incidence, and survival of primary cerebral lymphoma: A population based study
Presenter: Sherief Ghozy
Session: Poster Display session 1
Resources:
Abstract
5362 - Trends in Incidence and Survival Analyses of Adult-onset Medulloblastoma
Presenter: Feifei Lin
Session: Poster Display session 1
Resources:
Abstract
3868 - Meta of classical chemotherapy compared with high-dose chemotherapy combined with autologous stem cell transplantation in newly diagnosed medulloblastoma patients after radiotherapy
Presenter: Mengting Zhang
Session: Poster Display session 1
Resources:
Abstract
4446 - Effect of cumulative dose of maintenance temozolomide on overall survival in patients with high grade glia tumors: a single institution analysis
Presenter: Marta Nerone
Session: Poster Display session 1
Resources:
Abstract
5119 - Markers of systemic inflammation correlate with survival prognosis in patients with newly diagnosed brain metastases
Presenter: Angelika Starzer
Session: Poster Display session 1
Resources:
Abstract
3882 - Venous Thromboembolism and Intracranial Hemorrhage in Patients with High-grade Glioma
Presenter: Clara Borges
Session: Poster Display session 1
Resources:
Abstract
5152 - Comprehensive Geriatric Assessment (CGA) can categorize elderly glioblastoma (GBM) patients into three groups predicting survival: a monoinstitutional study
Presenter: Eleonora Bergo
Session: Poster Display session 1
Resources:
Abstract