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
4242 - HIV, HBV and HCV screening practices in oncology: a cross-sectional interregional survey
Presenter: Isabelle Poizot-Martin
Session: Poster Display session 1
Resources:
Abstract
1267 - Genetic landscape of KEAP1 and NFE2L2 mutated cancers from the AACR GENIE database
Presenter: Mark Zaki
Session: Poster Display session 1
Resources:
Abstract
878 - β-arrestin1 is involved in the Ras-induced malignant transformation
Presenter: Takashi Shibano
Session: Poster Display session 1
Resources:
Abstract
4143 - Incidence of second cancer among PLWHIV: retrospective observational study of a series of 601 patients in the French CANCERVIH network
Presenter: Jean-Philippe Spano
Session: Poster Display session 1
Resources:
Abstract
5145 - A challenging task – Identifying carcinoma of unknown primary (CUP) patients according to ESMO guidelines: the CUPISCO trial experience
Presenter: Chantal Pauli
Session: Poster Display session 1
Resources:
Abstract
1737 - Incidence and Outcome of chronic lymphocytic leukemia with Deletion 17p: An Indian experience; challenges and opportunities
Presenter: Ajay Gogia
Session: Poster Display session 1
Resources:
Abstract
2596 - Driving solo? Investigation into collaborating mutations in SDH-deficient neoplasia
Presenter: Jonathan Killian
Session: Poster Display session 1
Resources:
Abstract
1499 - The potential of a novel antiangiogenic VEGFR1-D2 binding peptide in oncology therapeutics
Presenter: Afsaneh Sadre Momtaz
Session: Poster Display session 1
Resources:
Abstract
1775 - First-in-human phase I study of TAS-117, an allosteric AKT inhibitor, in patients with advanced solid tumors
Presenter: Mayu Yunokawa
Session: Poster Display session 1
Resources:
Abstract
4584 - First-in-human study of ABBV-621 in patients (pts) with previously treated sold tumors: Dose-optimization cohorts
Presenter: Emiliano Calvo
Session: Poster Display session 1
Resources:
Abstract