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
3309 - Heat Shock Protein 90 chaperones and Protein Kinase D3 regulates androgen-independent prostate cancer development
Presenter: Attila Varga
Session: Poster Display session 1
Resources:
Abstract
3441 - The SWI/SNF driven reprograming for the AR cistrome is NSD2 dependent
Presenter: Katia Ruggero
Session: Poster Display session 1
Resources:
Abstract
1659 - IGF1R inhibition affects the survival of HT29 cancer cells by alterations of the TLR9- and autophagy signaling
Presenter: Györgyi Műzes
Session: Poster Display session 1
Resources:
Abstract
1379 - Characterization of atypical dMMR (deficient MisMatch Repair) tumors: a study from a large cohort of 4948 cases
Presenter: Marion Jaffrelot
Session: Poster Display session 1
Resources:
Abstract
1657 - Modulation of TLR9-dependent autophagy response via inhibition of c-Met signaling influences the survival of HT29 cancer cells
Presenter: Ferenc Sipos
Session: Poster Display session 1
Resources:
Abstract
3045 - Positive Feedback Activation of Notch Signal by Obesity Enhances Colorectal Tumorigenicity
Presenter: Dake Chu
Session: Poster Display session 1
Resources:
Abstract
2285 - The Pathological and Functional Roles of BRPF1 in Hepatocellular Carcinoma
Presenter: Lai Hung Carol Cheng
Session: Poster Display session 1
Resources:
Abstract
3210 - Protein tyrosine phosphatase non-receptor type 3 (PTPN3) could be a new therapeutic target for pancreatic cancer.
Presenter: Akio Yamasaki
Session: Poster Display session 1
Resources:
Abstract
3920 - A Novel bispecific BCMAxCD3 T cell engaging antibody that treat multiple myeloma (MM) with minimal cytokine serection
Presenter: Zhenyu Li
Session: Poster Display session 1
Resources:
Abstract
2691 - Quantitative spatial profiling of lymphocyte-activation gene 3 (LAG-3)/major histocompatibility complex class II (MHC II) interaction in gastric and urothelial tumors
Presenter: Cyrus Hedvat
Session: Poster Display session 1
Resources:
Abstract