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
4615 - Proteomic Profiling Identifies Molecular Basis of Adverse Event to BPM31510 Exposure: Rationale for Comprehensive Molecular Pharmacodynamics (PD) in Phase 1 Clinical Trial Design
Presenter: Vivek Subbiah
Session: Poster Display session 1
Resources:
Abstract
5052 - Identification of first-in-class, naturally occurring LAG3 checkpoint inhibitor
Presenter: Gennady Bratslavsky
Session: Poster Display session 1
Resources:
Abstract
5336 - Are Epigenetic therapies modifying sensitivity to conventional chemotherapy?
Presenter: Alexandra Bizot
Session: Poster Display session 1
Resources:
Abstract
5739 - Oncogenic mutations at the dimer interface of EGFR lead to formation of covalent homo-dimers and allosteric activation of the kinase domain: A mechanism which alters the selectivity profile of oncogenic EGFR.
Presenter: Elizabeth Buck
Session: Poster Display session 1
Resources:
Abstract
5492 - Basic selective estrogen receptor degraders (B-SERDs) in combination with novel BET inhibitors in ER+ breast cancer
Presenter: Rui Xiong
Session: Poster Display session 1
Resources:
Abstract
5965 - EPI-7386 is a novel N-terminal domain androgen receptor inhibitor for the treatment of prostate cancer
Presenter: Ronan Le Moigne
Session: Poster Display session 1
Resources:
Abstract
3582 - AVID200 neutralizes TGF-beta1 and -beta3, the principal immunosuppressive TGF-beta isoforms overexpressed by tumors, and sensitizes tumors to immune checkpoint inhibitors.
Presenter: Tina Gruosso
Session: Poster Display session 1
Resources:
Abstract
1996 - High NAMPT expression and anti-tumor activity of NAMPT inhibitor in adult T-cell leukemia/lymphoma
Presenter: Tomohiro Kozako
Session: Poster Display session 1
Resources:
Abstract
4307 - TPX-0046 is a novel and potent RET/SRC inhibitor for RET-driven cancers
Presenter: Alexander Drilon
Session: Poster Display session 1
Resources:
Abstract
4869 - In Vivo Evaluation of Cisplatin-loaded PEG-PCL Block Copolymeric Nanoparticles for Anticancer Drug Delivery
Presenter: Yingtzu Yen
Session: Poster Display session 1
Resources:
Abstract