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
4085 - A Phase 1, Open-Label, Dose-Escalation Study to Evaluate the Safety, Tolerability, Pharmacokinetics, and Antitumor Activity of ADCT-601 in Patients with Advanced Solid Tumors
Presenter: Anthony Tolcher
Session: Poster Display session 1
Resources:
Abstract
1054 - Safety, efficacy, and pharmacokinetic (PK) profile of cosibelimab, an anti‐PD‐L1 antibody, in patients (pts) with advanced cancers
Presenter: Philip Clingan
Session: Poster Display session 1
Resources:
Abstract
4264 - A Phase I study of tinostamustine in patients (pts) with advanced solid tumours
Presenter: Alain Mita
Session: Poster Display session 1
Resources:
Abstract
3811 - Lurbinectedin (LUR) in combination with Irinotecan (IRI) in patients (pts) with advanced solid tumors
Presenter: Santiago Ponce Aix
Session: Poster Display session 1
Resources:
Abstract
1311 - A phase I study of varlitinib (VAR; ASLAN001) an oral pan-HER tyrosine kinase inhibitor (TKI) combined with mFOLFIRI chemotherapy in advanced solid tumors
Presenter: Aaron Tan
Session: Poster Display session 1
Resources:
Abstract
3482 - Phase I study of lapatinib and trametinib in patients with KRAS mutant colorectal, non-small cell lung and pancreatic cancer
Presenter: Sanne Huijberts
Session: Poster Display session 1
Resources:
Abstract
4749 - Pharmacokinetic (PK) and updated survival data from the Canadian Cancer Trials Group IND.226 study of durvalumab ± tremelimumab in combination with platinum-doublet chemotherapy
Presenter: Desiree Hao
Session: Poster Display session 1
Resources:
Abstract
4530 - A Phase 2a clinical trial combining ALRN-6924 and palbociclib for the treatment of patients with tumors harboring wild-type p53 and MDM2 amplification or MDM2/CDK4 co-amplification
Presenter: Funda Meric-Bernstam
Session: Poster Display session 1
Resources:
Abstract
4280 - Updated Efficacy and Safety of Entrectinib in Patients with NTRK Fusion-Positive Tumors: Integrated Analysis of STARTRK-2, STARTRK-1 and ALKA-372-001
Presenter: Christian Rolfo
Session: Poster Display session 1
Resources:
Abstract
6144 - An international randomized cross-over bio-equivalence study of oral paclitaxel + HM30181 compared with weekly intravenous (IV) paclitaxel in patients with advanced solid tumors
Presenter: Christopher Jackson
Session: Poster Display session 1
Resources:
Abstract