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
2182 - Evaluating the prevalence of the expression of PD-L1 in NSCLC specimens with short-duration formalin fixation using IHC 22C3 pharmDx
Presenter: Keiichi Ota
Session: Poster Display session 1
Resources:
Abstract
5255 - [18F]-FDG PET/CT in predicting PD-L1 status in nasopharyngeal carcinoma
Presenter: Liang Zhao
Session: Poster Display session 1
Resources:
Abstract
4910 - Expression of PD-L1 in Chinese Patients with Common Cancers
Presenter: Min Zheng
Session: Poster Display session 1
Resources:
Abstract
4227 - The clearance of EGF by tumor-associated macrophages is suppressed by chemotherapeutic agent cisplatin
Presenter: Irina Larionova
Session: Poster Display session 1
Resources:
Abstract
5222 - VHIO-300 and a thousand one nights, a tale of Precision Medicine
Presenter: Ginevra Caratù
Session: Poster Display session 1
Resources:
Abstract
5668 - Matched Whole-Genome Sequencing and Whole-Exome Sequencing with Circulating Tumor DNA (ctDNA) Analysis are complementary modalities in clinical practice
Presenter: Robin Imperial
Session: Poster Display session 1
Resources:
Abstract
5772 - Exploring the role of genes associated with familial cancer syndromes on the development of multiple primary tumors
Presenter: Atanaska Mitkova
Session: Poster Display session 1
Resources:
Abstract
4784 - Doxorubicin resistance: early and advanced tumors can use two different strategies based on initial and profound abnormalities in microRNA expression signature
Presenter: Volodymyr Halytskiy
Session: Poster Display session 1
Resources:
Abstract
3456 - From tumor transcriptomes to underlying cell type proportions to better predict prognosis and response to treatments
Presenter: Yuna Blum
Session: Poster Display session 1
Resources:
Abstract
4976 - Optimization of automated germline DNA extraction from non-tumoral formalin-fixed paraffin embedded (FFPE) tissues
Presenter: Omar Youssef
Session: Poster Display session 1
Resources:
Abstract