Abstract
This study investigated the effectiveness of pre-treatment quantitative MRI and clinical features along with machine learning techniques to predict local failure in patients with brain metastasis treated with hypo-fractionated stereotactic radiation therapy (SRT). The predictive models were developed using the data from 100 patients (141 lesions) and evaluated on an independent test set with data from 20 patients (30 lesions). Quantitative MRI radiomic features were derived from the treatment-planning contrast-enhanced T1w and T2-FLAIR images. A multi-phase feature reduction and selection procedure was applied to construct an optimal quantitative MRI biomarker for predicting therapy outcome. The performance of standard clinical features in therapy outcome prediction was evaluated using a similar procedure. Survival analyses were conducted to compare the long-term outcome of the two patient cohorts (local control/failure) identified based on prediction at pre-treatment, and standard clinical criteria at last patient follow-up after SRT. The developed quantitative MRI biomarker consists of four features with two features quantifying heterogeneity in the edema region, one feature characterizing intra-tumour heterogeneity, and one feature describing tumour morphology. The predictive models with the radiomic and clinical feature sets yielded an AUC of 0.87 and 0.62, respectively on the independent test set. Incorporating radiomic features into the clinical predictive model improved the AUC of the model by up to 16%, relatively. A statistically significant difference was observed in survival of the two patient cohorts identified at pre-treatment using the radiomics-based predictive model, and at post-treatment using the the RANO-BM criteria. Results of this study revealed a good potential for quantitative MRI radiomic features at pre-treatment in predicting local failure in relatively large brain metastases undergoing SRT, and is a step forward towards a precision oncology paradigm for brain metastasis.
Highlights
Over the past decades, medical imaging has advanced in four distinct aspects including medical devices, imaging agents, standardized protocols for quantitative imaging and digital image analysis[10]
This study explored the efficacy of quantitative magnetic resonance imaging (MRI) coupled with machine learning techniques in a priori prediction of the LC/LF outcome in brain metastasis treated with hypo-fractionated stereotactic radiation therapy (SRT)
The feature reduction/selection framework selected four radiomic features derived from treatment-planning contrast-enhanced T1-weighted (CE-T1w) and T2-FLAIR images as the optimal quantitative MRI biomarker for predicting outcome
Summary
Medical imaging has advanced in four distinct aspects including medical devices (hardware), imaging agents, standardized protocols for quantitative imaging and digital image analysis[10]. A number of previous studies have integrated quantitative imaging and genomic data analysis for further biological interpretation or better patient stratification in precision o ncology[23,24,25,26,27,28,29,30] Such parallel analyses have revealed important links between radiomic features and tumour g enetics[31,32,33,34]. A total of 440 features were derived from the tumour core and the peri-tumoural regions, using the CE-T1w and T2-FLAIR images acquired at pre-treatment Their model with selected clinical variables could predict LC outcome with a mean area under the receiver operating characteristic (ROC) curve (AUC) of 0.67. The efficacy of the developed predictive models in differentiating patients in terms of survival was investigated and compared with those based on clinical criteria at post-treatment
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
