Distinguishing True Progression From Radionecrosis After Stereotactic Radiation Therapy for Brain Metastases With Machine Learning and Radiomics

Abstract

Purpose: Treatment effect or radiation necrosis after stereotactic radiosurgery (SRS) for brain metastases is a common phenomenon often indistinguishable from true progression. Radiomics is an emerging field that promises to improve on conventional imaging. In this study, we sought to apply a radiomics-based prediction model to the problem of diagnosing treatment effect after SRS. Methods and Materials: We included patients in the Johns Hopkins Health System who were treated with SRS for brain metastases who subsequently underwent resection for symptomatic growth. We also included cases of likely treatment effect in which lesions grew but subsequently regressed spontaneously. Lesions were segmented semiautomatically on preoperative T1 postcontrast and T2 fluid-attenuated inversion recovery magnetic resonance imaging, and radiomic features were extracted with software developed in-house. Top-performing features on univariate logistic regression were entered into a hybrid feature selection/classification model, IsoSVM, with parameter optimization and further feature selection performed using leave-one-out cross-validation. Final model performance was assessed by 10-fold cross-validation with 100 repeats. All cases were independently reviewed by a board-certified neuroradiologist for comparison. Results: We identified 82 treated lesions across 66 patients, with 77 lesions having pathologic confirmation. There were 51 radiomic features extracted per segmented lesion on each magnetic resonance imaging sequence. An optimized IsoSVM classifier based on top-ranked radiomic features had sensitivity and specificity of 65.38% and 86.67%, respectively, with an area under the curve of 0.81 on leave-one-out cross-validation. Only 73% of cases were classifiable by the neuroradiologist, with a sensitivity of 97% and specificity of 19%. Conclusions: Radiomics holds promise for differentiating between treatment effect and true progression in brain metastases treated with SRS. A predictive model built on radiomic features from an institutional cohort performed well on cross-validation testing. These results warrant further validation in independent datasets. Such work could prove invaluable for guiding management of individual patients and assessing outcomes of novel interventions.

PET/MRI Radiomics in Patients With Brain Metastases

“…Peng et al (37) evaluated the usefulness of MRI radiomics for this important question. Sixty-six patients with 82 lesions treated with stereotactic radiosurgery and imaging findings on contrast-enhanced T1 and FLAIR sequences suspicious for tumor recurrence were included in the study.…”

Multiparametric radiomics methods for breast cancer tissue characterization using radiological imaging

“…Radiomics use texture features to define potential quantitative metrics from radiological images [1][2][3][4][5][6][7][8][9][10][11].The texture features extracted are based on several properties inherent to image data, such as, gray-level distribution [12], inter-voxel relationships [13][14][15][16][17], and shape [18]. The goal of radiomics is to provide a quantitative framework for a radiological biopsy of tissue, which could be correlated to the underlying tissue biology.…”

Radiomics for radiation oncologists: are we ready to go?

“…Radiomic analysis has shown very promising results in this field, especially in lung 92 and brain disease. [93][94][95] As an example of this, in lung SBRT for NSCLC, Mattonen et al 81,92 have demonstrated the ability of quantitative CT analysis to provide early prediction of recurrence versus radiation damage. This analysis was based on higher-density HU consolidation changes and GCLM-derived texture modifications detected as early as 2-5 months after SBRT.…”