A Multidimensional Connectomics- and Radiomics-Based Advanced Machine-Learning Framework to Distinguish Radiation Necrosis from True Progression in Brain Metastases

SIMPLE SUMMARY: Diagnosing true progression (TP) versus radiation necrosis (RN) in brain metastases treated with stereotactic radiosurgery is a significant clinical challenge that can lead to delays of care or unnecessary neurosurgical procedures. We implemented a novel machine-learning framework that uses both multiparametic radiomics (mpRad) and tumor connectomics analysis to probe the textural properties and structural networks within radiographically progressive lesions, respectively. Our predictive model was able to distinguish histopathologically proven cases of TP from RN with excellent discrimination and may ultimately serve as a useful tool to inform clinical decision making. ABSTRACT: We introduce tumor connectomics, a novel MRI-based complex graph theory framework that describes the intricate network of relationships within the tumor and surrounding tissue, and combine this with multiparametric radiomics (mpRad) in a machine-learning approach to distinguish radiation necrosis (RN) from true progression (TP). Pathologically confirmed cases of RN vs. TP in brain metastases treated with SRS were included from a single institution. The region of interest was manually segmented as the single largest diameter of the T1 post-contrast (T1C) lesion plus the corresponding area of T2 FLAIR hyperintensity. There were 40 mpRad features and 6 connectomics features extracted, as well as 5 clinical and treatment factors. We developed an Integrated Radiomics Informatics System (IRIS) based on an Isomap support vector machine (IsoSVM) model to distinguish TP from RN using leave-one-out cross-validation. Class imbalance was resolved with differential misclassification weighting during model training using the IRIS. In total, 135 lesions in 110 patients were analyzed, including 43 cases (31.9%) of pathologically proven RN and 92 cases (68.1%) of TP. The top-performing connectomics features were three centrality measures of degree, betweenness, and eigenvector centralities. Combining these with the 10 top-performing mpRad features, an optimized IsoSVM model was able to produce a sensitivity of 0.87, specificity of 0.84, AUC-ROC of 0.89 (95% CI: 0.82–0.94), and AUC-PR of 0.94 (95% CI: 0.87–0.97).