DSAI-08 MIXED-EFFECTS DEEP-LEARNING BASED QUANTITATIVE RADIOMIC ANALYSIS OF LONGITUDINAL MAGNETIC RESONANCE IMAGING OF BRAIN METASTASES PREDICT PRIMARY TUMOR ORIGIN

Abstract BACKGROUND Brain metastases, secondary brain tumors originating from cancers elsewhere in the body, can present with focal neurologic deficits without systemic symptoms and are usually evaluated using magnetic resonance imaging (MRI). Multimodal imaging methods are usually used to determine the primary cancer source. Radiomic analysis involves extracting quantitative features from medical images using data-characterization algorithms. Recent advances in deep learning and radiomics, which quantitatively analyze imaging data, offer the potential for improved prediction of primary tumor origin through MR imaging analysis. Using longitudinal MRI data, we developed and validated a mixed-effects neural network model for predicting the primary origin of brain metastases. METHODS We used the open-source dataset from 5 different institutions made available by Ocaña-Tienda et al. (2023) to build the model. Radiomic feature selection was performed, followed by building a novel quantitative radiomic approach that uses mixed-effects deep learning to analyze longitudinal radiomic data of brain metastases from MRI scans. Model performance was evaluated using receiver operating characteristic curve (ROC) analysis. RESULTS Our mixed-effects model demonstrated high accuracy (90.5%), precision (92.7%), recall (87.8%), and F1 score (90.2%), with an area under the ROC (AUC-ROC) curve of 0.944 in identifying the primary tumor site. The nested mixed-effects model was superior to the fixed-effects model with an AUC-ROC of 0.719. CONCLUSIONS Our mixed-effects neural network model accurately predicts the primary origin of brain metastases with high internal and external validity. Using advanced radiomic feature selection and deep learning techniques. Our model achieved high-performance metrics, thus providing a promising tool for enhancing diagnostic capability and tailoring patient-specific management strategies. Further research could explore adding more data from other institutions and studying the effect of integrating this model in clinical workflows to optimize patient care.