AI-based response assessment and prediction in longitudinal imaging for brain metastases treated with stereotactic radiosurgery

2025-09-08

AI Summary

Manual assessment of longitudinal MRI in brain metastasis (BM) patients post-stereotactic radiosurgery (SRS) suffers from low efficiency and poor early therapeutic response prediction. Method: We propose an automated analytical framework integrating data-driven clustering with graph machine learning (GML), establishing a lesion-level longitudinal imaging pipeline that enables automatic multi-timepoint MRI registration, lesion annotation, and spatiotemporal modeling. The framework identifies five canonical lesion growth trajectories and supports flexible timepoint inputs for early treatment response prediction. Contribution/Results: Evaluated on a cohort of 896 lesions, the full framework achieves an AUC of 0.90 for 12-month treatment outcome prediction, while the GML submodel alone attains 0.88—both significantly outperforming conventional methods. This interpretable, high-accuracy, and clinically feasible AI solution advances personalized BM surveillance and clinical decision support.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Humans and AI: Brain-Sensing and Analysis
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Brain Metastases (BM) are a large contributor to mortality of patients with cancer. They are treated with Stereotactic Radiosurgery (SRS) and monitored with Magnetic Resonance Imaging (MRI) at regular follow-up intervals according to treatment guidelines. Analyzing and quantifying this longitudinal imaging represents an intractable workload for clinicians. As a result, follow-up images are not annotated and merely assessed by observation. Response to treatment in longitudinal imaging is being studied, to better understand growth trajectories and ultimately predict treatment success or toxicity as early as possible. In this study, we implement an automated pipeline to curate a large longitudinal dataset of SRS treatment data, resulting in a cohort of 896 BMs in 177 patients who were monitored for >360 days at approximately two-month intervals at Lausanne University Hospital (CHUV). We use a data-driven clustering to identify characteristic trajectories. In addition, we predict 12 months lesion-level response using classical as well as graph machine learning Graph Machine Learning (GML). Clustering revealed 5 dominant growth trajectories with distinct final response categories. Response prediction reaches up to 0.90 AUC (CI95%=0.88-0.92) using only pre-treatment and first follow-up MRI with gradient boosting. Similarly, robust predictive performance of up to 0.88 AUC (CI95%=0.86-0.90) was obtained using GML, offering more flexibility with a single model for multiple input time-points configurations. Our results suggest potential automation and increased precision for the comprehensive assessment and prediction of BM response to SRS in longitudinal MRI. The proposed pipeline facilitates scalable data curation for the investigation of BM growth patterns, and lays the foundation for clinical decision support systems aiming at optimizing personalized care.

Problem

• Automating analysis of longitudinal MRI for brain metastases
• Predicting treatment response using machine learning methods
• Identifying growth trajectories to optimize personalized care

Innovation

• Automated pipeline curates large longitudinal SRS dataset
• Data-driven clustering identifies characteristic growth trajectories
• Graph machine learning predicts lesion-level response accurately