Related Experiment Video
Updated: Jul 10, 2026
Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging
Published on: June 7, 2020
A multimodal MRI-radiomics deep learning model for survival risk stratification after gamma knife radiosurgery in
Yijun Chen1, Qingyu Yuan2, Christina K Cramer1
1Department of Radiation Oncology, Wake Forest University School of Medicine, Winston-Salem, NC, United States.
Background:
Brain metastasis (BM) is a high-mortality complication occurring in 20-40% of cancer patients. While Gamma Knife (GK) radiosurgery is a primary treatment, individualized prognostic prediction remains limited. This study develops and validates a multimodal deep-learning framework for overall survival risk stratification after GK.
Patients And Methods:
This multicenter retrospective study included 875 patients across three centers. A mask-guided multi-scale encoder was applied to extract MRI features. The proposed model integrated full MRI, grid-based MRI patches, radiomics, and consistently available clinical variables to generate a patient-level log-risk score for overall survival. Performance was assessed via time-dependent AUC, C-index, and Decision Curve Analysis (DCA).
Results:
The model achieved 1-year AUCs of 0.870 (Training), 0.755 (Internal Val), 0.740 (External Val 1), and 0.788 (External Val 2). C-indices remained moderate across validation cohorts (0.655, 0.653, and 0.649). Multivariable Cox regression showed that the model-derived risk score was independently associated with overall survival across all cohorts. Using a training-derived exploratory threshold of 0.17, the model stratified patients into high- and low-risk groups with significant differences in overall survival across all cohorts. DCA suggested potential net benefit at 12 months.
Conclusion:
The proposed multimodal model showed consistent but moderate discrimination for overall survival stratification in BM patients. By integrating multimodal data, the framework may provide incremental prognostic information for post-GK risk stratification. Further recalibration, incorporation of comprehensive clinical variables, and prospective validation are warranted before clinical implementation.
