MRI radiomics did not robustly outperform clinical predictors after head and neck chemoradiotherapy
A best MRI model reached AUC 0.91, but across 366 configurations radiomics did not consistently outperform a simple clinical model.
Tag
machine-learning
CyberKnife dose models found size-dependent but non-monotonic brain metastasis control
Tumour-size strata showed non-monotonic BED–control relationships, while machine-learning performance remained unvalidated outside a single retrospective centre.
Machine learning stratified survival after palliative radiotherapy for bone metastases
A decision tree model identified interleukin-8, hemoglobin, and lymphocyte count as key survival predictors after palliative radiotherapy.
Explainable machine learning predicts structure-specific quality assurance performance in intensity-modulated radiotherapy
Anatomy- and dose-based machine learning predicted gamma passing rates accurately for organs at risk, but less reliably for target volumes.