CTA Radiomics Model Distinguishes Symptomatic From Silent Vertebrobasilar

Researchers at Beijing Tiantan Hospital and the Beijing Neurosurgical Institute (Capital Medical University) developed machine-learning models to distinguish symptomatic from asymptomatic unruptured spontaneous intracranial vertebrobasilar artery dissection (sIVBD) using routine CT angiography. In a retrospective single-center study published in Frontiers in Neurology, 173 patients were evaluated between May 2018 and September 2024; 56 were symptomatic and 117 asymptomatic. The best-performing approach combined clinical variables, conventional CTA features, and a cross-fitted radiomics probability among four prespecified models. The study highlights the challenge posed by sIVBD’s varied presentations and uncertain natural history, where some cases stay stable while others lead to stroke, subarachnoid hemorrhage, or neurological deterioration.