Non-invasive and precise prediction for survivals of glioma patients is challenging. With the development of artificial intelligence, much more potential lies in the preoperative conventional/advanced MR imaging (T1 weighted imaging, T2 weighted imaging, FLAIR, contrast-enhanced T1 weighted imaging, diffusion-weighted imaging, and perfusion imaging) could be excavated to aid prediction of patients' prognosis in the frame of molecular pathology of gliomas. The creation of a registry for primary glioma with detailed survival data, molecular pathology, radiological data and with sufficient sample size for deep learning (>1000) provides opportunities for personalized prediction of survival of glioma patients with non-invasiveness and precision.

