基于影像组学的低级别胶质瘤引发癫痫风险评估方法研究

低级别脑胶质瘤是青少年中最为常见的脑胶质瘤，由于其病灶具有刺激性，相比其他类型的颅脑肿瘤更易引起癫痫。在很多情况下，癫痫发作就是低级别脑胶质瘤患者的首发症状或唯一症状。癫痫的发作和抗癫痫药物的副作用严重影响了患者的生存质量。对低级别脑胶质瘤患者进行无创的癫痫风险评估和癫痫发作类型预测，对不同风险级别的患者采取不同的干预手段，能够大大提高脑胶质瘤的综合治疗效果。本项目拟采用新兴的影像组学分析方法，利用磁共振图像，针对低级别脑胶质瘤引起癫痫的危险因素难以量化以及癫痫风险难以个体化预测的问题，提取反映低级别脑胶质瘤引起癫痫发作危险因素的定量化肿瘤位置和传统影像组学特征，以及它们之间的交互作用，构建影像组学标签，研发能够进行个体化精准分类的预测模型，为临床医生和患者提供简便易用的低级别脑胶质瘤引起癫痫风险评估和癫痫类型预测工具。

Low grade gliomas (LGG; World Health Organization grade II) are the most common type of primary brain tumor in young adults. For its damage to the brain tissue, a majority of patients with LGG experience tumor-related epilepsy during the course of the disease. The impact of tumor-related epilepsy on quality of life for patients with LGG is profound due to life-threatening complications associated with epilepsy onset as well as long-term cognitive damage induced by the use of antiepileptic drugs. While imaging features may reflect the underlying pathophysiology of LGG, we could investigate the association between the LGG-related seizures and imaging features including tumor location, tumor shape, textural features and the interactions among them. Based on the quantitative imaging features, a radiomics-based prediction model could be proposed for individualized evaluation of seizure risk and prediction of seizure type.