Although post-traumatic epilepsy (PTE) is a common complication of traumatic brain injury (TBI), the relationship between these conditions is unclear, early PTE detection and prevention being major unmet clinical challenges. This study aims to identify imaging biomarkers that distinguish PTE and non-PTE subjects among TBI survivors based on a magnetic resonance imaging (MRI) dataset. We performed tensor-based morphometry to analyze brain shape changes associated with TBI and to derive imaging features for statistical group comparison. Additionally, machine learning was used to identify structural anomalies associated with brain lesions. Automatically generated brain lesion maps were used to identify brain regions where lesion load may indicate an increased incidence of PTE. Statistical analysis suggests that lesions in the temporal lobes, cerebellum, and the right occipital lobe are associated with an increased PTE incidence.

中文翻译：

---

基于磁共振成像和机器学习的创伤后癫痫的神经解剖学标记

尽管创伤后癫痫（PTE）是颅脑外伤（TBI）的常见并发症，但这些情况之间的关系尚不清楚，早期PTE的发现和预防是临床上尚未解决的主要挑战。这项研究的目的是基于磁共振成像（MRI）数据集，识别在TBI幸存者中区分PTE和非PTE受试者的成像生物标记物。我们进行了基于张量的形态分析，以分析与TBI相关的大脑形状变化，并导出影像特征以进行统计组比较。另外，机器学习被用来识别与脑损伤相关的结构异常。使用自动生成的脑部病变图来识别脑部区域，其中病变负荷可能表明PTE发生率增加。统计分析表明，颞叶病变，