本研究通过对18例老年轻度认知障碍(Mild Cognitive Impairment,MCI)患者及18例健康对照者,采用灰度共生矩阵和游程长矩阵方法提取受试者胼胝体部位的三维纹理特征参数(对比度、逆差距、熵、短游程因子、长游程因子、灰度不均匀度因子、游程长不均匀度因子),研究比较各纹理特征在两组之间的差异。研究结果显示,所提取的7个纹理参数中除灰度不均匀度因子外,其余均存在显著性差异。研究表明三维纹理特征能一定程度上反映MCI患者胼胝体部位的病理变化,从而有助于MCI的早期诊断。
To explore the 3D texture features of corpus callosum in magnetic resonance images from the patients with mild cognitive impairment (MCI), this paper selected Tl-weighted MRI of 18 MCI patients and 18 normal controls, extracted 3D texture features of the corpus callosum, including contrast, inverse difference moment, entropy, short run emphasis, long run emphasis, grey level nonuniformity, run length nonuniformity from the gray level co-occurrence matrix and run length matrix. The results showed that the 3D texture featm'es had significant differences between two groups except grey level nonuniformity. It indicated that 3D texture analysis can reflect the pathological changes of corpus callosum in patients with MCI, and it may be helpful to the MCI's early diagnosis.