Objective This article studied the texture features of cingulum of patients with Alzheimer's disease(AD)and mild cognitive impairment(MCI)based on magnetic resonance images and analyzed them according to different gender. The purpose was to explore the application of texture features in early diagnosis of AD. Methods Texture analysis was applied to MR images of 14 AD，20 MCI and 18 normal controls(NC). Texture features extracted from gray level co-occurrence matrix and run-length matrix were analyzed between each two groups. The texture features that existed significant differences among groups were used as input features in a classification procedure based on support vector machines(SVM). Results Compared with NC group，texture features including energy and run length non-uniformity of AD and MCI group were significantly different on anterior and posterior cingulum. The results grouped by gender showed that except the differences between AD and NC group，male posterior cingulum showed significant differences between MCI and NC group and MCI and AD group (P<0.05),female anterior cingulum showed significant differences between MCI and NC group(P<0.05). The classification accuracy for AD and NC group of male posterior cingulum was 90%. Conclusion The results indicated that the pathological changes in cingulum could be reflected by texture features and the pathological changes may be different in the two genders. This may be helpful to early diagnosis of AD.