Discrimination of Alzheimer’s disease using hippocampus texture features from MRI

Background: Alzheimer’s disease is the commonest cause of dementia and is fatal. Early detection of Alzheimer’s disease is important because treatment may be most useful if introduced early.

Objective: Analyse the utility of using the texture features of hippocampus MRI as the biomarker to identify Alzheimer’s disease.

Materials and methods: We chose the MRI of 146 normal controls and 133 Alzheimer’s disease patients from the Alzheimer’s disease neuroimaging initiative website. Sixty-nine texture features were extracted from the hippocampus region of interest as obtained from an automatic segmentation procedure. The best features were selected based on principal component analysis to decide which ones resulted in the highest rate of good classification. The proposed method is validated using a Support Vector Machine classifier.

Results: The accuracy of the proposed method on discrimination of Alzheimer’s disease patients is 93.6%.

Conclusion: The texture features taken only from hippocampus gives better discrimination between Alzheimer’s disease and normal controls. Therefore, the textures of hippocampus are much affected by Alzheimer’s disease.