3D Residual Dense Convolutional Network for Diagnosis of Alzheimer’s Disease and Mild Cognitive Impairment

摘要

Alzheimer's disease (AD) is a common and incurable dementia, so it is particularly important to correctly distinguish AD from normal people. In recent years, the development of deep learning has pointed out a new direction for the study of AD classification. This paper proposes a 3D residual densely connected convolutional network for AD and mild cognitive impairment (MCI) diagnosis. First, the Residual Dense Block (RDB) is used to expand the information flow to avoid the disappearance of gradients. Then we use the global feature fusion method to comprehensively consider the shallow and deep features to improve the accuracy of classification. This paper mainly uses the MRI data of the ADNI dataset for experiments to prove the superior performance of the proposed model.