Hippocampus segmentation based on Attention U-Net model

According to surveys, in the past 20 years, Alzheimer's disease has become the top ten cause of death globally. The volume measurement of the hippocampus is a prerequisite for early prevention and complementary diagnosis of Alzheimer's disease. For this reason, by adding the Attention mechanism and residual module to the original U-net network, it is used to segment the hippocampus region automatically. To demonstrate the method's efficacy, the experiment was carried out on the EADC-ADNI Harmonized Protocol Project data set. And compared with other traditional methods.