Prediction of Alzheimer’s Disease Using DHO-Based Pretrained CNN Model

Figure 3

Hippocampal image patches: (a) without patches segmentation labels, (b) patches overlaid with segmentation labels before manual correction, and (c) segmentation tags added to the patches following manual adjustment. Subj1, Subj2, and Subj3 are three people from each of the three different study groups which were chosen at random [21, 22].