Skip to main content
. Author manuscript; available in PMC: 2024 Jun 6.
Published in final edited form as: Neuroimage. 2023 Feb 4;269:119929. doi: 10.1016/j.neuroimage.2023.119929

Fig. 2.

Fig. 2.

CNN models used in this study to classify ADNI AD participants and controls. For each architecture, several numbers of channels c were tested. The number of channels c corresponds to the number of 3D convolutional kernels used in each convolutional layer. Increasing numbers of layers were tested for ModelE. The Residual Block used in ModelE concatenates its input with the output of two 3 ×3 ×3 × c convolutional layers.