Figure 3
From: Comparative validation of AI and non-AI methods in MRI volumetry to diagnose Parkinsonian syndromes
Architecture of CNN-based 3D segmentation using V-Net. ResBlock, MaxPooling, and UpConvolution were used to reduce the depth, height, and width. The output shown in the figure is the segmentation of pallidum. (Conv convolution layer, BN batch normalization).
