Figure 2
From: Comparative validation of AI and non-AI methods in MRI volumetry to diagnose Parkinsonian syndromes
(a) Segmentation results of CNN-based V-Net (left 3D images in first column and red-highlighted areas in second column) and FS (right 3D images in first column and blue-highlighted areas in second column) for each brain structure. (b) Segmentation results of ViT-based UNETR (left 3D images in first column and red-highlighted areas in second column) and FS (right 3D images in first column and blue-highlighted areas in second column) for each brain structure.
