Source Themes

We proposed a hybrid ViT and convolutional U-net for brain MRI image registration, which achieved a higher dice score than ViT-V-Net and VoxelMorph. Quantitative and qualitative comparison results demonstrate that our model outperforms the previous ViT-based and convolution-based networks and achieved a better dice score of 79.7% in OASIS dataset.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.