Table 5 Quantitative results of models trained with different encoders on the LPBA40 dataset.

From: Hybrid transformer and convolution iteratively optimized pyramid network for brain large deformation image registration

Variant model

\(\:\text{D}\text{S}\text{C}\uparrow\:\)

\(\:\text{A}\text{S}\text{S}\text{D}\downarrow\:\)

\(\:\left|{J}_{\varnothing\:}\right|<0\downarrow\:\)

\(\:\text{T}\left(\text{s}\right)\downarrow\:\)

\(\text{Params}\:\:\downarrow\:\)

Pure_ConvBlock

0.736±0.014

1.415±0.066

< 0.0082%

0.400

5156752

Res_ConvBlock

0.735±0.015

1.413±0.069

< 0.0168%

0.385

5149824

ExtraPrior + SE_ConvBlock

0.728±0.017

1.438±0.069

< 0.0097%

0.415

5172012

ExtraPrior_ConvBlock(Ours)

0.737±0.013,

1.404±0.066

< 0.0165%

0.419

5753352

Back to article page