Skip to main content

Table 6 Performance of macMIND and MIND in deep learning-based registration (mean ± std)

From: macJNet: weakly-supervised multimodal image deformable registration using joint learning framework and multi-sampling cascaded MIND

Methods

det (Jϕ(p)) < 0 (‱)

Reg-SubNet with MIND

0.92 ± 0.45

Reg-SubNet with macMIND

0.63 ± 0.22

Joint learning framework with MIND

0.96 ± 0.47

Joint learning framework with macMIND (macJNet)

0.74 ± 0.24

  1. Bold values indicate better results than other methods