Skip to main content
EJNMMI Research

Table 3 Correlation coefficients (ϱ) between the distance metrics and the intensity-based (dis)similarity parameters (calculated in three different manners: α, β, γ; see details in the text)

From: Automated procedure assessing the accuracy of HRCT–PET registration applied in functional virtual bronchoscopy

Masking

(dis)similarity parameter

Pearson (s)

MI (s)

NMI (s)

HKL (d)

L1norm (d)

L2norm2 (d)

α

0.15

0.02

0.02

− 0.07

0.25

0.22

β

0.38

0.56

0.5

0.45

− 0.04

− 0.09

γ

0.4

0.6

0.51

− 0.02

0.07

0.09

  1. MI mutual information, NMI normalised mutual information, HKL Kullback–Leibler divergence, L1Norm L1 norm or Manhattan norm, L2norm2 square L2 norm or square Euclidean distance, (s) similarity parameter, (d) dissimilarity parameter (data are rounded to two significant digits, the highest correlation coefficient is emphasized in bold text)
Back to article page