Table 4 Performance on segmentation metrics of the variational method (VM) only, and standard and hybrid pipeline in brain tumour segmentation.

From: Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning

BraTS:

VM

Standard

Hybrid

DICE

0.746 \({\pm }\) 0.148

0.596 \({\pm }\) 0.308

0.832 \({\pm }\) 0.130

JACCARD

0.614 \({\pm }\) 0.159

0.490 \({\pm }\) 0.314

0.730 \({\pm }\) 0.170

VS

0.792 \({\pm }\) 0.156

0.633 \({\pm }\) 0.316

0.863 \({\pm }\) 0.132

HD

28.3 \({\pm }\) 18.0

49.4 \({\pm }\) 29.5

36.8 \({\pm }\) 20.5

TPR

0.637 \({\pm }\) 0.165

0.800 \({\pm }\) 0.262

0.884 \({\pm }\) 0.141

TNR

0.999 \({\pm }\) 0.001

0.998 \({\pm }\) 0.001

0.999 \({\pm }\) 0.001

Time (s)

46.6 \({\pm }\) 6.76

3.71 \({\pm }\) 0.102

3.73 \({\pm }\) 0.123

  1. Units given as mean \({\pm }\) standard deviation.