Table 11 Comparison of \({{\text{M}}}_{{\text{seg}}+{\text{spleen}}}\) with studies that developed liver w/wo spleen segmentation.

From: Fully automated deep learning based auto-contouring of liver segments and spleen on contrast-enhanced CT images

 

Ours

Lee et al. 202218

Tian et al. 201917

Mean (\({{\text{C}}}_{{\text{RT}}}\) test, N = 33)

Median (\({{\text{C}}}_{{\text{RT}}}\) test, N = 33)

Mean (\({{\text{C}}}_{{\text{LS}}}\), N = 33)

Median (\({{\text{C}}}_{{\text{LS}}}\), N = 33)

Median (Data 1, N = 35)

Median (Data 1, N = 35)

Mean

Seg 1

0.89

0.93

0.912

0.94

0.64

0.66

0.9246

Seg 2

0.86

0.86

0.91

0.92

Seg 3

0.91

0.91

0.88

0.88

Seg 4

0.90

0.92

0.82

0.85

Seg 5–8*

0.97

0.98

0.86

0.84

Spleen

0.99

0.99

0.91

0.96

0.96

0.95

 
  1. *Lee et al. 2022 reported separate results of segment 5 thru 8. We averaged the reported median values.
Back to article page