Skip to main content

Table 5 The difference in clinical measures between automated segmentation and manual segmentation, as well between measurements by different human observers

From: Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

(a) Absolute difference     
  Auto vs Manual O1 vs O2 O2 vs O3 O3 vs O1
  (n = 600) (n = 50) (n = 50) (n = 50)
LVEDV (mL) 6.1 (5.3) 6.1 (4.4) 8.8 (4.8) 4.8 (3.1)
LVESV (mL) 5.3 (4.9) 4.1 (4.2) 6.7 (4.2) 7.1 (3.8)
LVM (gram) 6.9 (5.5) 4.2 (3.2) 6.6 (4.9) 6.5 (4.8)
RVEDV (mL) 8.5 (7.1) 11.1 (7.2) 6.2 (4.6) 8.7 (5.8)
RVESV (mL) 7.2 (6.8) 15.6 (7.8) 6.6 (5.5) 11.7 (6.9)
(b) Relative difference     
LVEDV (%) 4.1 (3.5) 4.2 (3.1) 6.3 (3.3) 3.4 (2.2)
LVESV (%) 9.5 (9.5) 6.8 (7.5) 12.5 (8.5) 11.7 (5.1)
LVM (%) 8.3 (7.6) 4.4 (3.3) 6.0 (3.7) 6.7 (4.6)
RVEDV (%) 5.6 (4.6) 8.0 (5.0) 4.2 (3.1) 5.7 (3.6)
RVESV (%) 11.8 (12.2) 30.6 (15.5) 10.9 (8.3) 16.9 (9.2)
  1. The first column shows the difference between automated and manual segmentations on a test set of 600 subjects. The second to fourth columns show the inter-observer variability, which is evaluated on a randomly selected set of 50 subjects, each being analysed by three different human observers (O1, O2, O3) independently. The mean and standard deviation (in parenthesis) of the absolute difference and relative difference are reported