Skip to main content

Table 5 Comparison of volume overlap error (VOE) for atlas-based segmentation against deep-learning-based segmentation with four organs (heart, liver, kidney, stomach). Averages and standard deviations are listed for ten test cases

From: Comparative clinical evaluation of atlas and deep-learning-based auto-segmentation of organ structures in liver cancer

Test CaseHeartLiverRight kidneyLeft kidneyStomach
CatlasCdeepCatlasCdeepCatlasCdeepCatlasCdeepCatlasCdeep
# 18.496.8310.2210.5812.8810.3130.1518.3784.8331.01
# 211.6813.249.957.8117.6218.3814.3919.6245.9639.11
# 37.3411.178.3913.4412.4211.0763.9012.4265.7334.86
# 411.1712.736.737.348.868.548.3410.3181.1754.12
# 513.8711.8910.2911.649.397.5920.7635.0772.4231.16
# 626.6011.9534.3215.3215.1715.6614.3217.8455.5835.68
# 724.396.6620.4111.028.109.039.9912.0032.2141.44
# 819.3412.1213.2910.3015.2715.4116.5812.5339.0223.24
# 97.7410.3413.1412.0740.6613.0620.1514.5985.5142.75
# 1021.0411.488.378.6834.6812.8757.7310.3963.9241.97
Avg SD15.1710.8413.5110.8217.5112.1925.6316.3162.6437.53
6.772.187.832.3610.573.3318.577.0118.107.99
  1. Avg: Average
  2. SD: Standard deviation