Table 2 Mean (SD) dice similarity coefficient score (DSC), Jaccard index (JI), precision (PR), recall (RC), volume of error (VOE), relative volume difference (RVD), and mean curve distance (MCD) by Canal-Net (ours), ConvLSTM 3D U-Net (ours), MPL 3D U-Net (ours), 3D U-Net, SegNet, and 2D U-Net Net by five-fold cross-validation.

From: Canal-Net for automatic and robust 3D segmentation of mandibular canals in CBCT images using a continuity-aware contextual network

Ā 

DSC

JI

PR

RC

RVD

VOE

MCD (mm)

Canal-Net

0.87 ± 0.05

0.80 ± 0.06

0.89 ± 0.06

0.88 ± 0.06

0.14 ± 0.04

0.10 ± 0.04

0.62 ± 0.10

ConvLSTM

3D U-Net

0.85 ± 0.08*

0.77 ± 0.08*

0.87 ± 0.08*

0.86 ± 0.09*

0.17 ± 0.05*

0.13 ± 0.05*

0.66 ± 0.12*

MPL

3D U-Net

0.84 ± 0.06†

0.75 ± 0.07†

0.88 ± 0.07†

0.82 ± 0.08†

0.19 ± 0.04†

0.14 ± 0.06†

0.69 ± 0.15†

3D U-Net

0.83 ± 0.07—

0.74 ± 0.07—

0.85 ± 0.08—

0.84 ± 0.09—

0.19 ± 0.05—

0.15 ± 0.07—

0.69 ± 0.13—

SegNet

0.84 ± 0.06+

0.77 ± 0.06+

0.85 ± 0.06+

0.85 ± 0.07+

0.18 ± 0.04+

0.14 ± 0.05+

0.78 ± 0.19+

2D U-Net

0.84 ± 0.07Φ

0.77 ± 0.07Φ

0.85 ± 0.07Φ

0.84 ± 0.08Φ

0.18 ± 0.04Φ

0.14 ± 0.05Φ

0.87 ± 0.22Φ

  1. *Significant difference between Canal-Net and ConvLSTM 3D U-Net (p < 0.05).
  2. †Between Canal-Net and MPL 3D U-Net (p < 0.05).
  3. —Between Canal-Net and 3D U-Net (p < 0.05).
  4. +Between Canal-Net and SegNet (p < 0.05).
  5. ΦBetween Canal-Net and 2D U-Net (p < 0.05).