Skip to main content

Table 4 Evaluation of segmentation accuracy of PSD and AG in different dataset (i.e., VGlP, HCP-DA, and HCP-YA). The method accuracies are evaluated using Dice-Sørensen coefficients (DSC), Recall, and Precision. Root mean squared (RMS) differences are expressed in cm3 for the PSD volume and mm3 for the AG volume

From: Deep learning segmentation of peri-sinus structures from structural magnetic resonance imaging: validation and normative ranges across the adult lifespan

  

DSC

(std)

Recall

(std)

Precision (std)

RMS

(std)

R

(p-value)

PSD

VGlP

80.3 (4.3)

82.4 (5.6)

78.4 (4.4)

0.61 (0.42)

0.95 (< 0.001)

HCP-YA

79.5 (3.4)

82.5 (3.2)

77.0 (5.4)

0.58 (0.44)

0.97 (< 0.001)

HCP-DA

77.3 (3.8)

82.7 (4.5)

76.2 (2.6)

1.11 (0.31)

0.88 (< 0.001)

AG

VGlP

76.6 (13.4)

75.1 (16.4)

79.5 (12.3)

26.60 (43.96)

0.97 (< 0.001)

HCP-YA

75.5 (12.1)

75.5 (13.2)

81.1 (7.7)

10.57 (12.74)

0.98 (< 0.001)

HCP-DA

69.9 (15.6)

69.9 (16.3)

80.4 (15.7)

9.50 (10.68)

0.98 (< 0.001)