Table 2 Comparison of different model backbones for the classifier

From: A deep learning-based approach to enhance accuracy and feasibility of long-term high-resolution manometry examinations

Method

Precision (%)

Recall (%)

F1-score (%)

Classifier Backbone: MobileNet

86.13 ± 2.98

94.07 ± 2.46

89.57 ± 2.59

Classifier Backbone: GoogLeNet

83.48 ± 4.39

94.05 ± 2.16

88.00 ± 3.23

Classifier Backbone: EfficientNet

83.86 ± 5.55

94.01 ± 1.80

88.23 ± 4.06

Classifier Backbone: RegNet

80.94 ± 4.59

91.06 ± 3.96

85.27 ± 4.25

  1. We report the average metrics using a fivefold cross-validation along with their respective standard deviation (±). Bold numbers indicate the highest performance in the respective category.
Back to article page