Visual Computing for Industry, Biomedicine, and Art

Table 2 Comparison of evaluation metrics for the six segmentation algorithms

From: PlaqueNet: deep learning enabled coronary artery plaque segmentation from coronary computed tomography angiography

Algorithm	Precision (%)	Recall (%)	F1score (%)
ResNet	89.943 ± 5.146	76.330 ± 4.479	67.860 ± 3.075
ResNest	89.992 ± 2.875	71.399 ± 10.525	79.305 ± 8.558
ResNetVC	89.081 ± 3.944	80.586 ± 4.429	84.797 ± 3.512
ResNetVD	88.717 ± 3.944	80.185 ± 3.124	84.800 ± 3.844
ResNext	90.200 ± 3.818	70.123 ± 9.483	79.407 ± 8.896
AResNet	93.423 ± 1.936	90.623 ± 1.918	92.354 ± 1.452

Back to article page