Visual Computing for Industry, Biomedicine, and Art

Table 5 Quantitative comparison of segmentation performance with different methods on the BUSI [21] dataset

From: Multi-task approach based on combined CNN-transformer for efficient segmentation and classification of breast tumors in ultrasound images

Model	Accuracy (%)	DC (%)	IoU (%)	Sensitivity (%)
U-Net [8]	95.55	77.19	62.71	74.74
UT-Net [55]	95.58	78.08	64.02	77.93
LinkNet [54]	96.07	81.22	68.21	81.77
TransUNet [17]	96.10	81.57	68.69	82.05
D-LinkNet [54]	96.21	81.72	68.68	82.56
Axial-DeepLab [40]	96.31	82.01	69.00	80.36
ATFE-Net [52]	96.32	82.46	69.73	82.78
Ours	94.04	83.42	72.56	80.10

Back to article page