In this paper, we presented a fully automated algorithm (AUGC) for breast UST image segmentation.
Quantitative evaluation of segmentation performance suggests that AUGC is superior to other three algorithms, ACCD, watershed, and CCRG, shown in Figures 3 and 4 and Table 2.
AUGC is also superior to other approaches in terms of the real-time capacity.
High UST image quality can improve the performance of AUGC in breast segmentation, suggesting an even greater potential of AUGC to facilitate clinical diagnosis by using whole-breast UST images
Caption: Figure 1: The flowchart of the proposed AUGC algorithm.
Caption: Figure 2: A case study of AUGC in UST image segmentation.
(a) Ground truth produced by manual delineating, (b) AUGC, (c) ACCU, (d) watershed, and (e) CCRG.
Caption: Figure 4: Accuracy evaluation of AUGC, ACCD, watershed, and CCRG segmentation methods, (a) represents the values of D, (b) is the values of J, and (c) denotes the values of FP.
Time consumption is decreased dramatically from manual segmentation to AUGC. The figure can be enlarged to view details.