Breast MRI Segmentation and Ki-67 High- and Low-Expression Prediction Algorithm Based on Deep Learning

Table 1

Comparison of different algorithms.

Method	Literature	DSC	PPV	Sensitivity
U-Net	Dalmış et al. [37]	0.87	0.86	0.89
Connected-U-Nets	Baccouche et al. [38]	0.89	0.90	0.91
BTS-GAN	Haq et al. [39]	0.90	0.92	0.91
CNN+SVM	Our method	0.94	0.93	0.94