Deep Convolutional Neural Networks-Based Automatic Breast Segmentation and Mass Detection in DCE-MRI

Figure 1

The framework of breast region segmentation and breast mass detection. The entire framework is divided into two parts. The upper part is image segmentation. Breast region mask is obtained by importing the image into segmentation network such as U-Net++ and U-Net. The breast region can be segmented by masking the input image. The following part is the target detection. The breast region image was input to Faster RCNN to obtain the location coordinates and probability of the mass.