Data augmentation guided breast tumor segmentation based on generative adversarial neural networks

Abstract

Breast tumor segmentation built on Dynamic Contrast-Enhanced Magnetic Resonance Imaging is a noteworthy phase for the quantifiable radiomics study of breast cancer. Manual tumor explanation is an inefficient method and encompasses medical associates, influenced, persuaded to error, and inter-user divergence. The quantities of contemporary preparations have exposed the competence of deep learning depictions in image segmentation. At this point, we designate a 3D Connected-AUNets for tumor segmentation from 3D MRIs built on encoder–decoder design. Owing to a constrained training dataset size, a generative adversarial networks channel is complementary to modernizing the input image itself to recognize the shared decoder and implement added controls on its layers. Based on the preliminary segmentation of Connected-AUNets, a fully connected 3D condition random field is used to improve segmentation results by determining 2D neighbor areas and 3D volume statistics. Furthermore, 3D connected components assessment is used to sustain around large components and reduce segmentation noise. The proposed system has been estimated on two regularly available datasets, apparently INbreast and the Curated Breast Imaging Subset of Digital Database for Screening Mammography. The proposed system has also been evaluated using a private dataset. The experimental significances show that the proposed model outperforms the state-of-the-art processes for breast tumor segmentation.