DCE-MRI based Breast Intratumor Heterogeneity Analysis via Dual Attention Deep Clustering Network and its Application in Molecular Typing

More attention has been paid to the precision and personalized treatment of breast cancer, which is a primary risk factor that threatens the females lives. It is momentous for diagnosis, analysis and therapy of tumors to lucubrate breast intratumor heterogeneity. We propose a DCE-MRI dynamic mode based self-supervised dual attention deep clustering network (DADCN) which is utilized to achieve the individual precise segmentation of breast intratumor heterogeneity region in this paper. The specific representations learned by the graph attention network are consciously combined with the deep abstract features extracted from the deep convolutional neural network. Then the structural information of the voxel in breast tumor is mined by spreading on the graph. The model is self-supervised by dual relative loss and residual loss and the clustering graph is measured by graph cut loss. We also employ Pearson, Spearman and Kendall analysis to evaluate degree of correlation between clustering results and intratumor heterogeneity represented by molecular typing. We ultimately detect that the degree of intratumor heterogeneity is automatically determined via segmentation of the heterogeneity region, to accomplish the noninvasive individual molecular typing prediction of breast cancer. The number of clusters in breast intratumor heterogeneity region is an independent biomarker for the diagnosis of benign and malignant tumors and prediction of basal-like molecular typing.