Zi-Xiang Kuai

Multi-Objective Representation based Dynamic Prototype Learning for Unsupervised DCE-MRI Breast Tumor Segmentation

Unsupervised segmentation is a potential means to detect the breast tumors from DCE-MRI without using any annotated images, which can provide a coarse prior for several downstream tasks. However, the existing unsupervised segmentation methods are prone to collapse due to the presence of large backgr…