Deep radial basis function networks with subcategorization for mitosis detection in breast histopathology images
Abstract: Highlights•Candidate proposal model provides detailed mitotic candidates, reducing missed detections.•Joint training of classification and clustering capture representative RBF centers.•RBF subcategorization scheme guides feature learning, making members in each subcategory closer in feature space.•RBF subcategorization scheme handles the intra-class diversity and inter-class similarity.
External IDs:dblp:journals/mia/TangC24
Loading