ROBUST NUCLEUS CLASSIFICATION WITH ITERATIVE GRAPH REPRESENTATIONAL LEARNING

Classifying nuclei communities in histology images is vital for early cancer treatment, but it remains challenging due to the similar structure of nuclei communities. To address this, we propose an iterative neural graph improvement and broadcasting approach. Starting with a baseline classification, a fully connected graph is constructed with nuclei as nodes. Node and edge features are updated and exchanged along a Hamiltonian path, removing weak connections. This process filters communities by disconnecting weakly connected nodes and iterates until stability is reached. Loose nodes from this refining stage are then assigned to their closest community clusters. Experimental results on two public datasets demonstrate the superiority of the proposed approach over state-of-the-art methods.