Integrating multiscale topology in digital pathology with pyramidal graph convolutional networks

arXiv:2403.15068v1 Announce Type: cross
Abstract: Graph convolutional networks (GCNs) have emerged as a powerful alternative to multiple instance learning with convolutional neural networks in digital pathology, offering superior handling of structural information across various spatial ranges - a crucial aspect of learning from gigapixel H&E-stained whole slide images (WSI). However, graph message-passing algorithms often suffer from oversmoothing when aggregating a large neighborhood. Hence, effective modeling of multi-range interactions relies on the careful construction of the graph. Our proposed multi-scale GCN …

abstract arxiv convolutional neural networks cs.cv digital digital pathology eess.iv graph images information instance multiple networks neural networks pathology spatial topology type