Persistent Homology for Fast Tumor Segmentation in Whole Slide Histology Images

Abstract

Automated tumor segmentation in Hematoxylin & Eosin stained histology images is an essential step towards a computer-aided diagnosis system. In this work we propose a novel tumor segmentation approach for a histology whole-slide image (WSI) by exploring the degree of connectivity among nuclei using the novel idea of persistent homology profiles. Our approach is based on 3 steps: 1) selection of exemplar patches from the training dataset using convolutional neural networks (CNNs); 2) construction of persistent homology profiles based on topological features; 3) classification using variant of k-nearest neighbors (k-NN). Extensive experimental results favor our algorithm over a conventional CNN.