Cells are Actors: Social Network Analysis with Classical ML for SOTA Histology Image Classification

TL;DR

This paper introduces a scalable, explainable network analysis approach using classical machine learning to improve colorectal cancer grading from histology images, outperforming existing methods.

Contribution

The authors propose a novel network analysis method that models cell interactions for cancer grading, offering scalability, explainability, and high performance over deep learning approaches.

Findings

Achieved state-of-the-art accuracy in CRA grading

Method is scalable to millions of cells

Provides highly interpretable features

Abstract

Digitization of histology images and the advent of new computational methods, like deep learning, have helped the automatic grading of colorectal adenocarcinoma cancer (CRA). Present automated CRA grading methods, however, usually use tiny image patches and thus fail to integrate the entire tissue micro-architecture for grading purposes. To tackle these challenges, we propose to use a statistical network analysis method to describe the complex structure of the tissue micro-environment by modelling nuclei and their connections as a network. We show that by analyzing only the interactions between the cells in a network, we can extract highly discriminative statistical features for CRA grading. Unlike other deep learning or convolutional graph-based approaches, our method is highly scalable (can be used for cell networks consist of millions of nodes), completely explainable, and computationally inexpensive. We create cell networks on a broad CRC histology image dataset, experiment with our method, and report state-of-the-art performance for the prediction of three-class CRA grading.